{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":1,"outputs":[{"output_type":"stream","text":"['train.csv', 'sample_submission.csv', 'test.csv']\n","name":"stdout"}]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"X_Data = pd.read_csv(\"../input/test.csv\")\nX_Data.head(10)","execution_count":2,"outputs":[{"output_type":"execute_result","execution_count":2,"data":{"text/plain":" pixel0 pixel1 pixel2 ... pixel781 pixel782 pixel783\n0 0 0 0 ... 0 0 0\n1 0 0 0 ... 0 0 0\n2 0 0 0 ... 0 0 0\n3 0 0 0 ... 0 0 0\n4 0 0 0 ... 0 0 0\n5 0 0 0 ... 0 0 0\n6 0 0 0 ... 0 0 0\n7 0 0 0 ... 0 0 0\n8 0 0 0 ... 0 0 0\n9 0 0 0 ... 0 0 0\n\n[10 rows x 784 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
pixel0pixel1pixel2pixel3pixel4pixel5pixel6pixel7pixel8pixel9pixel10pixel11pixel12pixel13pixel14pixel15pixel16pixel17pixel18pixel19pixel20pixel21pixel22pixel23pixel24pixel25pixel26pixel27pixel28pixel29pixel30pixel31pixel32pixel33pixel34pixel35pixel36pixel37pixel38pixel39...pixel744pixel745pixel746pixel747pixel748pixel749pixel750pixel751pixel752pixel753pixel754pixel755pixel756pixel757pixel758pixel759pixel760pixel761pixel762pixel763pixel764pixel765pixel766pixel767pixel768pixel769pixel770pixel771pixel772pixel773pixel774pixel775pixel776pixel777pixel778pixel779pixel780pixel781pixel782pixel783
00000000000000000000000000000000000000000...0000000000000000000000000000000000000000
10000000000000000000000000000000000000000...0000000000000000000000000000000000000000
20000000000000000000000000000000000000000...0000000000000000000000000000000000000000
30000000000000000000000000000000000000000...0000000000000000000000000000000000000000
40000000000000000000000000000000000000000...0000000000000000000000000000000000000000
50000000000000000000000000000000000000000...0000000000000000000000000000000000000000
60000000000000000000000000000000000000000...0000000000000000000000000000000000000000
70000000000000000000000000000000000000000...0000000000000000000000000000000000000000
80000000000000000000000000000000000000000...0000000000000000000000000000000000000000
90000000000000000000000000000000000000000...0000000000000000000000000000000000000000
\n
"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"import os\nimport numpy as np\nfrom keras.datasets import mnist\nfrom keras.layers import Input, Dense, Reshape, Flatten, Dropout\nfrom keras.layers import BatchNormalization\nfrom keras.layers.advanced_activations import LeakyReLU\nfrom keras.models import Sequential\nfrom keras.optimizers import Adam\nimport matplotlib.pyplot as plt\n#%matplotlib inline","execution_count":3,"outputs":[{"output_type":"stream","text":"Using TensorFlow backend.\n","name":"stderr"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"class GAN(object):\n def __init__(self, width=28, height=28, channels=1):\n self.width = width\n self.height = height\n self.channels = channels\n self.shape = (self.width , self.height , self.channels)\n self.optimizer = Adam(lr=0.0002, beta_1=0.5, decay=8e-8)\n self.G = self.__generator()\n self.G.compile(loss=\"binary_crossentropy\" , optimizer = self.optimizer)\n self.D = self.__discriminator()\n self.D.compile(loss=\"binary_crossentropy\" , optimizer = self.optimizer, metrics=[\"accuracy\"])\n \n self.stack_generator_discriminator = self.__stack_generator_discriminator()\n self.stack_generator_discriminator.compile(loss=\"binary_crossentropy\", optimizer=self.optimizer)\n self.lossSummary = []\n \n def __generator(self):\n model = Sequential()\n model.add(Dense(256, input_shape=(100,)))\n model.add(LeakyReLU(alpha=0.2))\n model.add(BatchNormalization(momentum=0.8))\n model.add(Dense(512))\n model.add(LeakyReLU(alpha=0.2))\n model.add(BatchNormalization(momentum=0.8))\n model.add(Dense(1024))\n model.add(LeakyReLU(alpha=0.2))\n model.add(BatchNormalization(momentum=0.8))\n model.add(Dense((self.width * self.height * self.channels), activation=\"tanh\"))\n model.add(Reshape((self.width, self.height, self.channels)))\n model.summary()\n return model\n \n def __discriminator(self):\n model = Sequential()\n model.add(Flatten(input_shape = self.shape))\n model.add(Dense(512))\n model.add(LeakyReLU(alpha=0.2))\n model.add(Dense(256))\n model.add(LeakyReLU(alpha=0.2))\n model.add(Dense(1, activation=\"sigmoid\"))\n model.summary()\n return model\n\n def __stack_generator_discriminator(self):\n self.D.Trainabel = False;\n model = Sequential()\n model.add(self.G)\n model.add(self.D)\n return model\n \n def train(self, X_train, epochs = 1000, batch=32, save_interal=100):\n for cnt in range(epochs):\n random_index = np.random.randint(0, len(X_train) - np.int64(batch/2))\n legit_images = X_train[random_index:random_index + np.int64(batch/2)].reshape(np.int64(batch/2)\\\n , self.width, self.height, self.channels) \n gen_noise = np.random.normal(0, 1, (np.int64(batch/2), 100))\n syntetic_images = self.G.predict(gen_noise)\n x_combined_batch = np.concatenate((legit_images, syntetic_images))\n y_combined_batch = np.concatenate((np.ones((np.int64(batch/2), 1)), np.zeros((np.int64(batch/2), 1))))\n\n d_loss = self.D.train_on_batch(x_combined_batch, y_combined_batch)\n\n noise = np.random.normal(0, 1, (batch,100))\n y_mislabled = np.ones((batch,1))\n g_loss = self.stack_generator_discriminator.train_on_batch(noise, y_mislabled)\n self.lossSummary.append((cnt, d_loss[0], d_loss[1], g_loss))\n print ('epoch: %d, [Discriminator :: d_loss: %f :: accuracy %f], [ Generator :: loss: %f]' % (cnt, d_loss[0], d_loss[1]*100, g_loss))\n ","execution_count":19,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"if __name__ == '__main__': \n # Rescale -1 to 1\n X_train = (X_Data.astype(np.float32) - 127.5) / 127.5\n X_train = np.array(X_train)[:,:,np.newaxis]\n X_train.shape\n\n gan = GAN()\n gan.train(X_train)\n ","execution_count":20,"outputs":[{"output_type":"stream","text":"_________________________________________________________________\nLayer (type) Output Shape Param # \n=================================================================\ndense_43 (Dense) (None, 256) 25856 \n_________________________________________________________________\nleaky_re_lu_31 (LeakyReLU) (None, 256) 0 \n_________________________________________________________________\nbatch_normalization_19 (Batc (None, 256) 1024 \n_________________________________________________________________\ndense_44 (Dense) (None, 512) 131584 \n_________________________________________________________________\nleaky_re_lu_32 (LeakyReLU) (None, 512) 0 \n_________________________________________________________________\nbatch_normalization_20 (Batc (None, 512) 2048 \n_________________________________________________________________\ndense_45 (Dense) (None, 1024) 525312 \n_________________________________________________________________\nleaky_re_lu_33 (LeakyReLU) (None, 1024) 0 \n_________________________________________________________________\nbatch_normalization_21 (Batc (None, 1024) 4096 \n_________________________________________________________________\ndense_46 (Dense) (None, 784) 803600 \n_________________________________________________________________\nreshape_7 (Reshape) (None, 28, 28, 1) 0 \n=================================================================\nTotal params: 1,493,520\nTrainable params: 1,489,936\nNon-trainable params: 3,584\n_________________________________________________________________\n_________________________________________________________________\nLayer (type) Output Shape Param # \n=================================================================\nflatten_7 (Flatten) (None, 784) 0 \n_________________________________________________________________\ndense_47 (Dense) (None, 512) 401920 \n_________________________________________________________________\nleaky_re_lu_34 (LeakyReLU) (None, 512) 0 \n_________________________________________________________________\ndense_48 (Dense) (None, 256) 131328 \n_________________________________________________________________\nleaky_re_lu_35 (LeakyReLU) (None, 256) 0 \n_________________________________________________________________\ndense_49 (Dense) (None, 1) 257 \n=================================================================\nTotal params: 533,505\nTrainable params: 533,505\nNon-trainable params: 0\n_________________________________________________________________\nepoch: 0, [Discriminator :: d_loss: 0.627645 :: accuracy 59.375000], [ Generator :: loss: 0.542732]\nepoch: 1, [Discriminator :: d_loss: 0.614843 :: accuracy 59.375000], [ Generator :: loss: 0.460862]\nepoch: 2, [Discriminator :: d_loss: 0.584593 :: accuracy 53.125000], [ Generator :: loss: 0.398691]\nepoch: 3, [Discriminator :: d_loss: 0.691155 :: accuracy 50.000000], [ Generator :: loss: 0.372797]\nepoch: 4, [Discriminator :: d_loss: 0.783003 :: accuracy 50.000000], [ Generator :: loss: 0.291161]\nepoch: 5, [Discriminator :: d_loss: 0.767173 :: accuracy 50.000000], [ Generator :: loss: 0.333633]\nepoch: 6, [Discriminator :: d_loss: 0.854826 :: accuracy 50.000000], [ Generator :: loss: 0.311232]\nepoch: 7, [Discriminator :: d_loss: 0.825300 :: accuracy 50.000000], [ Generator :: loss: 0.306407]\nepoch: 8, [Discriminator :: d_loss: 0.876629 :: accuracy 50.000000], [ Generator :: loss: 0.279274]\nepoch: 9, [Discriminator :: d_loss: 0.961230 :: accuracy 50.000000], [ Generator :: loss: 0.253730]\nepoch: 10, [Discriminator :: d_loss: 0.952800 :: accuracy 50.000000], [ Generator :: loss: 0.250268]\nepoch: 11, [Discriminator :: d_loss: 0.937408 :: accuracy 50.000000], [ Generator :: loss: 0.248193]\nepoch: 12, [Discriminator :: d_loss: 0.935942 :: accuracy 50.000000], [ Generator :: loss: 0.249474]\nepoch: 13, [Discriminator :: d_loss: 0.986353 :: accuracy 50.000000], [ Generator :: loss: 0.252182]\nepoch: 14, [Discriminator :: d_loss: 0.997578 :: accuracy 50.000000], [ Generator :: loss: 0.242955]\nepoch: 15, [Discriminator :: d_loss: 0.949270 :: accuracy 50.000000], [ Generator :: loss: 0.233297]\nepoch: 16, [Discriminator :: d_loss: 0.925624 :: accuracy 50.000000], [ Generator :: loss: 0.237858]\nepoch: 17, [Discriminator :: d_loss: 1.018399 :: accuracy 50.000000], [ Generator :: loss: 0.208893]\nepoch: 18, [Discriminator :: d_loss: 0.998631 :: accuracy 50.000000], [ Generator :: loss: 0.238169]\nepoch: 19, [Discriminator :: d_loss: 1.080624 :: accuracy 50.000000], [ Generator :: loss: 0.215060]\nepoch: 20, [Discriminator :: d_loss: 1.030452 :: accuracy 50.000000], [ Generator :: loss: 0.209112]\nepoch: 21, [Discriminator :: d_loss: 1.058493 :: accuracy 50.000000], [ Generator :: loss: 0.237951]\nepoch: 22, [Discriminator :: d_loss: 1.036673 :: accuracy 50.000000], [ Generator :: loss: 0.206010]\nepoch: 23, [Discriminator :: d_loss: 1.031561 :: accuracy 50.000000], [ Generator :: loss: 0.193473]\nepoch: 24, [Discriminator :: d_loss: 1.073496 :: accuracy 50.000000], [ Generator :: loss: 0.222991]\nepoch: 25, [Discriminator :: d_loss: 0.959514 :: accuracy 50.000000], [ Generator :: loss: 0.209164]\nepoch: 26, [Discriminator :: d_loss: 1.042981 :: accuracy 50.000000], [ Generator :: loss: 0.208609]\nepoch: 27, [Discriminator :: d_loss: 1.114482 :: accuracy 50.000000], [ Generator :: loss: 0.193045]\nepoch: 28, [Discriminator :: d_loss: 1.110154 :: accuracy 50.000000], [ Generator :: loss: 0.175185]\nepoch: 29, [Discriminator :: d_loss: 1.000741 :: accuracy 50.000000], [ Generator :: loss: 0.235111]\nepoch: 30, [Discriminator :: d_loss: 1.006849 :: accuracy 50.000000], [ Generator :: loss: 0.211717]\nepoch: 31, [Discriminator :: d_loss: 1.091589 :: accuracy 50.000000], [ Generator :: loss: 0.250869]\nepoch: 32, [Discriminator :: d_loss: 1.073727 :: accuracy 50.000000], [ Generator :: loss: 0.207625]\nepoch: 33, [Discriminator :: d_loss: 0.995676 :: accuracy 50.000000], [ Generator :: loss: 0.192828]\nepoch: 34, [Discriminator :: d_loss: 1.172346 :: accuracy 50.000000], [ Generator :: loss: 0.189368]\nepoch: 35, [Discriminator :: d_loss: 1.105840 :: accuracy 50.000000], [ Generator :: loss: 0.201550]\nepoch: 36, [Discriminator :: d_loss: 1.227430 :: accuracy 50.000000], [ Generator :: loss: 0.201169]\nepoch: 37, [Discriminator :: d_loss: 1.068911 :: accuracy 50.000000], [ Generator :: loss: 0.175356]\nepoch: 38, [Discriminator :: d_loss: 1.259713 :: accuracy 50.000000], [ Generator :: loss: 0.160497]\nepoch: 39, [Discriminator :: d_loss: 1.178331 :: accuracy 50.000000], [ Generator :: loss: 0.166935]\nepoch: 40, [Discriminator :: d_loss: 1.125678 :: accuracy 50.000000], [ Generator :: loss: 0.202745]\nepoch: 41, [Discriminator :: d_loss: 1.166221 :: accuracy 50.000000], [ Generator :: loss: 0.216170]\nepoch: 42, [Discriminator :: d_loss: 1.112669 :: accuracy 50.000000], [ Generator :: loss: 0.190179]\nepoch: 43, [Discriminator :: d_loss: 1.187441 :: accuracy 50.000000], [ Generator :: loss: 0.198595]\nepoch: 44, [Discriminator :: d_loss: 1.191284 :: accuracy 50.000000], [ Generator :: loss: 0.175394]\nepoch: 45, [Discriminator :: d_loss: 1.158302 :: accuracy 50.000000], [ Generator :: loss: 0.185712]\nepoch: 46, [Discriminator :: d_loss: 1.183198 :: accuracy 50.000000], [ Generator :: loss: 0.174958]\nepoch: 47, [Discriminator :: d_loss: 1.216562 :: accuracy 50.000000], [ Generator :: loss: 0.150860]\nepoch: 48, [Discriminator :: d_loss: 1.119068 :: accuracy 50.000000], [ Generator :: loss: 0.187781]\nepoch: 49, [Discriminator :: d_loss: 1.083376 :: accuracy 50.000000], [ Generator :: loss: 0.200137]\nepoch: 50, [Discriminator :: d_loss: 1.206664 :: accuracy 50.000000], [ Generator :: loss: 0.183951]\nepoch: 51, [Discriminator :: d_loss: 1.187468 :: accuracy 50.000000], [ Generator :: loss: 0.183537]\nepoch: 52, [Discriminator :: d_loss: 1.171485 :: accuracy 50.000000], [ Generator :: loss: 0.166912]\n","name":"stdout"},{"output_type":"stream","text":"epoch: 53, [Discriminator :: d_loss: 1.261804 :: accuracy 50.000000], [ Generator :: loss: 0.182535]\nepoch: 54, [Discriminator :: d_loss: 1.164854 :: accuracy 50.000000], [ Generator :: loss: 0.181230]\nepoch: 55, [Discriminator :: d_loss: 1.261063 :: accuracy 50.000000], [ Generator :: loss: 0.156766]\nepoch: 56, [Discriminator :: d_loss: 1.181217 :: accuracy 50.000000], [ Generator :: loss: 0.139948]\nepoch: 57, [Discriminator :: d_loss: 1.182926 :: accuracy 50.000000], [ Generator :: loss: 0.137551]\nepoch: 58, [Discriminator :: d_loss: 1.294302 :: accuracy 50.000000], [ Generator :: loss: 0.199003]\nepoch: 59, [Discriminator :: d_loss: 1.301401 :: accuracy 50.000000], [ Generator :: loss: 0.179412]\nepoch: 60, [Discriminator :: d_loss: 1.216778 :: accuracy 50.000000], [ Generator :: loss: 0.212363]\nepoch: 61, [Discriminator :: d_loss: 1.212484 :: accuracy 50.000000], [ Generator :: loss: 0.222788]\nepoch: 62, [Discriminator :: d_loss: 1.299598 :: accuracy 50.000000], [ Generator :: loss: 0.165057]\nepoch: 63, [Discriminator :: d_loss: 1.245660 :: accuracy 50.000000], [ Generator :: loss: 0.175161]\nepoch: 64, [Discriminator :: d_loss: 1.370698 :: accuracy 50.000000], [ Generator :: loss: 0.173463]\nepoch: 65, [Discriminator :: d_loss: 1.201715 :: accuracy 50.000000], [ Generator :: loss: 0.222796]\nepoch: 66, [Discriminator :: d_loss: 1.235930 :: accuracy 50.000000], [ Generator :: loss: 0.157563]\nepoch: 67, [Discriminator :: d_loss: 1.264741 :: accuracy 50.000000], [ Generator :: loss: 0.180954]\nepoch: 68, [Discriminator :: d_loss: 1.378715 :: accuracy 50.000000], [ Generator :: loss: 0.181665]\nepoch: 69, [Discriminator :: d_loss: 1.305339 :: accuracy 50.000000], [ Generator :: loss: 0.154083]\nepoch: 70, [Discriminator :: d_loss: 1.284258 :: accuracy 50.000000], [ Generator :: loss: 0.156090]\nepoch: 71, [Discriminator :: d_loss: 1.397262 :: accuracy 50.000000], [ Generator :: loss: 0.179645]\nepoch: 72, [Discriminator :: d_loss: 1.362202 :: accuracy 50.000000], [ Generator :: loss: 0.188583]\nepoch: 73, [Discriminator :: d_loss: 1.210627 :: accuracy 50.000000], [ Generator :: loss: 0.152415]\nepoch: 74, [Discriminator :: d_loss: 1.193546 :: accuracy 50.000000], [ Generator :: loss: 0.141565]\nepoch: 75, [Discriminator :: d_loss: 1.358547 :: accuracy 50.000000], [ Generator :: loss: 0.161653]\nepoch: 76, [Discriminator :: d_loss: 1.264221 :: accuracy 50.000000], [ Generator :: loss: 0.174133]\nepoch: 77, [Discriminator :: d_loss: 1.349932 :: accuracy 50.000000], [ Generator :: loss: 0.157064]\nepoch: 78, [Discriminator :: d_loss: 1.237539 :: accuracy 50.000000], [ Generator :: loss: 0.169640]\nepoch: 79, [Discriminator :: d_loss: 1.252780 :: accuracy 50.000000], [ Generator :: loss: 0.197979]\nepoch: 80, [Discriminator :: d_loss: 1.355903 :: accuracy 50.000000], [ Generator :: loss: 0.230164]\nepoch: 81, [Discriminator :: d_loss: 1.202534 :: accuracy 50.000000], [ Generator :: loss: 0.154817]\nepoch: 82, [Discriminator :: d_loss: 1.424922 :: accuracy 50.000000], [ Generator :: loss: 0.141207]\nepoch: 83, [Discriminator :: d_loss: 1.413162 :: accuracy 50.000000], [ Generator :: loss: 0.169982]\nepoch: 84, [Discriminator :: d_loss: 1.271501 :: accuracy 50.000000], [ Generator :: loss: 0.135482]\nepoch: 85, [Discriminator :: d_loss: 1.358307 :: accuracy 50.000000], [ Generator :: loss: 0.264128]\nepoch: 86, [Discriminator :: d_loss: 1.303911 :: accuracy 50.000000], [ Generator :: loss: 0.178262]\nepoch: 87, [Discriminator :: d_loss: 1.318215 :: accuracy 50.000000], [ Generator :: loss: 0.140083]\nepoch: 88, [Discriminator :: d_loss: 1.436340 :: accuracy 50.000000], [ Generator :: loss: 0.161893]\nepoch: 89, [Discriminator :: d_loss: 1.225492 :: accuracy 50.000000], [ Generator :: loss: 0.169474]\nepoch: 90, [Discriminator :: d_loss: 1.276847 :: accuracy 50.000000], [ Generator :: loss: 0.146149]\nepoch: 91, [Discriminator :: d_loss: 1.372111 :: accuracy 50.000000], [ Generator :: loss: 0.148514]\nepoch: 92, [Discriminator :: d_loss: 1.353739 :: accuracy 50.000000], [ Generator :: loss: 0.110098]\nepoch: 93, [Discriminator :: d_loss: 1.538988 :: accuracy 50.000000], [ Generator :: loss: 0.150976]\nepoch: 94, [Discriminator :: d_loss: 1.316212 :: accuracy 50.000000], [ Generator :: loss: 0.162287]\nepoch: 95, [Discriminator :: d_loss: 1.457214 :: accuracy 50.000000], [ Generator :: loss: 0.147060]\nepoch: 96, [Discriminator :: d_loss: 1.221027 :: accuracy 50.000000], [ Generator :: loss: 0.172111]\nepoch: 97, [Discriminator :: d_loss: 1.506858 :: accuracy 50.000000], [ Generator :: loss: 0.153665]\nepoch: 98, [Discriminator :: d_loss: 1.279640 :: accuracy 50.000000], [ Generator :: loss: 0.194424]\nepoch: 99, [Discriminator :: d_loss: 1.348262 :: accuracy 50.000000], [ Generator :: loss: 0.163604]\nepoch: 100, [Discriminator :: d_loss: 1.268374 :: accuracy 50.000000], [ Generator :: loss: 0.174242]\nepoch: 101, [Discriminator :: d_loss: 1.419640 :: accuracy 50.000000], [ Generator :: loss: 0.154527]\nepoch: 102, [Discriminator :: d_loss: 1.367541 :: accuracy 50.000000], [ Generator :: loss: 0.155590]\nepoch: 103, [Discriminator :: d_loss: 1.424656 :: accuracy 50.000000], [ Generator :: loss: 0.174131]\nepoch: 104, [Discriminator :: d_loss: 1.227195 :: accuracy 50.000000], [ Generator :: loss: 0.168548]\nepoch: 105, [Discriminator :: d_loss: 1.393506 :: accuracy 50.000000], [ Generator :: loss: 0.135986]\nepoch: 106, [Discriminator :: d_loss: 1.390882 :: accuracy 50.000000], [ Generator :: loss: 0.169232]\nepoch: 107, [Discriminator :: d_loss: 1.459316 :: accuracy 50.000000], [ Generator :: loss: 0.154021]\nepoch: 108, [Discriminator :: d_loss: 1.438264 :: accuracy 50.000000], [ Generator :: loss: 0.144154]\nepoch: 109, [Discriminator :: d_loss: 1.287070 :: accuracy 53.125000], [ Generator :: loss: 0.165142]\nepoch: 110, [Discriminator :: d_loss: 1.419369 :: accuracy 50.000000], [ Generator :: loss: 0.271843]\nepoch: 111, [Discriminator :: d_loss: 1.336784 :: accuracy 53.125000], [ Generator :: loss: 0.222470]\nepoch: 112, [Discriminator :: d_loss: 1.743817 :: accuracy 50.000000], [ Generator :: loss: 0.126184]\nepoch: 113, [Discriminator :: d_loss: 1.648847 :: accuracy 50.000000], [ Generator :: loss: 0.152279]\nepoch: 114, [Discriminator :: d_loss: 1.662541 :: accuracy 50.000000], [ Generator :: loss: 0.136285]\nepoch: 115, [Discriminator :: d_loss: 1.479676 :: accuracy 50.000000], [ Generator :: loss: 0.137229]\nepoch: 116, [Discriminator :: d_loss: 1.495419 :: accuracy 50.000000], [ Generator :: loss: 0.144902]\nepoch: 117, [Discriminator :: d_loss: 1.373918 :: accuracy 50.000000], [ Generator :: loss: 0.180008]\nepoch: 118, [Discriminator :: d_loss: 1.447286 :: accuracy 50.000000], [ Generator :: loss: 0.164319]\nepoch: 119, [Discriminator :: d_loss: 1.250963 :: accuracy 50.000000], [ Generator :: loss: 0.197305]\nepoch: 120, [Discriminator :: d_loss: 1.535634 :: accuracy 50.000000], [ Generator :: loss: 0.154710]\nepoch: 121, [Discriminator :: d_loss: 1.330476 :: accuracy 50.000000], [ Generator :: loss: 0.146436]\nepoch: 122, [Discriminator :: d_loss: 1.419131 :: accuracy 50.000000], [ Generator :: loss: 0.125868]\nepoch: 123, [Discriminator :: d_loss: 1.319034 :: accuracy 50.000000], [ Generator :: loss: 0.131083]\nepoch: 124, [Discriminator :: d_loss: 1.405621 :: accuracy 50.000000], [ Generator :: loss: 0.174339]\nepoch: 125, [Discriminator :: d_loss: 1.289455 :: accuracy 50.000000], [ Generator :: loss: 0.169831]\nepoch: 126, [Discriminator :: d_loss: 1.306103 :: accuracy 50.000000], [ Generator :: loss: 0.203302]\nepoch: 127, [Discriminator :: d_loss: 1.502120 :: accuracy 50.000000], [ Generator :: loss: 0.144730]\nepoch: 128, [Discriminator :: d_loss: 1.512131 :: accuracy 50.000000], [ Generator :: loss: 0.138034]\nepoch: 129, [Discriminator :: d_loss: 1.426876 :: accuracy 50.000000], [ Generator :: loss: 0.154425]\nepoch: 130, [Discriminator :: d_loss: 1.559871 :: accuracy 50.000000], [ Generator :: loss: 0.146805]\nepoch: 131, [Discriminator :: d_loss: 1.503764 :: accuracy 50.000000], [ Generator :: loss: 0.275419]\nepoch: 132, [Discriminator :: d_loss: 1.638395 :: accuracy 50.000000], [ Generator :: loss: 0.119382]\nepoch: 133, [Discriminator :: d_loss: 1.414926 :: accuracy 50.000000], [ Generator :: loss: 0.148280]\nepoch: 134, [Discriminator :: d_loss: 1.575815 :: accuracy 50.000000], [ Generator :: loss: 0.124332]\nepoch: 135, [Discriminator :: d_loss: 1.441265 :: accuracy 50.000000], [ Generator :: loss: 0.262837]\nepoch: 136, [Discriminator :: d_loss: 1.454747 :: accuracy 50.000000], [ Generator :: loss: 0.141133]\n","name":"stdout"},{"output_type":"stream","text":"epoch: 137, [Discriminator :: d_loss: 1.516602 :: accuracy 50.000000], [ Generator :: loss: 0.156206]\nepoch: 138, [Discriminator :: d_loss: 1.589737 :: accuracy 50.000000], [ Generator :: loss: 0.128130]\nepoch: 139, [Discriminator :: d_loss: 1.589271 :: accuracy 50.000000], [ Generator :: loss: 0.112536]\nepoch: 140, [Discriminator :: d_loss: 1.292278 :: accuracy 50.000000], [ Generator :: loss: 0.159763]\nepoch: 141, [Discriminator :: d_loss: 1.354824 :: accuracy 50.000000], [ Generator :: loss: 0.153074]\nepoch: 142, [Discriminator :: d_loss: 1.306815 :: accuracy 50.000000], [ Generator :: loss: 0.139989]\nepoch: 143, [Discriminator :: d_loss: 1.290767 :: accuracy 50.000000], [ Generator :: loss: 0.150505]\nepoch: 144, [Discriminator :: d_loss: 1.471421 :: accuracy 50.000000], [ Generator :: loss: 0.149496]\nepoch: 145, [Discriminator :: d_loss: 1.434818 :: accuracy 50.000000], [ Generator :: loss: 0.138068]\nepoch: 146, [Discriminator :: d_loss: 1.379696 :: accuracy 50.000000], [ Generator :: loss: 0.149659]\nepoch: 147, [Discriminator :: d_loss: 1.341009 :: accuracy 50.000000], [ Generator :: loss: 0.245928]\nepoch: 148, [Discriminator :: d_loss: 1.297626 :: accuracy 50.000000], [ Generator :: loss: 0.106079]\nepoch: 149, [Discriminator :: d_loss: 1.587193 :: accuracy 50.000000], [ Generator :: loss: 0.155363]\nepoch: 150, [Discriminator :: d_loss: 1.314198 :: accuracy 50.000000], [ Generator :: loss: 0.142597]\nepoch: 151, [Discriminator :: d_loss: 1.576397 :: accuracy 50.000000], [ Generator :: loss: 0.144457]\nepoch: 152, [Discriminator :: d_loss: 1.486239 :: accuracy 50.000000], [ Generator :: loss: 0.173661]\nepoch: 153, [Discriminator :: d_loss: 1.394295 :: accuracy 50.000000], [ Generator :: loss: 0.145774]\nepoch: 154, [Discriminator :: d_loss: 1.441411 :: accuracy 50.000000], [ Generator :: loss: 0.181400]\nepoch: 155, [Discriminator :: d_loss: 1.491190 :: accuracy 50.000000], [ Generator :: loss: 0.164909]\nepoch: 156, [Discriminator :: d_loss: 1.529256 :: accuracy 50.000000], [ Generator :: loss: 0.112122]\nepoch: 157, [Discriminator :: d_loss: 1.342676 :: accuracy 50.000000], [ Generator :: loss: 0.171093]\nepoch: 158, [Discriminator :: d_loss: 1.468588 :: accuracy 50.000000], [ Generator :: loss: 0.122096]\nepoch: 159, [Discriminator :: d_loss: 1.389058 :: accuracy 50.000000], [ Generator :: loss: 0.180569]\nepoch: 160, [Discriminator :: d_loss: 1.407955 :: accuracy 50.000000], [ Generator :: loss: 0.149749]\nepoch: 161, [Discriminator :: d_loss: 1.588715 :: accuracy 50.000000], [ Generator :: loss: 0.152074]\nepoch: 162, [Discriminator :: d_loss: 1.435134 :: accuracy 50.000000], [ Generator :: loss: 0.148058]\nepoch: 163, [Discriminator :: d_loss: 1.385010 :: accuracy 50.000000], [ Generator :: loss: 0.133564]\nepoch: 164, [Discriminator :: d_loss: 1.437479 :: accuracy 50.000000], [ Generator :: loss: 0.274014]\nepoch: 165, [Discriminator :: d_loss: 1.639170 :: accuracy 50.000000], [ Generator :: loss: 0.153328]\nepoch: 166, [Discriminator :: d_loss: 1.540875 :: accuracy 50.000000], [ Generator :: loss: 0.137464]\nepoch: 167, [Discriminator :: d_loss: 1.537705 :: accuracy 50.000000], [ Generator :: loss: 0.112364]\nepoch: 168, [Discriminator :: d_loss: 1.368118 :: accuracy 50.000000], [ Generator :: loss: 0.123890]\nepoch: 169, [Discriminator :: d_loss: 1.477973 :: accuracy 50.000000], [ Generator :: loss: 0.159063]\nepoch: 170, [Discriminator :: d_loss: 1.363075 :: accuracy 50.000000], [ Generator :: loss: 0.156348]\nepoch: 171, [Discriminator :: d_loss: 1.319874 :: accuracy 50.000000], [ Generator :: loss: 0.141684]\nepoch: 172, [Discriminator :: d_loss: 1.389069 :: accuracy 50.000000], [ Generator :: loss: 0.139832]\nepoch: 173, [Discriminator :: d_loss: 1.446198 :: accuracy 50.000000], [ Generator :: loss: 0.144961]\nepoch: 174, [Discriminator :: d_loss: 1.408229 :: accuracy 50.000000], [ Generator :: loss: 0.164660]\nepoch: 175, [Discriminator :: d_loss: 1.425987 :: accuracy 50.000000], [ Generator :: loss: 0.187087]\nepoch: 176, [Discriminator :: d_loss: 1.381111 :: accuracy 50.000000], [ Generator :: loss: 0.151288]\nepoch: 177, [Discriminator :: d_loss: 1.294043 :: accuracy 50.000000], [ Generator :: loss: 0.140377]\nepoch: 178, [Discriminator :: d_loss: 1.578311 :: accuracy 50.000000], [ Generator :: loss: 0.187797]\nepoch: 179, [Discriminator :: d_loss: 1.610048 :: accuracy 50.000000], [ Generator :: loss: 0.169456]\nepoch: 180, [Discriminator :: d_loss: 1.424895 :: accuracy 50.000000], [ Generator :: loss: 0.127136]\nepoch: 181, [Discriminator :: d_loss: 1.380180 :: accuracy 50.000000], [ Generator :: loss: 0.232188]\nepoch: 182, [Discriminator :: d_loss: 1.571237 :: accuracy 50.000000], [ Generator :: loss: 0.147611]\nepoch: 183, [Discriminator :: d_loss: 1.473265 :: accuracy 50.000000], [ Generator :: loss: 0.153122]\nepoch: 184, [Discriminator :: d_loss: 1.500994 :: accuracy 50.000000], [ Generator :: loss: 0.160662]\nepoch: 185, [Discriminator :: d_loss: 1.419277 :: accuracy 50.000000], [ Generator :: loss: 0.156603]\nepoch: 186, [Discriminator :: d_loss: 1.519405 :: accuracy 50.000000], [ Generator :: loss: 0.162198]\nepoch: 187, [Discriminator :: d_loss: 1.541296 :: accuracy 50.000000], [ Generator :: loss: 0.122274]\nepoch: 188, [Discriminator :: d_loss: 1.504106 :: accuracy 50.000000], [ Generator :: loss: 0.177507]\nepoch: 189, [Discriminator :: d_loss: 1.411706 :: accuracy 50.000000], [ Generator :: loss: 0.145314]\nepoch: 190, [Discriminator :: d_loss: 1.539264 :: accuracy 50.000000], [ Generator :: loss: 0.141015]\nepoch: 191, [Discriminator :: d_loss: 1.448635 :: accuracy 50.000000], [ Generator :: loss: 0.127502]\nepoch: 192, [Discriminator :: d_loss: 1.449988 :: accuracy 50.000000], [ Generator :: loss: 0.176821]\nepoch: 193, [Discriminator :: d_loss: 1.442992 :: accuracy 50.000000], [ Generator :: loss: 0.166924]\nepoch: 194, [Discriminator :: d_loss: 1.558171 :: accuracy 50.000000], [ Generator :: loss: 0.144709]\nepoch: 195, [Discriminator :: d_loss: 1.362617 :: accuracy 50.000000], [ Generator :: loss: 0.126935]\nepoch: 196, [Discriminator :: d_loss: 1.429020 :: accuracy 50.000000], [ Generator :: loss: 0.133710]\nepoch: 197, [Discriminator :: d_loss: 1.341821 :: accuracy 50.000000], [ Generator :: loss: 0.135432]\nepoch: 198, [Discriminator :: d_loss: 1.275096 :: accuracy 50.000000], [ Generator :: loss: 0.211345]\nepoch: 199, [Discriminator :: d_loss: 1.374227 :: accuracy 50.000000], [ Generator :: loss: 0.127942]\nepoch: 200, [Discriminator :: d_loss: 1.386322 :: accuracy 50.000000], [ Generator :: loss: 0.174097]\nepoch: 201, [Discriminator :: d_loss: 1.452397 :: accuracy 50.000000], [ Generator :: loss: 0.184643]\nepoch: 202, [Discriminator :: d_loss: 1.522329 :: accuracy 50.000000], [ Generator :: loss: 0.132308]\nepoch: 203, [Discriminator :: d_loss: 1.307881 :: accuracy 50.000000], [ Generator :: loss: 0.186634]\nepoch: 204, [Discriminator :: d_loss: 1.503362 :: accuracy 50.000000], [ Generator :: loss: 0.170748]\nepoch: 205, [Discriminator :: d_loss: 1.473291 :: accuracy 50.000000], [ Generator :: loss: 0.139203]\nepoch: 206, [Discriminator :: d_loss: 1.430230 :: accuracy 50.000000], [ Generator :: loss: 0.136660]\nepoch: 207, [Discriminator :: d_loss: 1.381807 :: accuracy 50.000000], [ Generator :: loss: 0.174949]\nepoch: 208, [Discriminator :: d_loss: 1.301314 :: accuracy 50.000000], [ Generator :: loss: 0.146291]\nepoch: 209, [Discriminator :: d_loss: 1.446334 :: accuracy 50.000000], [ Generator :: loss: 0.144372]\nepoch: 210, [Discriminator :: d_loss: 1.368390 :: accuracy 50.000000], [ Generator :: loss: 0.187170]\nepoch: 211, [Discriminator :: d_loss: 1.600896 :: accuracy 50.000000], [ Generator :: loss: 0.174465]\nepoch: 212, [Discriminator :: d_loss: 1.605455 :: accuracy 50.000000], [ Generator :: loss: 0.122326]\nepoch: 213, [Discriminator :: d_loss: 1.351387 :: accuracy 50.000000], [ Generator :: loss: 0.156609]\nepoch: 214, [Discriminator :: d_loss: 1.419937 :: accuracy 50.000000], [ Generator :: loss: 0.135013]\nepoch: 215, [Discriminator :: d_loss: 1.456186 :: accuracy 50.000000], [ Generator :: loss: 0.169462]\nepoch: 216, [Discriminator :: d_loss: 1.311342 :: accuracy 50.000000], [ Generator :: loss: 0.191906]\nepoch: 217, [Discriminator :: d_loss: 1.544707 :: accuracy 50.000000], [ Generator :: loss: 0.183774]\nepoch: 218, [Discriminator :: d_loss: 1.445191 :: accuracy 50.000000], [ Generator :: loss: 0.147602]\nepoch: 219, [Discriminator :: d_loss: 1.398952 :: accuracy 50.000000], [ Generator :: loss: 0.152895]\nepoch: 220, [Discriminator :: d_loss: 1.454037 :: accuracy 50.000000], [ Generator :: loss: 0.126009]\n","name":"stdout"},{"output_type":"stream","text":"epoch: 221, [Discriminator :: d_loss: 1.350795 :: accuracy 50.000000], [ Generator :: loss: 0.144890]\nepoch: 222, [Discriminator :: d_loss: 1.408745 :: accuracy 50.000000], [ Generator :: loss: 0.190473]\nepoch: 223, [Discriminator :: d_loss: 1.307877 :: accuracy 50.000000], [ Generator :: loss: 0.177006]\nepoch: 224, [Discriminator :: d_loss: 1.412521 :: accuracy 50.000000], [ Generator :: loss: 0.107870]\nepoch: 225, [Discriminator :: d_loss: 1.351686 :: accuracy 50.000000], [ Generator :: loss: 0.206750]\nepoch: 226, [Discriminator :: d_loss: 1.608680 :: accuracy 50.000000], [ Generator :: loss: 0.112814]\nepoch: 227, [Discriminator :: d_loss: 1.589368 :: accuracy 50.000000], [ Generator :: loss: 0.147638]\nepoch: 228, [Discriminator :: d_loss: 1.473883 :: accuracy 50.000000], [ Generator :: loss: 0.192256]\nepoch: 229, [Discriminator :: d_loss: 1.290755 :: accuracy 50.000000], [ Generator :: loss: 0.177039]\nepoch: 230, [Discriminator :: d_loss: 1.328353 :: accuracy 50.000000], [ Generator :: loss: 0.199239]\nepoch: 231, [Discriminator :: d_loss: 1.421694 :: accuracy 50.000000], [ Generator :: loss: 0.115687]\nepoch: 232, [Discriminator :: d_loss: 1.483545 :: accuracy 50.000000], [ Generator :: loss: 0.166483]\nepoch: 233, [Discriminator :: d_loss: 1.567750 :: accuracy 50.000000], [ Generator :: loss: 0.124586]\nepoch: 234, [Discriminator :: d_loss: 1.361275 :: accuracy 50.000000], [ Generator :: loss: 0.154928]\nepoch: 235, [Discriminator :: d_loss: 1.447044 :: accuracy 50.000000], [ Generator :: loss: 0.124780]\nepoch: 236, [Discriminator :: d_loss: 1.383166 :: accuracy 50.000000], [ Generator :: loss: 0.133478]\nepoch: 237, [Discriminator :: d_loss: 1.298380 :: accuracy 50.000000], [ Generator :: loss: 0.185981]\nepoch: 238, [Discriminator :: d_loss: 1.382944 :: accuracy 50.000000], [ Generator :: loss: 0.172360]\nepoch: 239, [Discriminator :: d_loss: 1.408093 :: accuracy 50.000000], [ Generator :: loss: 0.155757]\nepoch: 240, [Discriminator :: d_loss: 1.432938 :: accuracy 50.000000], [ Generator :: loss: 0.146432]\nepoch: 241, [Discriminator :: d_loss: 1.298743 :: accuracy 50.000000], [ Generator :: loss: 0.195485]\nepoch: 242, [Discriminator :: d_loss: 1.352615 :: accuracy 50.000000], [ Generator :: loss: 0.142364]\nepoch: 243, [Discriminator :: d_loss: 1.377633 :: accuracy 50.000000], [ Generator :: loss: 0.185942]\nepoch: 244, [Discriminator :: d_loss: 1.506507 :: accuracy 50.000000], [ Generator :: loss: 0.108686]\nepoch: 245, [Discriminator :: d_loss: 1.649913 :: accuracy 50.000000], [ Generator :: loss: 0.142742]\nepoch: 246, [Discriminator :: d_loss: 1.378941 :: accuracy 50.000000], [ Generator :: loss: 0.154240]\nepoch: 247, [Discriminator :: d_loss: 1.366664 :: accuracy 50.000000], [ Generator :: loss: 0.135654]\nepoch: 248, [Discriminator :: d_loss: 1.259925 :: accuracy 50.000000], [ Generator :: loss: 0.164138]\nepoch: 249, [Discriminator :: d_loss: 1.399251 :: accuracy 50.000000], [ Generator :: loss: 0.155165]\nepoch: 250, [Discriminator :: d_loss: 1.273819 :: accuracy 50.000000], [ Generator :: loss: 0.182460]\nepoch: 251, [Discriminator :: d_loss: 1.364024 :: accuracy 50.000000], [ Generator :: loss: 0.128573]\nepoch: 252, [Discriminator :: d_loss: 1.375409 :: accuracy 50.000000], [ Generator :: loss: 0.167532]\nepoch: 253, [Discriminator :: d_loss: 1.293631 :: accuracy 50.000000], [ Generator :: loss: 0.147371]\nepoch: 254, [Discriminator :: d_loss: 1.470234 :: accuracy 50.000000], [ Generator :: loss: 0.150257]\nepoch: 255, [Discriminator :: d_loss: 1.421845 :: accuracy 50.000000], [ Generator :: loss: 0.218406]\nepoch: 256, [Discriminator :: d_loss: 1.430440 :: accuracy 50.000000], [ Generator :: loss: 0.148904]\nepoch: 257, [Discriminator :: d_loss: 1.466150 :: accuracy 50.000000], [ Generator :: loss: 0.181312]\nepoch: 258, [Discriminator :: d_loss: 1.324193 :: accuracy 50.000000], [ Generator :: loss: 0.163434]\nepoch: 259, [Discriminator :: d_loss: 1.301708 :: accuracy 50.000000], [ Generator :: loss: 0.188535]\nepoch: 260, [Discriminator :: d_loss: 1.445844 :: accuracy 50.000000], [ Generator :: loss: 0.113841]\nepoch: 261, [Discriminator :: d_loss: 1.495430 :: accuracy 50.000000], [ Generator :: loss: 0.162146]\nepoch: 262, [Discriminator :: d_loss: 1.455704 :: accuracy 50.000000], [ Generator :: loss: 0.161665]\nepoch: 263, [Discriminator :: d_loss: 1.337433 :: accuracy 50.000000], [ Generator :: loss: 0.161782]\nepoch: 264, [Discriminator :: d_loss: 1.343071 :: accuracy 50.000000], [ Generator :: loss: 0.140355]\nepoch: 265, [Discriminator :: d_loss: 1.402582 :: accuracy 50.000000], [ Generator :: loss: 0.138507]\nepoch: 266, [Discriminator :: d_loss: 1.408920 :: accuracy 50.000000], [ Generator :: loss: 0.130305]\nepoch: 267, [Discriminator :: d_loss: 1.363131 :: accuracy 50.000000], [ Generator :: loss: 0.175418]\nepoch: 268, [Discriminator :: d_loss: 1.288743 :: accuracy 50.000000], [ Generator :: loss: 0.168057]\nepoch: 269, [Discriminator :: d_loss: 1.393521 :: accuracy 50.000000], [ Generator :: loss: 0.170645]\nepoch: 270, [Discriminator :: d_loss: 1.413966 :: accuracy 50.000000], [ Generator :: loss: 0.141536]\nepoch: 271, [Discriminator :: d_loss: 1.342723 :: accuracy 50.000000], [ Generator :: loss: 0.211767]\nepoch: 272, [Discriminator :: d_loss: 1.465963 :: accuracy 50.000000], [ Generator :: loss: 0.152706]\nepoch: 273, [Discriminator :: d_loss: 1.575986 :: accuracy 50.000000], [ Generator :: loss: 0.146939]\nepoch: 274, [Discriminator :: d_loss: 1.397721 :: accuracy 50.000000], [ Generator :: loss: 0.142327]\nepoch: 275, [Discriminator :: d_loss: 1.428022 :: accuracy 50.000000], [ Generator :: loss: 0.204284]\nepoch: 276, [Discriminator :: d_loss: 1.273935 :: accuracy 50.000000], [ Generator :: loss: 0.243241]\nepoch: 277, [Discriminator :: d_loss: 1.505762 :: accuracy 50.000000], [ Generator :: loss: 0.133046]\nepoch: 278, [Discriminator :: d_loss: 1.407713 :: accuracy 50.000000], [ Generator :: loss: 0.185805]\nepoch: 279, [Discriminator :: d_loss: 1.534422 :: accuracy 50.000000], [ Generator :: loss: 0.125408]\nepoch: 280, [Discriminator :: d_loss: 1.525926 :: accuracy 50.000000], [ Generator :: loss: 0.134490]\nepoch: 281, [Discriminator :: d_loss: 1.398299 :: accuracy 50.000000], [ Generator :: loss: 0.138734]\nepoch: 282, [Discriminator :: d_loss: 1.365641 :: accuracy 50.000000], [ Generator :: loss: 0.145663]\nepoch: 283, [Discriminator :: d_loss: 1.405476 :: accuracy 50.000000], [ Generator :: loss: 0.190560]\nepoch: 284, [Discriminator :: d_loss: 1.322499 :: accuracy 50.000000], [ Generator :: loss: 0.165710]\nepoch: 285, [Discriminator :: d_loss: 1.402345 :: accuracy 50.000000], [ Generator :: loss: 0.145620]\nepoch: 286, [Discriminator :: d_loss: 1.400526 :: accuracy 50.000000], [ Generator :: loss: 0.150992]\nepoch: 287, [Discriminator :: d_loss: 1.373909 :: accuracy 50.000000], [ Generator :: loss: 0.167903]\nepoch: 288, [Discriminator :: d_loss: 1.339023 :: accuracy 50.000000], [ Generator :: loss: 0.150459]\nepoch: 289, [Discriminator :: d_loss: 1.310033 :: accuracy 50.000000], [ Generator :: loss: 0.145142]\nepoch: 290, [Discriminator :: d_loss: 1.369871 :: accuracy 50.000000], [ Generator :: loss: 0.154629]\nepoch: 291, [Discriminator :: d_loss: 1.308886 :: accuracy 50.000000], [ Generator :: loss: 0.170596]\nepoch: 292, [Discriminator :: d_loss: 1.354256 :: accuracy 50.000000], [ Generator :: loss: 0.147647]\nepoch: 293, [Discriminator :: d_loss: 1.396101 :: accuracy 50.000000], [ Generator :: loss: 0.157490]\nepoch: 294, [Discriminator :: d_loss: 1.349900 :: accuracy 50.000000], [ Generator :: loss: 0.194723]\nepoch: 295, [Discriminator :: d_loss: 1.380654 :: accuracy 50.000000], [ Generator :: loss: 0.157777]\nepoch: 296, [Discriminator :: d_loss: 1.268492 :: accuracy 50.000000], [ Generator :: loss: 0.211360]\nepoch: 297, [Discriminator :: d_loss: 1.501086 :: accuracy 50.000000], [ Generator :: loss: 0.174442]\nepoch: 298, [Discriminator :: d_loss: 1.456394 :: accuracy 50.000000], [ Generator :: loss: 0.142748]\nepoch: 299, [Discriminator :: d_loss: 1.368430 :: accuracy 50.000000], [ Generator :: loss: 0.161685]\nepoch: 300, [Discriminator :: d_loss: 1.398277 :: accuracy 50.000000], [ Generator :: loss: 0.173283]\nepoch: 301, [Discriminator :: d_loss: 1.379123 :: accuracy 50.000000], [ Generator :: loss: 0.145072]\nepoch: 302, [Discriminator :: d_loss: 1.380373 :: accuracy 50.000000], [ Generator :: loss: 0.149063]\nepoch: 303, [Discriminator :: d_loss: 1.345089 :: accuracy 50.000000], [ Generator :: loss: 0.168301]\nepoch: 304, [Discriminator :: d_loss: 1.359751 :: accuracy 50.000000], [ Generator :: loss: 0.185999]\n","name":"stdout"},{"output_type":"stream","text":"epoch: 305, [Discriminator :: d_loss: 1.294606 :: accuracy 50.000000], [ Generator :: loss: 0.174713]\nepoch: 306, [Discriminator :: d_loss: 1.472775 :: accuracy 50.000000], [ Generator :: loss: 0.149977]\nepoch: 307, [Discriminator :: d_loss: 1.439049 :: accuracy 50.000000], [ Generator :: loss: 0.140197]\nepoch: 308, [Discriminator :: d_loss: 1.369683 :: accuracy 50.000000], [ Generator :: loss: 0.159247]\nepoch: 309, [Discriminator :: d_loss: 1.368227 :: accuracy 50.000000], [ Generator :: loss: 0.172815]\nepoch: 310, [Discriminator :: d_loss: 1.379397 :: accuracy 50.000000], [ Generator :: loss: 0.144523]\nepoch: 311, [Discriminator :: d_loss: 1.372567 :: accuracy 50.000000], [ Generator :: loss: 0.159968]\nepoch: 312, [Discriminator :: d_loss: 1.312940 :: accuracy 50.000000], [ Generator :: loss: 0.159626]\nepoch: 313, [Discriminator :: d_loss: 1.379543 :: accuracy 50.000000], [ Generator :: loss: 0.170414]\nepoch: 314, [Discriminator :: d_loss: 1.323139 :: accuracy 50.000000], [ Generator :: loss: 0.153749]\nepoch: 315, [Discriminator :: d_loss: 1.322437 :: accuracy 50.000000], [ Generator :: loss: 0.177120]\nepoch: 316, [Discriminator :: d_loss: 1.358937 :: accuracy 50.000000], [ Generator :: loss: 0.154711]\nepoch: 317, [Discriminator :: d_loss: 1.287226 :: accuracy 50.000000], [ Generator :: loss: 0.160928]\nepoch: 318, [Discriminator :: d_loss: 1.255318 :: accuracy 50.000000], [ Generator :: loss: 0.137613]\nepoch: 319, [Discriminator :: d_loss: 1.399661 :: accuracy 50.000000], [ Generator :: loss: 0.326280]\nepoch: 320, [Discriminator :: d_loss: 1.319435 :: accuracy 50.000000], [ Generator :: loss: 0.127367]\nepoch: 321, [Discriminator :: d_loss: 1.418573 :: accuracy 50.000000], [ Generator :: loss: 0.155125]\nepoch: 322, [Discriminator :: d_loss: 1.561307 :: accuracy 50.000000], [ Generator :: loss: 0.141762]\nepoch: 323, [Discriminator :: d_loss: 1.362724 :: accuracy 50.000000], [ Generator :: loss: 0.198057]\nepoch: 324, [Discriminator :: d_loss: 1.479459 :: accuracy 50.000000], [ Generator :: loss: 0.149760]\nepoch: 325, [Discriminator :: d_loss: 1.465563 :: accuracy 50.000000], [ Generator :: loss: 0.143514]\nepoch: 326, [Discriminator :: d_loss: 1.435246 :: accuracy 50.000000], [ Generator :: loss: 0.151672]\nepoch: 327, [Discriminator :: d_loss: 1.387360 :: accuracy 50.000000], [ Generator :: loss: 0.170423]\nepoch: 328, [Discriminator :: d_loss: 1.355152 :: accuracy 50.000000], [ Generator :: loss: 0.163650]\nepoch: 329, [Discriminator :: d_loss: 1.361949 :: accuracy 50.000000], [ Generator :: loss: 0.164882]\nepoch: 330, [Discriminator :: d_loss: 1.323892 :: accuracy 50.000000], [ Generator :: loss: 0.146944]\nepoch: 331, [Discriminator :: d_loss: 1.312259 :: accuracy 50.000000], [ Generator :: loss: 0.184989]\nepoch: 332, [Discriminator :: d_loss: 1.314290 :: accuracy 50.000000], [ Generator :: loss: 0.144939]\nepoch: 333, [Discriminator :: d_loss: 1.399832 :: accuracy 50.000000], [ Generator :: loss: 0.141083]\nepoch: 334, [Discriminator :: d_loss: 1.449141 :: accuracy 50.000000], [ Generator :: loss: 0.153093]\nepoch: 335, [Discriminator :: d_loss: 1.406591 :: accuracy 50.000000], [ Generator :: loss: 0.156873]\nepoch: 336, [Discriminator :: d_loss: 1.407013 :: accuracy 50.000000], [ Generator :: loss: 0.166896]\nepoch: 337, [Discriminator :: d_loss: 1.264935 :: accuracy 50.000000], [ Generator :: loss: 0.188168]\nepoch: 338, [Discriminator :: d_loss: 1.393551 :: accuracy 50.000000], [ Generator :: loss: 0.162570]\nepoch: 339, [Discriminator :: d_loss: 1.349563 :: accuracy 50.000000], [ Generator :: loss: 0.171450]\nepoch: 340, [Discriminator :: d_loss: 1.409012 :: accuracy 50.000000], [ Generator :: loss: 0.149162]\nepoch: 341, [Discriminator :: d_loss: 1.470663 :: accuracy 50.000000], [ Generator :: loss: 0.170271]\nepoch: 342, [Discriminator :: d_loss: 1.477203 :: accuracy 50.000000], [ Generator :: loss: 0.172902]\nepoch: 343, [Discriminator :: d_loss: 1.256965 :: accuracy 50.000000], [ Generator :: loss: 0.181821]\nepoch: 344, [Discriminator :: d_loss: 1.446217 :: accuracy 50.000000], [ Generator :: loss: 0.163412]\nepoch: 345, [Discriminator :: d_loss: 1.408291 :: accuracy 50.000000], [ Generator :: loss: 0.140208]\nepoch: 346, [Discriminator :: d_loss: 1.338597 :: accuracy 50.000000], [ Generator :: loss: 0.146203]\nepoch: 347, [Discriminator :: d_loss: 1.410132 :: accuracy 50.000000], [ Generator :: loss: 0.152769]\nepoch: 348, [Discriminator :: d_loss: 1.380446 :: accuracy 50.000000], [ Generator :: loss: 0.151714]\nepoch: 349, [Discriminator :: d_loss: 1.330909 :: accuracy 50.000000], [ Generator :: loss: 0.158853]\nepoch: 350, [Discriminator :: d_loss: 1.302904 :: accuracy 50.000000], [ Generator :: loss: 0.160094]\nepoch: 351, [Discriminator :: d_loss: 1.302007 :: accuracy 50.000000], [ Generator :: loss: 0.186692]\nepoch: 352, [Discriminator :: d_loss: 1.258782 :: accuracy 50.000000], [ Generator :: loss: 0.176054]\nepoch: 353, [Discriminator :: d_loss: 1.403822 :: accuracy 50.000000], [ Generator :: loss: 0.154425]\nepoch: 354, [Discriminator :: d_loss: 1.350995 :: accuracy 50.000000], [ Generator :: loss: 0.152321]\nepoch: 355, [Discriminator :: d_loss: 1.357782 :: accuracy 50.000000], [ Generator :: loss: 0.180507]\nepoch: 356, [Discriminator :: d_loss: 1.356554 :: accuracy 50.000000], [ Generator :: loss: 0.145304]\nepoch: 357, [Discriminator :: d_loss: 1.367663 :: accuracy 50.000000], [ Generator :: loss: 0.156744]\nepoch: 358, [Discriminator :: d_loss: 1.422946 :: accuracy 50.000000], [ Generator :: loss: 0.171795]\nepoch: 359, [Discriminator :: d_loss: 1.355491 :: accuracy 50.000000], [ Generator :: loss: 0.154850]\nepoch: 360, [Discriminator :: d_loss: 1.423352 :: accuracy 50.000000], [ Generator :: loss: 0.161816]\nepoch: 361, [Discriminator :: d_loss: 1.490498 :: accuracy 50.000000], [ Generator :: loss: 0.164180]\nepoch: 362, [Discriminator :: d_loss: 1.376849 :: accuracy 50.000000], [ Generator :: loss: 0.143768]\nepoch: 363, [Discriminator :: d_loss: 1.290574 :: accuracy 50.000000], [ Generator :: loss: 0.152746]\nepoch: 364, [Discriminator :: d_loss: 1.315953 :: accuracy 50.000000], [ Generator :: loss: 0.155806]\nepoch: 365, [Discriminator :: d_loss: 1.289647 :: accuracy 50.000000], [ Generator :: loss: 0.153777]\nepoch: 366, [Discriminator :: d_loss: 1.369470 :: accuracy 50.000000], [ Generator :: loss: 0.153835]\nepoch: 367, [Discriminator :: d_loss: 1.384142 :: accuracy 50.000000], [ Generator :: loss: 0.191173]\nepoch: 368, [Discriminator :: d_loss: 1.338827 :: accuracy 50.000000], [ Generator :: loss: 0.149577]\nepoch: 369, [Discriminator :: d_loss: 1.312387 :: accuracy 50.000000], [ Generator :: loss: 0.165728]\nepoch: 370, [Discriminator :: d_loss: 1.357342 :: accuracy 50.000000], [ Generator :: loss: 0.138875]\nepoch: 371, [Discriminator :: d_loss: 1.366122 :: accuracy 50.000000], [ Generator :: loss: 0.172247]\nepoch: 372, [Discriminator :: d_loss: 1.329782 :: accuracy 50.000000], [ Generator :: loss: 0.169005]\nepoch: 373, [Discriminator :: d_loss: 1.320797 :: accuracy 50.000000], [ Generator :: loss: 0.155587]\nepoch: 374, [Discriminator :: d_loss: 1.399790 :: accuracy 50.000000], [ Generator :: loss: 0.154656]\nepoch: 375, [Discriminator :: d_loss: 1.367987 :: accuracy 50.000000], [ Generator :: loss: 0.147840]\nepoch: 376, [Discriminator :: d_loss: 1.328949 :: accuracy 50.000000], [ Generator :: loss: 0.166425]\nepoch: 377, [Discriminator :: d_loss: 1.327612 :: accuracy 50.000000], [ Generator :: loss: 0.157014]\nepoch: 378, [Discriminator :: d_loss: 1.338020 :: accuracy 50.000000], [ Generator :: loss: 0.149659]\nepoch: 379, [Discriminator :: d_loss: 1.399925 :: accuracy 50.000000], [ Generator :: loss: 0.147951]\nepoch: 380, [Discriminator :: d_loss: 1.309136 :: accuracy 50.000000], [ Generator :: loss: 0.151459]\nepoch: 381, [Discriminator :: d_loss: 1.416826 :: accuracy 50.000000], [ Generator :: loss: 0.149577]\nepoch: 382, [Discriminator :: d_loss: 1.334444 :: accuracy 50.000000], [ Generator :: loss: 0.191115]\nepoch: 383, [Discriminator :: d_loss: 1.290303 :: accuracy 50.000000], [ Generator :: loss: 0.150087]\nepoch: 384, [Discriminator :: d_loss: 1.341954 :: accuracy 50.000000], [ Generator :: loss: 0.190052]\nepoch: 385, [Discriminator :: d_loss: 1.456370 :: accuracy 50.000000], [ Generator :: loss: 0.141292]\nepoch: 386, [Discriminator :: d_loss: 1.381263 :: accuracy 50.000000], [ Generator :: loss: 0.151016]\nepoch: 387, [Discriminator :: d_loss: 1.315495 :: accuracy 50.000000], [ Generator :: loss: 0.149802]\nepoch: 388, [Discriminator :: d_loss: 1.396877 :: accuracy 50.000000], [ Generator :: loss: 0.189217]\n","name":"stdout"},{"output_type":"stream","text":"epoch: 389, [Discriminator :: d_loss: 1.346142 :: accuracy 50.000000], [ Generator :: loss: 0.143701]\nepoch: 390, [Discriminator :: d_loss: 1.373507 :: accuracy 50.000000], [ Generator :: loss: 0.140217]\nepoch: 391, [Discriminator :: d_loss: 1.315505 :: accuracy 50.000000], [ Generator :: loss: 0.205003]\nepoch: 392, [Discriminator :: d_loss: 1.437509 :: accuracy 50.000000], [ Generator :: loss: 0.134355]\nepoch: 393, [Discriminator :: d_loss: 1.324117 :: accuracy 50.000000], [ Generator :: loss: 0.166355]\nepoch: 394, [Discriminator :: d_loss: 1.412571 :: accuracy 50.000000], [ Generator :: loss: 0.173393]\nepoch: 395, [Discriminator :: d_loss: 1.464062 :: accuracy 50.000000], [ Generator :: loss: 0.171745]\nepoch: 396, [Discriminator :: d_loss: 1.417195 :: accuracy 50.000000], [ Generator :: loss: 0.153212]\nepoch: 397, [Discriminator :: d_loss: 1.343855 :: accuracy 50.000000], [ Generator :: loss: 0.155471]\nepoch: 398, [Discriminator :: d_loss: 1.275302 :: accuracy 50.000000], [ Generator :: loss: 0.183799]\nepoch: 399, [Discriminator :: d_loss: 1.393811 :: accuracy 50.000000], [ Generator :: loss: 0.142850]\nepoch: 400, [Discriminator :: d_loss: 1.338572 :: accuracy 50.000000], [ Generator :: loss: 0.145667]\nepoch: 401, [Discriminator :: d_loss: 1.263610 :: accuracy 50.000000], [ Generator :: loss: 0.174466]\nepoch: 402, [Discriminator :: d_loss: 1.395040 :: accuracy 50.000000], [ Generator :: loss: 0.189732]\nepoch: 403, [Discriminator :: d_loss: 1.352838 :: accuracy 50.000000], [ Generator :: loss: 0.135302]\nepoch: 404, [Discriminator :: d_loss: 1.237734 :: accuracy 50.000000], [ Generator :: loss: 0.154069]\nepoch: 405, [Discriminator :: d_loss: 1.421344 :: accuracy 50.000000], [ Generator :: loss: 0.150024]\nepoch: 406, [Discriminator :: d_loss: 1.332606 :: accuracy 50.000000], [ Generator :: loss: 0.153506]\nepoch: 407, [Discriminator :: d_loss: 1.328856 :: accuracy 50.000000], [ Generator :: loss: 0.174675]\nepoch: 408, [Discriminator :: d_loss: 1.313674 :: accuracy 50.000000], [ Generator :: loss: 0.177251]\nepoch: 409, [Discriminator :: d_loss: 1.369455 :: accuracy 50.000000], [ Generator :: loss: 0.139841]\nepoch: 410, [Discriminator :: d_loss: 1.328359 :: accuracy 50.000000], [ Generator :: loss: 0.155078]\nepoch: 411, [Discriminator :: d_loss: 1.300689 :: accuracy 50.000000], [ Generator :: loss: 0.181218]\nepoch: 412, [Discriminator :: d_loss: 1.257239 :: accuracy 50.000000], [ Generator :: loss: 0.172331]\nepoch: 413, [Discriminator :: d_loss: 1.311444 :: accuracy 50.000000], [ Generator :: loss: 0.200747]\nepoch: 414, [Discriminator :: d_loss: 1.332417 :: accuracy 50.000000], [ Generator :: loss: 0.150043]\nepoch: 415, [Discriminator :: d_loss: 1.350925 :: accuracy 50.000000], [ Generator :: loss: 0.144067]\nepoch: 416, [Discriminator :: d_loss: 1.311699 :: accuracy 50.000000], [ Generator :: loss: 0.150138]\nepoch: 417, [Discriminator :: d_loss: 1.329915 :: accuracy 50.000000], [ Generator :: loss: 0.148950]\nepoch: 418, [Discriminator :: d_loss: 1.289716 :: accuracy 50.000000], [ Generator :: loss: 0.187150]\nepoch: 419, [Discriminator :: d_loss: 1.395142 :: accuracy 50.000000], [ Generator :: loss: 0.178961]\nepoch: 420, [Discriminator :: d_loss: 1.405795 :: accuracy 50.000000], [ Generator :: loss: 0.149947]\nepoch: 421, [Discriminator :: d_loss: 1.196149 :: accuracy 50.000000], [ Generator :: loss: 0.183994]\nepoch: 422, [Discriminator :: d_loss: 1.365099 :: accuracy 50.000000], [ Generator :: loss: 0.141938]\nepoch: 423, [Discriminator :: d_loss: 1.353892 :: accuracy 50.000000], [ Generator :: loss: 0.142724]\nepoch: 424, [Discriminator :: d_loss: 1.319525 :: accuracy 50.000000], [ Generator :: loss: 0.201820]\nepoch: 425, [Discriminator :: d_loss: 1.345415 :: accuracy 50.000000], [ Generator :: loss: 0.167598]\nepoch: 426, [Discriminator :: d_loss: 1.451230 :: accuracy 50.000000], [ Generator :: loss: 0.132943]\nepoch: 427, [Discriminator :: d_loss: 1.352172 :: accuracy 50.000000], [ Generator :: loss: 0.134739]\nepoch: 428, [Discriminator :: d_loss: 1.326146 :: accuracy 50.000000], [ Generator :: loss: 0.170607]\nepoch: 429, [Discriminator :: d_loss: 1.286077 :: accuracy 50.000000], [ Generator :: loss: 0.169145]\nepoch: 430, [Discriminator :: d_loss: 1.351653 :: accuracy 50.000000], [ Generator :: loss: 0.153961]\nepoch: 431, [Discriminator :: d_loss: 1.239186 :: accuracy 50.000000], [ Generator :: loss: 0.170975]\nepoch: 432, [Discriminator :: d_loss: 1.326458 :: accuracy 50.000000], [ Generator :: loss: 0.145898]\nepoch: 433, [Discriminator :: d_loss: 1.378588 :: accuracy 50.000000], [ Generator :: loss: 0.145285]\nepoch: 434, [Discriminator :: d_loss: 1.344337 :: accuracy 50.000000], [ Generator :: loss: 0.155943]\nepoch: 435, [Discriminator :: d_loss: 1.281077 :: accuracy 50.000000], [ Generator :: loss: 0.158820]\nepoch: 436, [Discriminator :: d_loss: 1.351174 :: accuracy 50.000000], [ Generator :: loss: 0.148168]\nepoch: 437, [Discriminator :: d_loss: 1.181062 :: accuracy 50.000000], [ Generator :: loss: 0.202900]\nepoch: 438, [Discriminator :: d_loss: 1.359603 :: accuracy 50.000000], [ Generator :: loss: 0.146335]\nepoch: 439, [Discriminator :: d_loss: 1.344620 :: accuracy 50.000000], [ Generator :: loss: 0.193214]\nepoch: 440, [Discriminator :: d_loss: 1.370335 :: accuracy 50.000000], [ Generator :: loss: 0.159192]\nepoch: 441, [Discriminator :: d_loss: 1.368402 :: accuracy 50.000000], [ Generator :: loss: 0.131210]\nepoch: 442, [Discriminator :: d_loss: 1.394688 :: accuracy 50.000000], [ Generator :: loss: 0.149984]\nepoch: 443, [Discriminator :: d_loss: 1.386853 :: accuracy 50.000000], [ Generator :: loss: 0.140050]\nepoch: 444, [Discriminator :: d_loss: 1.308793 :: accuracy 50.000000], [ Generator :: loss: 0.145791]\nepoch: 445, [Discriminator :: d_loss: 1.306602 :: accuracy 50.000000], [ Generator :: loss: 0.164976]\nepoch: 446, [Discriminator :: d_loss: 1.312701 :: accuracy 50.000000], [ Generator :: loss: 0.154477]\nepoch: 447, [Discriminator :: d_loss: 1.312479 :: accuracy 50.000000], [ Generator :: loss: 0.167731]\nepoch: 448, [Discriminator :: d_loss: 1.329393 :: accuracy 50.000000], [ Generator :: loss: 0.145360]\nepoch: 449, [Discriminator :: d_loss: 1.332885 :: accuracy 50.000000], [ Generator :: loss: 0.160885]\nepoch: 450, [Discriminator :: d_loss: 1.313908 :: accuracy 50.000000], [ Generator :: loss: 0.151753]\nepoch: 451, [Discriminator :: d_loss: 1.319057 :: accuracy 50.000000], [ Generator :: loss: 0.148978]\nepoch: 452, [Discriminator :: d_loss: 1.258723 :: accuracy 50.000000], [ Generator :: loss: 0.152476]\nepoch: 453, [Discriminator :: d_loss: 1.273114 :: accuracy 50.000000], [ Generator :: loss: 0.150086]\nepoch: 454, [Discriminator :: d_loss: 1.330269 :: accuracy 50.000000], [ Generator :: loss: 0.160175]\nepoch: 455, [Discriminator :: d_loss: 1.273025 :: accuracy 50.000000], [ Generator :: loss: 0.153047]\nepoch: 456, [Discriminator :: d_loss: 1.308749 :: accuracy 50.000000], [ Generator :: loss: 0.151271]\nepoch: 457, [Discriminator :: d_loss: 1.284883 :: accuracy 50.000000], [ Generator :: loss: 0.168611]\nepoch: 458, [Discriminator :: d_loss: 1.266022 :: accuracy 50.000000], [ Generator :: loss: 0.160055]\nepoch: 459, [Discriminator :: d_loss: 1.357204 :: accuracy 50.000000], [ Generator :: loss: 0.166886]\nepoch: 460, [Discriminator :: d_loss: 1.267176 :: accuracy 50.000000], [ Generator :: loss: 0.159999]\nepoch: 461, [Discriminator :: d_loss: 1.235076 :: accuracy 50.000000], [ Generator :: loss: 0.151111]\nepoch: 462, [Discriminator :: d_loss: 1.341603 :: accuracy 50.000000], [ Generator :: loss: 0.168530]\nepoch: 463, [Discriminator :: d_loss: 1.287735 :: accuracy 50.000000], [ Generator :: loss: 0.139341]\nepoch: 464, [Discriminator :: d_loss: 1.301508 :: accuracy 50.000000], [ Generator :: loss: 0.153996]\nepoch: 465, [Discriminator :: d_loss: 1.269624 :: accuracy 50.000000], [ Generator :: loss: 0.158323]\nepoch: 466, [Discriminator :: d_loss: 1.316427 :: accuracy 50.000000], [ Generator :: loss: 0.156960]\nepoch: 467, [Discriminator :: d_loss: 1.273517 :: accuracy 50.000000], [ Generator :: loss: 0.166149]\nepoch: 468, [Discriminator :: d_loss: 1.387450 :: accuracy 50.000000], [ Generator :: loss: 0.168152]\nepoch: 469, [Discriminator :: d_loss: 1.417989 :: accuracy 50.000000], [ Generator :: loss: 0.199047]\nepoch: 470, [Discriminator :: d_loss: 1.282537 :: accuracy 50.000000], [ Generator :: loss: 0.171660]\nepoch: 471, [Discriminator :: d_loss: 1.368879 :: accuracy 50.000000], [ Generator :: loss: 0.148847]\nepoch: 472, [Discriminator :: d_loss: 1.351718 :: accuracy 50.000000], [ Generator :: loss: 0.157240]\n","name":"stdout"},{"output_type":"stream","text":"epoch: 473, [Discriminator :: d_loss: 1.354534 :: accuracy 50.000000], [ Generator :: loss: 0.151878]\nepoch: 474, [Discriminator :: d_loss: 1.270826 :: accuracy 50.000000], [ Generator :: loss: 0.162284]\nepoch: 475, [Discriminator :: d_loss: 1.347466 :: accuracy 50.000000], [ Generator :: loss: 0.183306]\nepoch: 476, [Discriminator :: d_loss: 1.303944 :: accuracy 50.000000], [ Generator :: loss: 0.204795]\nepoch: 477, [Discriminator :: d_loss: 1.403625 :: accuracy 50.000000], [ Generator :: loss: 0.136573]\nepoch: 478, [Discriminator :: d_loss: 1.317450 :: accuracy 50.000000], [ Generator :: loss: 0.167880]\nepoch: 479, [Discriminator :: d_loss: 1.366100 :: accuracy 50.000000], [ Generator :: loss: 0.154157]\nepoch: 480, [Discriminator :: d_loss: 1.369526 :: accuracy 50.000000], [ Generator :: loss: 0.126891]\nepoch: 481, [Discriminator :: d_loss: 1.355869 :: accuracy 50.000000], [ Generator :: loss: 0.169744]\nepoch: 482, [Discriminator :: d_loss: 1.388790 :: accuracy 50.000000], [ Generator :: loss: 0.136989]\nepoch: 483, [Discriminator :: d_loss: 1.355294 :: accuracy 50.000000], [ Generator :: loss: 0.150170]\nepoch: 484, [Discriminator :: d_loss: 1.271196 :: accuracy 50.000000], [ Generator :: loss: 0.148000]\nepoch: 485, [Discriminator :: d_loss: 1.291821 :: accuracy 50.000000], [ Generator :: loss: 0.163432]\nepoch: 486, [Discriminator :: d_loss: 1.320682 :: accuracy 50.000000], [ Generator :: loss: 0.161266]\nepoch: 487, [Discriminator :: d_loss: 1.288793 :: accuracy 50.000000], [ Generator :: loss: 0.155673]\nepoch: 488, [Discriminator :: d_loss: 1.308598 :: accuracy 50.000000], [ Generator :: loss: 0.153230]\nepoch: 489, [Discriminator :: d_loss: 1.405370 :: accuracy 50.000000], [ Generator :: loss: 0.163900]\nepoch: 490, [Discriminator :: d_loss: 1.249897 :: accuracy 50.000000], [ Generator :: loss: 0.155608]\nepoch: 491, [Discriminator :: d_loss: 1.325598 :: accuracy 50.000000], [ Generator :: loss: 0.189277]\nepoch: 492, [Discriminator :: d_loss: 1.280147 :: accuracy 50.000000], [ Generator :: loss: 0.162595]\nepoch: 493, [Discriminator :: d_loss: 1.327032 :: accuracy 50.000000], [ Generator :: loss: 0.190164]\nepoch: 494, [Discriminator :: d_loss: 1.269716 :: accuracy 50.000000], [ Generator :: loss: 0.160497]\nepoch: 495, [Discriminator :: d_loss: 1.308987 :: accuracy 50.000000], [ Generator :: loss: 0.151221]\nepoch: 496, [Discriminator :: d_loss: 1.305887 :: accuracy 50.000000], [ Generator :: loss: 0.140998]\nepoch: 497, [Discriminator :: d_loss: 1.332727 :: accuracy 50.000000], [ Generator :: loss: 0.155011]\nepoch: 498, [Discriminator :: d_loss: 1.290389 :: accuracy 50.000000], [ Generator :: loss: 0.156857]\nepoch: 499, [Discriminator :: d_loss: 1.354388 :: accuracy 50.000000], [ Generator :: loss: 0.157971]\nepoch: 500, [Discriminator :: d_loss: 1.319543 :: accuracy 50.000000], [ Generator :: loss: 0.149744]\nepoch: 501, [Discriminator :: d_loss: 1.317192 :: accuracy 50.000000], [ Generator :: loss: 0.150682]\nepoch: 502, [Discriminator :: d_loss: 1.223884 :: accuracy 50.000000], [ Generator :: loss: 0.165885]\nepoch: 503, [Discriminator :: d_loss: 1.318880 :: accuracy 50.000000], [ Generator :: loss: 0.163128]\nepoch: 504, [Discriminator :: d_loss: 1.385797 :: accuracy 50.000000], [ Generator :: loss: 0.154897]\nepoch: 505, [Discriminator :: d_loss: 1.297254 :: accuracy 50.000000], [ Generator :: loss: 0.169828]\nepoch: 506, [Discriminator :: d_loss: 1.299860 :: accuracy 50.000000], [ Generator :: loss: 0.162727]\nepoch: 507, [Discriminator :: d_loss: 1.335928 :: accuracy 50.000000], [ Generator :: loss: 0.138421]\nepoch: 508, [Discriminator :: d_loss: 1.384139 :: accuracy 50.000000], [ Generator :: loss: 0.152148]\nepoch: 509, [Discriminator :: d_loss: 1.342917 :: accuracy 50.000000], [ Generator :: loss: 0.138349]\nepoch: 510, [Discriminator :: d_loss: 1.349474 :: accuracy 50.000000], [ Generator :: loss: 0.155766]\nepoch: 511, [Discriminator :: d_loss: 1.263257 :: accuracy 50.000000], [ Generator :: loss: 0.158705]\nepoch: 512, [Discriminator :: d_loss: 1.263256 :: accuracy 50.000000], [ Generator :: loss: 0.187014]\nepoch: 513, [Discriminator :: d_loss: 1.326481 :: accuracy 50.000000], [ Generator :: loss: 0.170758]\nepoch: 514, [Discriminator :: d_loss: 1.343629 :: accuracy 50.000000], [ Generator :: loss: 0.146654]\nepoch: 515, [Discriminator :: d_loss: 1.209677 :: accuracy 50.000000], [ Generator :: loss: 0.169433]\nepoch: 516, [Discriminator :: d_loss: 1.266054 :: accuracy 50.000000], [ Generator :: loss: 0.165317]\nepoch: 517, [Discriminator :: d_loss: 1.399019 :: accuracy 50.000000], [ Generator :: loss: 0.137461]\nepoch: 518, [Discriminator :: d_loss: 1.351379 :: accuracy 50.000000], [ Generator :: loss: 0.139000]\nepoch: 519, [Discriminator :: d_loss: 1.273898 :: accuracy 50.000000], [ Generator :: loss: 0.159451]\nepoch: 520, [Discriminator :: d_loss: 1.281536 :: accuracy 50.000000], [ Generator :: loss: 0.166388]\nepoch: 521, [Discriminator :: d_loss: 1.301289 :: accuracy 50.000000], [ Generator :: loss: 0.157908]\nepoch: 522, [Discriminator :: d_loss: 1.336613 :: accuracy 50.000000], [ Generator :: loss: 0.150884]\nepoch: 523, [Discriminator :: d_loss: 1.321890 :: accuracy 50.000000], [ Generator :: loss: 0.149358]\nepoch: 524, [Discriminator :: d_loss: 1.272064 :: accuracy 50.000000], [ Generator :: loss: 0.161739]\nepoch: 525, [Discriminator :: d_loss: 1.339322 :: accuracy 50.000000], [ Generator :: loss: 0.161861]\nepoch: 526, [Discriminator :: d_loss: 1.290655 :: accuracy 50.000000], [ Generator :: loss: 0.158554]\nepoch: 527, [Discriminator :: d_loss: 1.257647 :: accuracy 50.000000], [ Generator :: loss: 0.168937]\nepoch: 528, [Discriminator :: d_loss: 1.318654 :: accuracy 50.000000], [ Generator :: loss: 0.142744]\nepoch: 529, [Discriminator :: d_loss: 1.298328 :: accuracy 50.000000], [ Generator :: loss: 0.141319]\nepoch: 530, [Discriminator :: d_loss: 1.328169 :: accuracy 50.000000], [ Generator :: loss: 0.147031]\nepoch: 531, [Discriminator :: d_loss: 1.228382 :: accuracy 50.000000], [ Generator :: loss: 0.167269]\nepoch: 532, [Discriminator :: d_loss: 1.259735 :: accuracy 50.000000], [ Generator :: loss: 0.156425]\nepoch: 533, [Discriminator :: d_loss: 1.266635 :: accuracy 50.000000], [ Generator :: loss: 0.177386]\nepoch: 534, [Discriminator :: d_loss: 1.264333 :: accuracy 50.000000], [ Generator :: loss: 0.170137]\nepoch: 535, [Discriminator :: d_loss: 1.282157 :: accuracy 50.000000], [ Generator :: loss: 0.141678]\nepoch: 536, [Discriminator :: d_loss: 1.375660 :: accuracy 50.000000], [ Generator :: loss: 0.157088]\nepoch: 537, [Discriminator :: d_loss: 1.329728 :: accuracy 50.000000], [ Generator :: loss: 0.155102]\nepoch: 538, [Discriminator :: d_loss: 1.374897 :: accuracy 50.000000], [ Generator :: loss: 0.156258]\nepoch: 539, [Discriminator :: d_loss: 1.222651 :: accuracy 50.000000], [ Generator :: loss: 0.165990]\nepoch: 540, [Discriminator :: d_loss: 1.325460 :: accuracy 50.000000], [ Generator :: loss: 0.180058]\nepoch: 541, [Discriminator :: d_loss: 1.268998 :: accuracy 50.000000], [ Generator :: loss: 0.151473]\nepoch: 542, [Discriminator :: d_loss: 1.333782 :: accuracy 50.000000], [ Generator :: loss: 0.152614]\nepoch: 543, [Discriminator :: d_loss: 1.304743 :: accuracy 50.000000], [ Generator :: loss: 0.150574]\nepoch: 544, [Discriminator :: d_loss: 1.298858 :: accuracy 50.000000], [ Generator :: loss: 0.160096]\nepoch: 545, [Discriminator :: d_loss: 1.295009 :: accuracy 50.000000], [ Generator :: loss: 0.170330]\nepoch: 546, [Discriminator :: d_loss: 1.361613 :: accuracy 50.000000], [ Generator :: loss: 0.157735]\nepoch: 547, [Discriminator :: d_loss: 1.307536 :: accuracy 50.000000], [ Generator :: loss: 0.151783]\nepoch: 548, [Discriminator :: d_loss: 1.391804 :: accuracy 50.000000], [ Generator :: loss: 0.149747]\nepoch: 549, [Discriminator :: d_loss: 1.260302 :: accuracy 50.000000], [ Generator :: loss: 0.167322]\nepoch: 550, [Discriminator :: d_loss: 1.373149 :: accuracy 50.000000], [ Generator :: loss: 0.158968]\nepoch: 551, [Discriminator :: d_loss: 1.333368 :: accuracy 50.000000], [ Generator :: loss: 0.146851]\nepoch: 552, [Discriminator :: d_loss: 1.283762 :: accuracy 50.000000], [ Generator :: loss: 0.150329]\nepoch: 553, [Discriminator :: d_loss: 1.240447 :: accuracy 50.000000], [ Generator :: loss: 0.144476]\nepoch: 554, [Discriminator :: d_loss: 1.362789 :: accuracy 50.000000], [ Generator :: loss: 0.179668]\nepoch: 555, [Discriminator :: d_loss: 1.323272 :: accuracy 50.000000], [ Generator :: loss: 0.177502]\nepoch: 556, [Discriminator :: d_loss: 1.236817 :: accuracy 50.000000], [ Generator :: loss: 0.147521]\n","name":"stdout"},{"output_type":"stream","text":"epoch: 557, [Discriminator :: d_loss: 1.250666 :: accuracy 50.000000], [ Generator :: loss: 0.165438]\nepoch: 558, [Discriminator :: d_loss: 1.393132 :: accuracy 50.000000], [ Generator :: loss: 0.156476]\nepoch: 559, [Discriminator :: d_loss: 1.285616 :: accuracy 50.000000], [ Generator :: loss: 0.151344]\nepoch: 560, [Discriminator :: d_loss: 1.224208 :: accuracy 50.000000], [ Generator :: loss: 0.164200]\nepoch: 561, [Discriminator :: d_loss: 1.260872 :: accuracy 50.000000], [ Generator :: loss: 0.176061]\nepoch: 562, [Discriminator :: d_loss: 1.307536 :: accuracy 50.000000], [ Generator :: loss: 0.168756]\nepoch: 563, [Discriminator :: d_loss: 1.316017 :: accuracy 50.000000], [ Generator :: loss: 0.154742]\nepoch: 564, [Discriminator :: d_loss: 1.253920 :: accuracy 50.000000], [ Generator :: loss: 0.170993]\nepoch: 565, [Discriminator :: d_loss: 1.352676 :: accuracy 50.000000], [ Generator :: loss: 0.160011]\nepoch: 566, [Discriminator :: d_loss: 1.374371 :: accuracy 50.000000], [ Generator :: loss: 0.148245]\nepoch: 567, [Discriminator :: d_loss: 1.287035 :: accuracy 50.000000], [ Generator :: loss: 0.149942]\nepoch: 568, [Discriminator :: d_loss: 1.268868 :: accuracy 50.000000], [ Generator :: loss: 0.155936]\nepoch: 569, [Discriminator :: d_loss: 1.342208 :: accuracy 50.000000], [ Generator :: loss: 0.150148]\nepoch: 570, [Discriminator :: d_loss: 1.246732 :: accuracy 50.000000], [ Generator :: loss: 0.179052]\nepoch: 571, [Discriminator :: d_loss: 1.340518 :: accuracy 50.000000], [ Generator :: loss: 0.157589]\nepoch: 572, [Discriminator :: d_loss: 1.393264 :: accuracy 50.000000], [ Generator :: loss: 0.145552]\nepoch: 573, [Discriminator :: d_loss: 1.326551 :: accuracy 50.000000], [ Generator :: loss: 0.159346]\nepoch: 574, [Discriminator :: d_loss: 1.333308 :: accuracy 50.000000], [ Generator :: loss: 0.162542]\nepoch: 575, [Discriminator :: d_loss: 1.279518 :: accuracy 50.000000], [ Generator :: loss: 0.145773]\nepoch: 576, [Discriminator :: d_loss: 1.305031 :: accuracy 50.000000], [ Generator :: loss: 0.160520]\nepoch: 577, [Discriminator :: d_loss: 1.372531 :: accuracy 50.000000], [ Generator :: loss: 0.156308]\nepoch: 578, [Discriminator :: d_loss: 1.294076 :: accuracy 50.000000], [ Generator :: loss: 0.163502]\nepoch: 579, [Discriminator :: d_loss: 1.258343 :: accuracy 50.000000], [ Generator :: loss: 0.158120]\nepoch: 580, [Discriminator :: d_loss: 1.294190 :: accuracy 50.000000], [ Generator :: loss: 0.163788]\nepoch: 581, [Discriminator :: d_loss: 1.269166 :: accuracy 50.000000], [ Generator :: loss: 0.187917]\nepoch: 582, [Discriminator :: d_loss: 1.342229 :: accuracy 50.000000], [ Generator :: loss: 0.151947]\nepoch: 583, [Discriminator :: d_loss: 1.226472 :: accuracy 50.000000], [ Generator :: loss: 0.139384]\nepoch: 584, [Discriminator :: d_loss: 1.378381 :: accuracy 50.000000], [ Generator :: loss: 0.160796]\nepoch: 585, [Discriminator :: d_loss: 1.378987 :: accuracy 50.000000], [ Generator :: loss: 0.148486]\nepoch: 586, [Discriminator :: d_loss: 1.475934 :: accuracy 50.000000], [ Generator :: loss: 0.166101]\nepoch: 587, [Discriminator :: d_loss: 1.262834 :: accuracy 50.000000], [ Generator :: loss: 0.164664]\nepoch: 588, [Discriminator :: d_loss: 1.327675 :: accuracy 50.000000], [ Generator :: loss: 0.166897]\nepoch: 589, [Discriminator :: d_loss: 1.333161 :: accuracy 50.000000], [ Generator :: loss: 0.151898]\nepoch: 590, [Discriminator :: d_loss: 1.351491 :: accuracy 50.000000], [ Generator :: loss: 0.154858]\nepoch: 591, [Discriminator :: d_loss: 1.365963 :: accuracy 50.000000], [ Generator :: loss: 0.147329]\nepoch: 592, [Discriminator :: d_loss: 1.366488 :: accuracy 50.000000], [ Generator :: loss: 0.168807]\nepoch: 593, [Discriminator :: d_loss: 1.246082 :: accuracy 50.000000], [ Generator :: loss: 0.161202]\nepoch: 594, [Discriminator :: d_loss: 1.385962 :: accuracy 50.000000], [ Generator :: loss: 0.175371]\nepoch: 595, [Discriminator :: d_loss: 1.389626 :: accuracy 50.000000], [ Generator :: loss: 0.204175]\nepoch: 596, [Discriminator :: d_loss: 1.360293 :: accuracy 50.000000], [ Generator :: loss: 0.140491]\nepoch: 597, [Discriminator :: d_loss: 1.533221 :: accuracy 50.000000], [ Generator :: loss: 0.156275]\nepoch: 598, [Discriminator :: d_loss: 1.393276 :: accuracy 50.000000], [ Generator :: loss: 0.151142]\nepoch: 599, [Discriminator :: d_loss: 1.320318 :: accuracy 50.000000], [ Generator :: loss: 0.139636]\nepoch: 600, [Discriminator :: d_loss: 1.358966 :: accuracy 50.000000], [ Generator :: loss: 0.143478]\nepoch: 601, [Discriminator :: d_loss: 1.399217 :: accuracy 50.000000], [ Generator :: loss: 0.181510]\nepoch: 602, [Discriminator :: d_loss: 1.360592 :: accuracy 50.000000], [ Generator :: loss: 0.158502]\nepoch: 603, [Discriminator :: d_loss: 1.329521 :: accuracy 50.000000], [ Generator :: loss: 0.154960]\nepoch: 604, [Discriminator :: d_loss: 1.351429 :: accuracy 50.000000], [ Generator :: loss: 0.145241]\nepoch: 605, [Discriminator :: d_loss: 1.322910 :: accuracy 50.000000], [ Generator :: loss: 0.140146]\nepoch: 606, [Discriminator :: d_loss: 1.299984 :: accuracy 50.000000], [ Generator :: loss: 0.140500]\nepoch: 607, [Discriminator :: d_loss: 1.386645 :: accuracy 50.000000], [ Generator :: loss: 0.171512]\nepoch: 608, [Discriminator :: d_loss: 1.268611 :: accuracy 50.000000], [ Generator :: loss: 0.164365]\nepoch: 609, [Discriminator :: d_loss: 1.320266 :: accuracy 50.000000], [ Generator :: loss: 0.148149]\nepoch: 610, [Discriminator :: d_loss: 1.303888 :: accuracy 50.000000], [ Generator :: loss: 0.199052]\nepoch: 611, [Discriminator :: d_loss: 1.253915 :: accuracy 50.000000], [ Generator :: loss: 0.152735]\nepoch: 612, [Discriminator :: d_loss: 1.338006 :: accuracy 50.000000], [ Generator :: loss: 0.158075]\nepoch: 613, [Discriminator :: d_loss: 1.289450 :: accuracy 50.000000], [ Generator :: loss: 0.144660]\nepoch: 614, [Discriminator :: d_loss: 1.265116 :: accuracy 50.000000], [ Generator :: loss: 0.150533]\nepoch: 615, [Discriminator :: d_loss: 1.255540 :: accuracy 50.000000], [ Generator :: loss: 0.167197]\nepoch: 616, [Discriminator :: d_loss: 1.349275 :: accuracy 50.000000], [ Generator :: loss: 0.146138]\nepoch: 617, [Discriminator :: d_loss: 1.258835 :: accuracy 50.000000], [ Generator :: loss: 0.179597]\nepoch: 618, [Discriminator :: d_loss: 1.371803 :: accuracy 50.000000], [ Generator :: loss: 0.161399]\nepoch: 619, [Discriminator :: d_loss: 1.300519 :: accuracy 50.000000], [ Generator :: loss: 0.158133]\nepoch: 620, [Discriminator :: d_loss: 1.279864 :: accuracy 50.000000], [ Generator :: loss: 0.148741]\nepoch: 621, [Discriminator :: d_loss: 1.315486 :: accuracy 50.000000], [ Generator :: loss: 0.133797]\nepoch: 622, [Discriminator :: d_loss: 1.327090 :: accuracy 50.000000], [ Generator :: loss: 0.171890]\nepoch: 623, [Discriminator :: d_loss: 1.206844 :: accuracy 50.000000], [ Generator :: loss: 0.150306]\nepoch: 624, [Discriminator :: d_loss: 1.410373 :: accuracy 50.000000], [ Generator :: loss: 0.157680]\nepoch: 625, [Discriminator :: d_loss: 1.291894 :: accuracy 50.000000], [ Generator :: loss: 0.137735]\nepoch: 626, [Discriminator :: d_loss: 1.402174 :: accuracy 50.000000], [ Generator :: loss: 0.161833]\nepoch: 627, [Discriminator :: d_loss: 1.283041 :: accuracy 50.000000], [ Generator :: loss: 0.155836]\nepoch: 628, [Discriminator :: d_loss: 1.248664 :: accuracy 50.000000], [ Generator :: loss: 0.182206]\nepoch: 629, [Discriminator :: d_loss: 1.378327 :: accuracy 50.000000], [ Generator :: loss: 0.145833]\nepoch: 630, [Discriminator :: d_loss: 1.320906 :: accuracy 50.000000], [ Generator :: loss: 0.192012]\nepoch: 631, [Discriminator :: d_loss: 1.339557 :: accuracy 50.000000], [ Generator :: loss: 0.159972]\nepoch: 632, [Discriminator :: d_loss: 1.320845 :: accuracy 50.000000], [ Generator :: loss: 0.155880]\nepoch: 633, [Discriminator :: d_loss: 1.218102 :: accuracy 50.000000], [ Generator :: loss: 0.206167]\nepoch: 634, [Discriminator :: d_loss: 1.374967 :: accuracy 50.000000], [ Generator :: loss: 0.135060]\nepoch: 635, [Discriminator :: d_loss: 1.308200 :: accuracy 50.000000], [ Generator :: loss: 0.139980]\nepoch: 636, [Discriminator :: d_loss: 1.252738 :: accuracy 50.000000], [ Generator :: loss: 0.164207]\nepoch: 637, [Discriminator :: d_loss: 1.251469 :: accuracy 50.000000], [ Generator :: loss: 0.192435]\nepoch: 638, [Discriminator :: d_loss: 1.377290 :: accuracy 50.000000], [ Generator :: loss: 0.143769]\nepoch: 639, [Discriminator :: d_loss: 1.342458 :: accuracy 50.000000], [ Generator :: loss: 0.146580]\nepoch: 640, [Discriminator :: d_loss: 1.355951 :: accuracy 50.000000], [ Generator :: loss: 0.143061]\n","name":"stdout"},{"output_type":"stream","text":"epoch: 641, [Discriminator :: d_loss: 1.365722 :: accuracy 50.000000], [ Generator :: loss: 0.146866]\nepoch: 642, [Discriminator :: d_loss: 1.363248 :: accuracy 50.000000], [ Generator :: loss: 0.142205]\nepoch: 643, [Discriminator :: d_loss: 1.346175 :: accuracy 50.000000], [ Generator :: loss: 0.165879]\nepoch: 644, [Discriminator :: d_loss: 1.311005 :: accuracy 50.000000], [ Generator :: loss: 0.147089]\nepoch: 645, [Discriminator :: d_loss: 1.263357 :: accuracy 50.000000], [ Generator :: loss: 0.175282]\nepoch: 646, [Discriminator :: d_loss: 1.339364 :: accuracy 50.000000], [ Generator :: loss: 0.187782]\nepoch: 647, [Discriminator :: d_loss: 1.404731 :: accuracy 50.000000], [ Generator :: loss: 0.150414]\nepoch: 648, [Discriminator :: d_loss: 1.212777 :: accuracy 50.000000], [ Generator :: loss: 0.158648]\nepoch: 649, [Discriminator :: d_loss: 1.317333 :: accuracy 50.000000], [ Generator :: loss: 0.148328]\nepoch: 650, [Discriminator :: d_loss: 1.400036 :: accuracy 50.000000], [ Generator :: loss: 0.134289]\nepoch: 651, [Discriminator :: d_loss: 1.249312 :: accuracy 50.000000], [ Generator :: loss: 0.145057]\nepoch: 652, [Discriminator :: d_loss: 1.329407 :: accuracy 50.000000], [ Generator :: loss: 0.154313]\nepoch: 653, [Discriminator :: d_loss: 1.246593 :: accuracy 50.000000], [ Generator :: loss: 0.181525]\nepoch: 654, [Discriminator :: d_loss: 1.283052 :: accuracy 50.000000], [ Generator :: loss: 0.149973]\nepoch: 655, [Discriminator :: d_loss: 1.347973 :: accuracy 50.000000], [ Generator :: loss: 0.147587]\nepoch: 656, [Discriminator :: d_loss: 1.296106 :: accuracy 50.000000], [ Generator :: loss: 0.149994]\nepoch: 657, [Discriminator :: d_loss: 1.373162 :: accuracy 50.000000], [ Generator :: loss: 0.146041]\nepoch: 658, [Discriminator :: d_loss: 1.447128 :: accuracy 50.000000], [ Generator :: loss: 0.157478]\nepoch: 659, [Discriminator :: d_loss: 1.274998 :: accuracy 50.000000], [ Generator :: loss: 0.151696]\nepoch: 660, [Discriminator :: d_loss: 1.282263 :: accuracy 50.000000], [ Generator :: loss: 0.193580]\nepoch: 661, [Discriminator :: d_loss: 1.315805 :: accuracy 50.000000], [ Generator :: loss: 0.160502]\nepoch: 662, [Discriminator :: d_loss: 1.350825 :: accuracy 50.000000], [ Generator :: loss: 0.138233]\nepoch: 663, [Discriminator :: d_loss: 1.238997 :: accuracy 50.000000], [ Generator :: loss: 0.151309]\nepoch: 664, [Discriminator :: d_loss: 1.423900 :: accuracy 50.000000], [ Generator :: loss: 0.156907]\nepoch: 665, [Discriminator :: d_loss: 1.317980 :: accuracy 50.000000], [ Generator :: loss: 0.162673]\nepoch: 666, [Discriminator :: d_loss: 1.353635 :: accuracy 50.000000], [ Generator :: loss: 0.151743]\nepoch: 667, [Discriminator :: d_loss: 1.288778 :: accuracy 50.000000], [ Generator :: loss: 0.154753]\nepoch: 668, [Discriminator :: d_loss: 1.293886 :: accuracy 50.000000], [ Generator :: loss: 0.152584]\nepoch: 669, [Discriminator :: d_loss: 1.385906 :: accuracy 50.000000], [ Generator :: loss: 0.158888]\nepoch: 670, [Discriminator :: d_loss: 1.242021 :: accuracy 50.000000], [ Generator :: loss: 0.161221]\nepoch: 671, [Discriminator :: d_loss: 1.264939 :: accuracy 50.000000], [ Generator :: loss: 0.150940]\nepoch: 672, [Discriminator :: d_loss: 1.283413 :: accuracy 50.000000], [ Generator :: loss: 0.143449]\nepoch: 673, [Discriminator :: d_loss: 1.294594 :: accuracy 50.000000], [ Generator :: loss: 0.148978]\nepoch: 674, [Discriminator :: d_loss: 1.355421 :: accuracy 50.000000], [ Generator :: loss: 0.165574]\nepoch: 675, [Discriminator :: d_loss: 1.298884 :: accuracy 50.000000], [ Generator :: loss: 0.167814]\nepoch: 676, [Discriminator :: d_loss: 1.251739 :: accuracy 50.000000], [ Generator :: loss: 0.172197]\nepoch: 677, [Discriminator :: d_loss: 1.282992 :: accuracy 50.000000], [ Generator :: loss: 0.172119]\nepoch: 678, [Discriminator :: d_loss: 1.331154 :: accuracy 50.000000], [ Generator :: loss: 0.157302]\nepoch: 679, [Discriminator :: d_loss: 1.312633 :: accuracy 50.000000], [ Generator :: loss: 0.184847]\nepoch: 680, [Discriminator :: d_loss: 1.386491 :: accuracy 50.000000], [ Generator :: loss: 0.134465]\nepoch: 681, [Discriminator :: d_loss: 1.304314 :: accuracy 50.000000], [ Generator :: loss: 0.145497]\nepoch: 682, [Discriminator :: d_loss: 1.361058 :: accuracy 50.000000], [ Generator :: loss: 0.138915]\nepoch: 683, [Discriminator :: d_loss: 1.361197 :: accuracy 50.000000], [ Generator :: loss: 0.164421]\nepoch: 684, [Discriminator :: d_loss: 1.311378 :: accuracy 50.000000], [ Generator :: loss: 0.141973]\nepoch: 685, [Discriminator :: d_loss: 1.286438 :: accuracy 50.000000], [ Generator :: loss: 0.157464]\nepoch: 686, [Discriminator :: d_loss: 1.277561 :: accuracy 50.000000], [ Generator :: loss: 0.139232]\nepoch: 687, [Discriminator :: d_loss: 1.232032 :: accuracy 50.000000], [ Generator :: loss: 0.139263]\nepoch: 688, [Discriminator :: d_loss: 1.290704 :: accuracy 50.000000], [ Generator :: loss: 0.144233]\nepoch: 689, [Discriminator :: d_loss: 1.382265 :: accuracy 50.000000], [ Generator :: loss: 0.155552]\nepoch: 690, [Discriminator :: d_loss: 1.343019 :: accuracy 50.000000], [ Generator :: loss: 0.160379]\nepoch: 691, [Discriminator :: d_loss: 1.235013 :: accuracy 50.000000], [ Generator :: loss: 0.179862]\nepoch: 692, [Discriminator :: d_loss: 1.257406 :: accuracy 50.000000], [ Generator :: loss: 0.177727]\nepoch: 693, [Discriminator :: d_loss: 1.351207 :: accuracy 50.000000], [ Generator :: loss: 0.157681]\nepoch: 694, [Discriminator :: d_loss: 1.406782 :: accuracy 50.000000], [ Generator :: loss: 0.157953]\nepoch: 695, [Discriminator :: d_loss: 1.292939 :: accuracy 50.000000], [ Generator :: loss: 0.147621]\nepoch: 696, [Discriminator :: d_loss: 1.310135 :: accuracy 50.000000], [ Generator :: loss: 0.138952]\nepoch: 697, [Discriminator :: d_loss: 1.302950 :: accuracy 50.000000], [ Generator :: loss: 0.137676]\nepoch: 698, [Discriminator :: d_loss: 1.404409 :: accuracy 50.000000], [ Generator :: loss: 0.144476]\nepoch: 699, [Discriminator :: d_loss: 1.342911 :: accuracy 50.000000], [ Generator :: loss: 0.155200]\nepoch: 700, [Discriminator :: d_loss: 1.290422 :: accuracy 50.000000], [ Generator :: loss: 0.181470]\nepoch: 701, [Discriminator :: d_loss: 1.251172 :: accuracy 50.000000], [ Generator :: loss: 0.162921]\nepoch: 702, [Discriminator :: d_loss: 1.328315 :: accuracy 50.000000], [ Generator :: loss: 0.162403]\nepoch: 703, [Discriminator :: d_loss: 1.379233 :: accuracy 50.000000], [ Generator :: loss: 0.154680]\nepoch: 704, [Discriminator :: d_loss: 1.375345 :: accuracy 50.000000], [ Generator :: loss: 0.142134]\nepoch: 705, [Discriminator :: d_loss: 1.410481 :: accuracy 50.000000], [ Generator :: loss: 0.143417]\nepoch: 706, [Discriminator :: d_loss: 1.349473 :: accuracy 50.000000], [ Generator :: loss: 0.154762]\nepoch: 707, [Discriminator :: d_loss: 1.417373 :: accuracy 50.000000], [ Generator :: loss: 0.180592]\nepoch: 708, [Discriminator :: d_loss: 1.290911 :: accuracy 50.000000], [ Generator :: loss: 0.151716]\nepoch: 709, [Discriminator :: d_loss: 1.357160 :: accuracy 50.000000], [ Generator :: loss: 0.143834]\nepoch: 710, [Discriminator :: d_loss: 1.320578 :: accuracy 50.000000], [ Generator :: loss: 0.146191]\nepoch: 711, [Discriminator :: d_loss: 1.330689 :: accuracy 50.000000], [ Generator :: loss: 0.150210]\nepoch: 712, [Discriminator :: d_loss: 1.368058 :: accuracy 50.000000], [ Generator :: loss: 0.157342]\nepoch: 713, [Discriminator :: d_loss: 1.322077 :: accuracy 50.000000], [ Generator :: loss: 0.148727]\nepoch: 714, [Discriminator :: d_loss: 1.337747 :: accuracy 50.000000], [ Generator :: loss: 0.142715]\nepoch: 715, [Discriminator :: d_loss: 1.293138 :: accuracy 50.000000], [ Generator :: loss: 0.174080]\nepoch: 716, [Discriminator :: d_loss: 1.337564 :: accuracy 50.000000], [ Generator :: loss: 0.144953]\nepoch: 717, [Discriminator :: d_loss: 1.322828 :: accuracy 50.000000], [ Generator :: loss: 0.169132]\nepoch: 718, [Discriminator :: d_loss: 1.409781 :: accuracy 50.000000], [ Generator :: loss: 0.149747]\nepoch: 719, [Discriminator :: d_loss: 1.285405 :: accuracy 50.000000], [ Generator :: loss: 0.154766]\nepoch: 720, [Discriminator :: d_loss: 1.419267 :: accuracy 50.000000], [ Generator :: loss: 0.144599]\nepoch: 721, [Discriminator :: d_loss: 1.351465 :: accuracy 50.000000], [ Generator :: loss: 0.186794]\nepoch: 722, [Discriminator :: d_loss: 1.353801 :: accuracy 50.000000], [ Generator :: loss: 0.151043]\nepoch: 723, [Discriminator :: d_loss: 1.368185 :: accuracy 50.000000], [ Generator :: loss: 0.155999]\nepoch: 724, [Discriminator :: d_loss: 1.333322 :: accuracy 50.000000], [ Generator :: loss: 0.154833]\n","name":"stdout"},{"output_type":"stream","text":"epoch: 725, [Discriminator :: d_loss: 1.380485 :: accuracy 50.000000], [ Generator :: loss: 0.138646]\nepoch: 726, [Discriminator :: d_loss: 1.417824 :: accuracy 50.000000], [ Generator :: loss: 0.146282]\nepoch: 727, [Discriminator :: d_loss: 1.288578 :: accuracy 50.000000], [ Generator :: loss: 0.154463]\nepoch: 728, [Discriminator :: d_loss: 1.294889 :: accuracy 50.000000], [ Generator :: loss: 0.165788]\nepoch: 729, [Discriminator :: d_loss: 1.361208 :: accuracy 50.000000], [ Generator :: loss: 0.135391]\nepoch: 730, [Discriminator :: d_loss: 1.342550 :: accuracy 50.000000], [ Generator :: loss: 0.140076]\nepoch: 731, [Discriminator :: d_loss: 1.318464 :: accuracy 50.000000], [ Generator :: loss: 0.149080]\nepoch: 732, [Discriminator :: d_loss: 1.316052 :: accuracy 50.000000], [ Generator :: loss: 0.164484]\nepoch: 733, [Discriminator :: d_loss: 1.313735 :: accuracy 50.000000], [ Generator :: loss: 0.170663]\nepoch: 734, [Discriminator :: d_loss: 1.302143 :: accuracy 50.000000], [ Generator :: loss: 0.149614]\nepoch: 735, [Discriminator :: d_loss: 1.350521 :: accuracy 50.000000], [ Generator :: loss: 0.155336]\nepoch: 736, [Discriminator :: d_loss: 1.316135 :: accuracy 50.000000], [ Generator :: loss: 0.151200]\nepoch: 737, [Discriminator :: d_loss: 1.261011 :: accuracy 50.000000], [ Generator :: loss: 0.150633]\nepoch: 738, [Discriminator :: d_loss: 1.311038 :: accuracy 50.000000], [ Generator :: loss: 0.160703]\nepoch: 739, [Discriminator :: d_loss: 1.243251 :: accuracy 50.000000], [ Generator :: loss: 0.150955]\nepoch: 740, [Discriminator :: d_loss: 1.268800 :: accuracy 50.000000], [ Generator :: loss: 0.147836]\nepoch: 741, [Discriminator :: d_loss: 1.305315 :: accuracy 50.000000], [ Generator :: loss: 0.151571]\nepoch: 742, [Discriminator :: d_loss: 1.418918 :: accuracy 50.000000], [ Generator :: loss: 0.155710]\nepoch: 743, [Discriminator :: d_loss: 1.335219 :: accuracy 50.000000], [ Generator :: loss: 0.172728]\nepoch: 744, [Discriminator :: d_loss: 1.233935 :: accuracy 50.000000], [ Generator :: loss: 0.182551]\nepoch: 745, [Discriminator :: d_loss: 1.270470 :: accuracy 50.000000], [ Generator :: loss: 0.158135]\nepoch: 746, [Discriminator :: d_loss: 1.264534 :: accuracy 50.000000], [ Generator :: loss: 0.177288]\nepoch: 747, [Discriminator :: d_loss: 1.324290 :: accuracy 50.000000], [ Generator :: loss: 0.142214]\nepoch: 748, [Discriminator :: d_loss: 1.435373 :: accuracy 50.000000], [ Generator :: loss: 0.135120]\nepoch: 749, [Discriminator :: d_loss: 1.420993 :: accuracy 50.000000], [ Generator :: loss: 0.135827]\nepoch: 750, [Discriminator :: d_loss: 1.300153 :: accuracy 50.000000], [ Generator :: loss: 0.147916]\nepoch: 751, [Discriminator :: d_loss: 1.381956 :: accuracy 50.000000], [ Generator :: loss: 0.185976]\nepoch: 752, [Discriminator :: d_loss: 1.296565 :: accuracy 50.000000], [ Generator :: loss: 0.165607]\nepoch: 753, [Discriminator :: d_loss: 1.241478 :: accuracy 50.000000], [ Generator :: loss: 0.152850]\nepoch: 754, [Discriminator :: d_loss: 1.262530 :: accuracy 50.000000], [ Generator :: loss: 0.153479]\nepoch: 755, [Discriminator :: d_loss: 1.285353 :: accuracy 50.000000], [ Generator :: loss: 0.171241]\nepoch: 756, [Discriminator :: d_loss: 1.380904 :: accuracy 50.000000], [ Generator :: loss: 0.148872]\nepoch: 757, [Discriminator :: d_loss: 1.363075 :: accuracy 50.000000], [ Generator :: loss: 0.131633]\nepoch: 758, [Discriminator :: d_loss: 1.395190 :: accuracy 50.000000], [ Generator :: loss: 0.145377]\nepoch: 759, [Discriminator :: d_loss: 1.374090 :: accuracy 50.000000], [ Generator :: loss: 0.135961]\nepoch: 760, [Discriminator :: d_loss: 1.300712 :: accuracy 50.000000], [ Generator :: loss: 0.170415]\nepoch: 761, [Discriminator :: d_loss: 1.308681 :: accuracy 50.000000], [ Generator :: loss: 0.152669]\nepoch: 762, [Discriminator :: d_loss: 1.306798 :: accuracy 50.000000], [ Generator :: loss: 0.172551]\nepoch: 763, [Discriminator :: d_loss: 1.359672 :: accuracy 50.000000], [ Generator :: loss: 0.141637]\nepoch: 764, [Discriminator :: d_loss: 1.306225 :: accuracy 50.000000], [ Generator :: loss: 0.153817]\nepoch: 765, [Discriminator :: d_loss: 1.346027 :: accuracy 50.000000], [ Generator :: loss: 0.165873]\nepoch: 766, [Discriminator :: d_loss: 1.318269 :: accuracy 50.000000], [ Generator :: loss: 0.144784]\nepoch: 767, [Discriminator :: d_loss: 1.389516 :: accuracy 50.000000], [ Generator :: loss: 0.149827]\nepoch: 768, [Discriminator :: d_loss: 1.393611 :: accuracy 50.000000], [ Generator :: loss: 0.141920]\nepoch: 769, [Discriminator :: d_loss: 1.339110 :: accuracy 50.000000], [ Generator :: loss: 0.156354]\nepoch: 770, [Discriminator :: d_loss: 1.257223 :: accuracy 50.000000], [ Generator :: loss: 0.142614]\nepoch: 771, [Discriminator :: d_loss: 1.392113 :: accuracy 50.000000], [ Generator :: loss: 0.146232]\nepoch: 772, [Discriminator :: d_loss: 1.319342 :: accuracy 50.000000], [ Generator :: loss: 0.175702]\nepoch: 773, [Discriminator :: d_loss: 1.306143 :: accuracy 50.000000], [ Generator :: loss: 0.153258]\nepoch: 774, [Discriminator :: d_loss: 1.282444 :: accuracy 50.000000], [ Generator :: loss: 0.145165]\nepoch: 775, [Discriminator :: d_loss: 1.274816 :: accuracy 50.000000], [ Generator :: loss: 0.153541]\nepoch: 776, [Discriminator :: d_loss: 1.294214 :: accuracy 50.000000], [ Generator :: loss: 0.147896]\nepoch: 777, [Discriminator :: d_loss: 1.346395 :: accuracy 50.000000], [ Generator :: loss: 0.143740]\nepoch: 778, [Discriminator :: d_loss: 1.472943 :: accuracy 50.000000], [ Generator :: loss: 0.175385]\nepoch: 779, [Discriminator :: d_loss: 1.294546 :: accuracy 50.000000], [ Generator :: loss: 0.158683]\nepoch: 780, [Discriminator :: d_loss: 1.258035 :: accuracy 50.000000], [ Generator :: loss: 0.160542]\nepoch: 781, [Discriminator :: d_loss: 1.383765 :: accuracy 50.000000], [ Generator :: loss: 0.147886]\nepoch: 782, [Discriminator :: d_loss: 1.249038 :: accuracy 50.000000], [ Generator :: loss: 0.154542]\nepoch: 783, [Discriminator :: d_loss: 1.278706 :: accuracy 50.000000], [ Generator :: loss: 0.143810]\nepoch: 784, [Discriminator :: d_loss: 1.315308 :: accuracy 50.000000], [ Generator :: loss: 0.163860]\nepoch: 785, [Discriminator :: d_loss: 1.309159 :: accuracy 50.000000], [ Generator :: loss: 0.156425]\nepoch: 786, [Discriminator :: d_loss: 1.308236 :: accuracy 50.000000], [ Generator :: loss: 0.162046]\nepoch: 787, [Discriminator :: d_loss: 1.312096 :: accuracy 50.000000], [ Generator :: loss: 0.144237]\nepoch: 788, [Discriminator :: d_loss: 1.309378 :: accuracy 50.000000], [ Generator :: loss: 0.172355]\nepoch: 789, [Discriminator :: d_loss: 1.356579 :: accuracy 50.000000], [ Generator :: loss: 0.177451]\nepoch: 790, [Discriminator :: d_loss: 1.390669 :: accuracy 50.000000], [ Generator :: loss: 0.133532]\nepoch: 791, [Discriminator :: d_loss: 1.352252 :: accuracy 50.000000], [ Generator :: loss: 0.139712]\nepoch: 792, [Discriminator :: d_loss: 1.364286 :: accuracy 50.000000], [ Generator :: loss: 0.142004]\nepoch: 793, [Discriminator :: d_loss: 1.347884 :: accuracy 50.000000], [ Generator :: loss: 0.161964]\nepoch: 794, [Discriminator :: d_loss: 1.339174 :: accuracy 50.000000], [ Generator :: loss: 0.145002]\nepoch: 795, [Discriminator :: d_loss: 1.326792 :: accuracy 50.000000], [ Generator :: loss: 0.150586]\nepoch: 796, [Discriminator :: d_loss: 1.293889 :: accuracy 50.000000], [ Generator :: loss: 0.159224]\nepoch: 797, [Discriminator :: d_loss: 1.372421 :: accuracy 50.000000], [ Generator :: loss: 0.164230]\nepoch: 798, [Discriminator :: d_loss: 1.264655 :: accuracy 50.000000], [ Generator :: loss: 0.147044]\nepoch: 799, [Discriminator :: d_loss: 1.345430 :: accuracy 50.000000], [ Generator :: loss: 0.144477]\nepoch: 800, [Discriminator :: d_loss: 1.334524 :: accuracy 50.000000], [ Generator :: loss: 0.155339]\nepoch: 801, [Discriminator :: d_loss: 1.361217 :: accuracy 50.000000], [ Generator :: loss: 0.148479]\nepoch: 802, [Discriminator :: d_loss: 1.307101 :: accuracy 50.000000], [ Generator :: loss: 0.149993]\nepoch: 803, [Discriminator :: d_loss: 1.289011 :: accuracy 50.000000], [ Generator :: loss: 0.147916]\nepoch: 804, [Discriminator :: d_loss: 1.253636 :: accuracy 50.000000], [ Generator :: loss: 0.172133]\nepoch: 805, [Discriminator :: d_loss: 1.340257 :: accuracy 50.000000], [ Generator :: loss: 0.162266]\nepoch: 806, [Discriminator :: d_loss: 1.319731 :: accuracy 50.000000], [ Generator :: loss: 0.142337]\nepoch: 807, [Discriminator :: d_loss: 1.355668 :: accuracy 50.000000], [ Generator :: loss: 0.167658]\nepoch: 808, [Discriminator :: d_loss: 1.324053 :: accuracy 50.000000], [ Generator :: loss: 0.180000]\n","name":"stdout"},{"output_type":"stream","text":"epoch: 809, [Discriminator :: d_loss: 1.318452 :: accuracy 50.000000], [ Generator :: loss: 0.150746]\nepoch: 810, [Discriminator :: d_loss: 1.315731 :: accuracy 50.000000], [ Generator :: loss: 0.141437]\nepoch: 811, [Discriminator :: d_loss: 1.369085 :: accuracy 50.000000], [ Generator :: loss: 0.145594]\nepoch: 812, [Discriminator :: d_loss: 1.351575 :: accuracy 50.000000], [ Generator :: loss: 0.151505]\nepoch: 813, [Discriminator :: d_loss: 1.425161 :: accuracy 50.000000], [ Generator :: loss: 0.163897]\nepoch: 814, [Discriminator :: d_loss: 1.291978 :: accuracy 50.000000], [ Generator :: loss: 0.153443]\nepoch: 815, [Discriminator :: d_loss: 1.280632 :: accuracy 50.000000], [ Generator :: loss: 0.146712]\nepoch: 816, [Discriminator :: d_loss: 1.342594 :: accuracy 50.000000], [ Generator :: loss: 0.149803]\nepoch: 817, [Discriminator :: d_loss: 1.282610 :: accuracy 50.000000], [ Generator :: loss: 0.153050]\nepoch: 818, [Discriminator :: d_loss: 1.296702 :: accuracy 50.000000], [ Generator :: loss: 0.170657]\nepoch: 819, [Discriminator :: d_loss: 1.310870 :: accuracy 50.000000], [ Generator :: loss: 0.146262]\nepoch: 820, [Discriminator :: d_loss: 1.335885 :: accuracy 50.000000], [ Generator :: loss: 0.148390]\nepoch: 821, [Discriminator :: d_loss: 1.270838 :: accuracy 50.000000], [ Generator :: loss: 0.145197]\nepoch: 822, [Discriminator :: d_loss: 1.334081 :: accuracy 50.000000], [ Generator :: loss: 0.168121]\nepoch: 823, [Discriminator :: d_loss: 1.428245 :: accuracy 50.000000], [ Generator :: loss: 0.153416]\nepoch: 824, [Discriminator :: d_loss: 1.361854 :: accuracy 50.000000], [ Generator :: loss: 0.166078]\nepoch: 825, [Discriminator :: d_loss: 1.340448 :: accuracy 50.000000], [ Generator :: loss: 0.180780]\nepoch: 826, [Discriminator :: d_loss: 1.310141 :: accuracy 50.000000], [ Generator :: loss: 0.135139]\nepoch: 827, [Discriminator :: d_loss: 1.374816 :: accuracy 50.000000], [ Generator :: loss: 0.129902]\nepoch: 828, [Discriminator :: d_loss: 1.270401 :: accuracy 50.000000], [ Generator :: loss: 0.140547]\nepoch: 829, [Discriminator :: d_loss: 1.330024 :: accuracy 50.000000], [ Generator :: loss: 0.136815]\nepoch: 830, [Discriminator :: d_loss: 1.297053 :: accuracy 50.000000], [ Generator :: loss: 0.159589]\nepoch: 831, [Discriminator :: d_loss: 1.266125 :: accuracy 50.000000], [ Generator :: loss: 0.148417]\nepoch: 832, [Discriminator :: d_loss: 1.253208 :: accuracy 50.000000], [ Generator :: loss: 0.173210]\nepoch: 833, [Discriminator :: d_loss: 1.219263 :: accuracy 50.000000], [ Generator :: loss: 0.148478]\nepoch: 834, [Discriminator :: d_loss: 1.333320 :: accuracy 50.000000], [ Generator :: loss: 0.155544]\nepoch: 835, [Discriminator :: d_loss: 1.266788 :: accuracy 50.000000], [ Generator :: loss: 0.151958]\nepoch: 836, [Discriminator :: d_loss: 1.304929 :: accuracy 50.000000], [ Generator :: loss: 0.192656]\nepoch: 837, [Discriminator :: d_loss: 1.254425 :: accuracy 50.000000], [ Generator :: loss: 0.162825]\nepoch: 838, [Discriminator :: d_loss: 1.401685 :: accuracy 50.000000], [ Generator :: loss: 0.150517]\nepoch: 839, [Discriminator :: d_loss: 1.388563 :: accuracy 50.000000], [ Generator :: loss: 0.129253]\nepoch: 840, [Discriminator :: d_loss: 1.299847 :: accuracy 50.000000], [ Generator :: loss: 0.159991]\nepoch: 841, [Discriminator :: d_loss: 1.325827 :: accuracy 50.000000], [ Generator :: loss: 0.175954]\nepoch: 842, [Discriminator :: d_loss: 1.402393 :: accuracy 50.000000], [ Generator :: loss: 0.146001]\nepoch: 843, [Discriminator :: d_loss: 1.330449 :: accuracy 50.000000], [ Generator :: loss: 0.141781]\nepoch: 844, [Discriminator :: d_loss: 1.318392 :: accuracy 50.000000], [ Generator :: loss: 0.147404]\nepoch: 845, [Discriminator :: d_loss: 1.334734 :: accuracy 50.000000], [ Generator :: loss: 0.149237]\nepoch: 846, [Discriminator :: d_loss: 1.384403 :: accuracy 50.000000], [ Generator :: loss: 0.148707]\nepoch: 847, [Discriminator :: d_loss: 1.304798 :: accuracy 50.000000], [ Generator :: loss: 0.141080]\nepoch: 848, [Discriminator :: d_loss: 1.399468 :: accuracy 50.000000], [ Generator :: loss: 0.151508]\nepoch: 849, [Discriminator :: d_loss: 1.329830 :: accuracy 50.000000], [ Generator :: loss: 0.188973]\nepoch: 850, [Discriminator :: d_loss: 1.327960 :: accuracy 50.000000], [ Generator :: loss: 0.133698]\nepoch: 851, [Discriminator :: d_loss: 1.331859 :: accuracy 50.000000], [ Generator :: loss: 0.146629]\nepoch: 852, [Discriminator :: d_loss: 1.336238 :: accuracy 50.000000], [ Generator :: loss: 0.143811]\nepoch: 853, [Discriminator :: d_loss: 1.289175 :: accuracy 50.000000], [ Generator :: loss: 0.160561]\nepoch: 854, [Discriminator :: d_loss: 1.333699 :: accuracy 50.000000], [ Generator :: loss: 0.191965]\nepoch: 855, [Discriminator :: d_loss: 1.373141 :: accuracy 50.000000], [ Generator :: loss: 0.145328]\nepoch: 856, [Discriminator :: d_loss: 1.348174 :: accuracy 50.000000], [ Generator :: loss: 0.137231]\nepoch: 857, [Discriminator :: d_loss: 1.343606 :: accuracy 50.000000], [ Generator :: loss: 0.140760]\nepoch: 858, [Discriminator :: d_loss: 1.326913 :: accuracy 50.000000], [ Generator :: loss: 0.146461]\nepoch: 859, [Discriminator :: d_loss: 1.272191 :: accuracy 50.000000], [ Generator :: loss: 0.155591]\nepoch: 860, [Discriminator :: d_loss: 1.339080 :: accuracy 50.000000], [ Generator :: loss: 0.155996]\nepoch: 861, [Discriminator :: d_loss: 1.285618 :: accuracy 50.000000], [ Generator :: loss: 0.148153]\nepoch: 862, [Discriminator :: d_loss: 1.358115 :: accuracy 50.000000], [ Generator :: loss: 0.144240]\nepoch: 863, [Discriminator :: d_loss: 1.331738 :: accuracy 50.000000], [ Generator :: loss: 0.175164]\nepoch: 864, [Discriminator :: d_loss: 1.317864 :: accuracy 50.000000], [ Generator :: loss: 0.132868]\nepoch: 865, [Discriminator :: d_loss: 1.373447 :: accuracy 50.000000], [ Generator :: loss: 0.145688]\nepoch: 866, [Discriminator :: d_loss: 1.238042 :: accuracy 50.000000], [ Generator :: loss: 0.147961]\nepoch: 867, [Discriminator :: d_loss: 1.248052 :: accuracy 50.000000], [ Generator :: loss: 0.179131]\nepoch: 868, [Discriminator :: d_loss: 1.355582 :: accuracy 50.000000], [ Generator :: loss: 0.143226]\nepoch: 869, [Discriminator :: d_loss: 1.305826 :: accuracy 50.000000], [ Generator :: loss: 0.167953]\nepoch: 870, [Discriminator :: d_loss: 1.384573 :: accuracy 50.000000], [ Generator :: loss: 0.153099]\nepoch: 871, [Discriminator :: d_loss: 1.243200 :: accuracy 50.000000], [ Generator :: loss: 0.152114]\nepoch: 872, [Discriminator :: d_loss: 1.266502 :: accuracy 50.000000], [ Generator :: loss: 0.141650]\nepoch: 873, [Discriminator :: d_loss: 1.332942 :: accuracy 50.000000], [ Generator :: loss: 0.152806]\nepoch: 874, [Discriminator :: d_loss: 1.283315 :: accuracy 50.000000], [ Generator :: loss: 0.150755]\nepoch: 875, [Discriminator :: d_loss: 1.464769 :: accuracy 50.000000], [ Generator :: loss: 0.155919]\nepoch: 876, [Discriminator :: d_loss: 1.373473 :: accuracy 50.000000], [ Generator :: loss: 0.163174]\nepoch: 877, [Discriminator :: d_loss: 1.347525 :: accuracy 50.000000], [ Generator :: loss: 0.152656]\nepoch: 878, [Discriminator :: d_loss: 1.354445 :: accuracy 50.000000], [ Generator :: loss: 0.164870]\nepoch: 879, [Discriminator :: d_loss: 1.289509 :: accuracy 50.000000], [ Generator :: loss: 0.167067]\nepoch: 880, [Discriminator :: d_loss: 1.347580 :: accuracy 50.000000], [ Generator :: loss: 0.147356]\nepoch: 881, [Discriminator :: d_loss: 1.395381 :: accuracy 50.000000], [ Generator :: loss: 0.156571]\nepoch: 882, [Discriminator :: d_loss: 1.311920 :: accuracy 50.000000], [ Generator :: loss: 0.143048]\nepoch: 883, [Discriminator :: d_loss: 1.382726 :: accuracy 50.000000], [ Generator :: loss: 0.172969]\nepoch: 884, [Discriminator :: d_loss: 1.363355 :: accuracy 50.000000], [ Generator :: loss: 0.134043]\nepoch: 885, [Discriminator :: d_loss: 1.414991 :: accuracy 50.000000], [ Generator :: loss: 0.132336]\nepoch: 886, [Discriminator :: d_loss: 1.275600 :: accuracy 50.000000], [ Generator :: loss: 0.154320]\nepoch: 887, [Discriminator :: d_loss: 1.404737 :: accuracy 50.000000], [ Generator :: loss: 0.146952]\nepoch: 888, [Discriminator :: d_loss: 1.397889 :: accuracy 50.000000], [ Generator :: loss: 0.174966]\nepoch: 889, [Discriminator :: d_loss: 1.302615 :: accuracy 50.000000], [ Generator :: loss: 0.179182]\nepoch: 890, [Discriminator :: d_loss: 1.306399 :: accuracy 50.000000], [ Generator :: loss: 0.187657]\nepoch: 891, [Discriminator :: d_loss: 1.435933 :: accuracy 50.000000], [ Generator :: loss: 0.135118]\nepoch: 892, [Discriminator :: d_loss: 1.377183 :: accuracy 50.000000], [ Generator :: loss: 0.134288]\n","name":"stdout"},{"output_type":"stream","text":"epoch: 893, [Discriminator :: d_loss: 1.349320 :: accuracy 50.000000], [ Generator :: loss: 0.152299]\nepoch: 894, [Discriminator :: d_loss: 1.315405 :: accuracy 50.000000], [ Generator :: loss: 0.139654]\nepoch: 895, [Discriminator :: d_loss: 1.292573 :: accuracy 50.000000], [ Generator :: loss: 0.146675]\nepoch: 896, [Discriminator :: d_loss: 1.303517 :: accuracy 50.000000], [ Generator :: loss: 0.139264]\nepoch: 897, [Discriminator :: d_loss: 1.335327 :: accuracy 50.000000], [ Generator :: loss: 0.140511]\nepoch: 898, [Discriminator :: d_loss: 1.356381 :: accuracy 50.000000], [ Generator :: loss: 0.169032]\nepoch: 899, [Discriminator :: d_loss: 1.337238 :: accuracy 50.000000], [ Generator :: loss: 0.163716]\nepoch: 900, [Discriminator :: d_loss: 1.391707 :: accuracy 50.000000], [ Generator :: loss: 0.156984]\nepoch: 901, [Discriminator :: d_loss: 1.307227 :: accuracy 50.000000], [ Generator :: loss: 0.162416]\nepoch: 902, [Discriminator :: d_loss: 1.368583 :: accuracy 50.000000], [ Generator :: loss: 0.160291]\nepoch: 903, [Discriminator :: d_loss: 1.374880 :: accuracy 50.000000], [ Generator :: loss: 0.138431]\nepoch: 904, [Discriminator :: d_loss: 1.349396 :: accuracy 50.000000], [ Generator :: loss: 0.178711]\nepoch: 905, [Discriminator :: d_loss: 1.409238 :: accuracy 50.000000], [ Generator :: loss: 0.147513]\nepoch: 906, [Discriminator :: d_loss: 1.341026 :: accuracy 50.000000], [ Generator :: loss: 0.138565]\nepoch: 907, [Discriminator :: d_loss: 1.335011 :: accuracy 50.000000], [ Generator :: loss: 0.150504]\nepoch: 908, [Discriminator :: d_loss: 1.370980 :: accuracy 50.000000], [ Generator :: loss: 0.138195]\nepoch: 909, [Discriminator :: d_loss: 1.338607 :: accuracy 50.000000], [ Generator :: loss: 0.160586]\nepoch: 910, [Discriminator :: d_loss: 1.353942 :: accuracy 50.000000], [ Generator :: loss: 0.139247]\nepoch: 911, [Discriminator :: d_loss: 1.342828 :: accuracy 50.000000], [ Generator :: loss: 0.136230]\nepoch: 912, [Discriminator :: d_loss: 1.343777 :: accuracy 50.000000], [ Generator :: loss: 0.133254]\nepoch: 913, [Discriminator :: d_loss: 1.401959 :: accuracy 50.000000], [ Generator :: loss: 0.139109]\nepoch: 914, [Discriminator :: d_loss: 1.293674 :: accuracy 50.000000], [ Generator :: loss: 0.160893]\nepoch: 915, [Discriminator :: d_loss: 1.281028 :: accuracy 50.000000], [ Generator :: loss: 0.152452]\nepoch: 916, [Discriminator :: d_loss: 1.248239 :: accuracy 50.000000], [ Generator :: loss: 0.139610]\nepoch: 917, [Discriminator :: d_loss: 1.361398 :: accuracy 50.000000], [ Generator :: loss: 0.153126]\nepoch: 918, [Discriminator :: d_loss: 1.307787 :: accuracy 50.000000], [ Generator :: loss: 0.165263]\nepoch: 919, [Discriminator :: d_loss: 1.341949 :: accuracy 50.000000], [ Generator :: loss: 0.166165]\nepoch: 920, [Discriminator :: d_loss: 1.288967 :: accuracy 50.000000], [ Generator :: loss: 0.156506]\nepoch: 921, [Discriminator :: d_loss: 1.289526 :: accuracy 50.000000], [ Generator :: loss: 0.168022]\nepoch: 922, [Discriminator :: d_loss: 1.351011 :: accuracy 50.000000], [ Generator :: loss: 0.146869]\nepoch: 923, [Discriminator :: d_loss: 1.284870 :: accuracy 50.000000], [ Generator :: loss: 0.153496]\nepoch: 924, [Discriminator :: d_loss: 1.330086 :: accuracy 50.000000], [ Generator :: loss: 0.172348]\nepoch: 925, [Discriminator :: d_loss: 1.344760 :: accuracy 50.000000], [ Generator :: loss: 0.164661]\nepoch: 926, [Discriminator :: d_loss: 1.415506 :: accuracy 50.000000], [ Generator :: loss: 0.146224]\nepoch: 927, [Discriminator :: d_loss: 1.372584 :: accuracy 50.000000], [ Generator :: loss: 0.153492]\nepoch: 928, [Discriminator :: d_loss: 1.356941 :: accuracy 50.000000], [ Generator :: loss: 0.128345]\nepoch: 929, [Discriminator :: d_loss: 1.365731 :: accuracy 50.000000], [ Generator :: loss: 0.140538]\nepoch: 930, [Discriminator :: d_loss: 1.355075 :: accuracy 50.000000], [ Generator :: loss: 0.148214]\nepoch: 931, [Discriminator :: d_loss: 1.320487 :: accuracy 50.000000], [ Generator :: loss: 0.148189]\nepoch: 932, [Discriminator :: d_loss: 1.282649 :: accuracy 50.000000], [ Generator :: loss: 0.183372]\nepoch: 933, [Discriminator :: d_loss: 1.365385 :: accuracy 50.000000], [ Generator :: loss: 0.144628]\nepoch: 934, [Discriminator :: d_loss: 1.404719 :: accuracy 50.000000], [ Generator :: loss: 0.135051]\nepoch: 935, [Discriminator :: d_loss: 1.319051 :: accuracy 50.000000], [ Generator :: loss: 0.130154]\nepoch: 936, [Discriminator :: d_loss: 1.459624 :: accuracy 50.000000], [ Generator :: loss: 0.166163]\nepoch: 937, [Discriminator :: d_loss: 1.313100 :: accuracy 50.000000], [ Generator :: loss: 0.143157]\nepoch: 938, [Discriminator :: d_loss: 1.327336 :: accuracy 50.000000], [ Generator :: loss: 0.144208]\nepoch: 939, [Discriminator :: d_loss: 1.289692 :: accuracy 50.000000], [ Generator :: loss: 0.141772]\nepoch: 940, [Discriminator :: d_loss: 1.326839 :: accuracy 50.000000], [ Generator :: loss: 0.141892]\nepoch: 941, [Discriminator :: d_loss: 1.306842 :: accuracy 50.000000], [ Generator :: loss: 0.160820]\nepoch: 942, [Discriminator :: d_loss: 1.255213 :: accuracy 50.000000], [ Generator :: loss: 0.167299]\nepoch: 943, [Discriminator :: d_loss: 1.264072 :: accuracy 50.000000], [ Generator :: loss: 0.247051]\nepoch: 944, [Discriminator :: d_loss: 1.424215 :: accuracy 50.000000], [ Generator :: loss: 0.135596]\nepoch: 945, [Discriminator :: d_loss: 1.368011 :: accuracy 50.000000], [ Generator :: loss: 0.140480]\nepoch: 946, [Discriminator :: d_loss: 1.485852 :: accuracy 50.000000], [ Generator :: loss: 0.134752]\nepoch: 947, [Discriminator :: d_loss: 1.269164 :: accuracy 50.000000], [ Generator :: loss: 0.158805]\nepoch: 948, [Discriminator :: d_loss: 1.466618 :: accuracy 50.000000], [ Generator :: loss: 0.137209]\nepoch: 949, [Discriminator :: d_loss: 1.295571 :: accuracy 50.000000], [ Generator :: loss: 0.162435]\nepoch: 950, [Discriminator :: d_loss: 1.332838 :: accuracy 50.000000], [ Generator :: loss: 0.150028]\nepoch: 951, [Discriminator :: d_loss: 1.375920 :: accuracy 50.000000], [ Generator :: loss: 0.157300]\nepoch: 952, [Discriminator :: d_loss: 1.321593 :: accuracy 50.000000], [ Generator :: loss: 0.149152]\nepoch: 953, [Discriminator :: d_loss: 1.257839 :: accuracy 50.000000], [ Generator :: loss: 0.150853]\nepoch: 954, [Discriminator :: d_loss: 1.374158 :: accuracy 50.000000], [ Generator :: loss: 0.155939]\nepoch: 955, [Discriminator :: d_loss: 1.335638 :: accuracy 50.000000], [ Generator :: loss: 0.139727]\nepoch: 956, [Discriminator :: d_loss: 1.363393 :: accuracy 50.000000], [ Generator :: loss: 0.145972]\nepoch: 957, [Discriminator :: d_loss: 1.372163 :: accuracy 50.000000], [ Generator :: loss: 0.142340]\nepoch: 958, [Discriminator :: d_loss: 1.264469 :: accuracy 50.000000], [ Generator :: loss: 0.154761]\nepoch: 959, [Discriminator :: d_loss: 1.387326 :: accuracy 50.000000], [ Generator :: loss: 0.173903]\nepoch: 960, [Discriminator :: d_loss: 1.295082 :: accuracy 50.000000], [ Generator :: loss: 0.158562]\nepoch: 961, [Discriminator :: d_loss: 1.385520 :: accuracy 50.000000], [ Generator :: loss: 0.143173]\nepoch: 962, [Discriminator :: d_loss: 1.315759 :: accuracy 50.000000], [ Generator :: loss: 0.129431]\nepoch: 963, [Discriminator :: d_loss: 1.414786 :: accuracy 50.000000], [ Generator :: loss: 0.161651]\nepoch: 964, [Discriminator :: d_loss: 1.417150 :: accuracy 50.000000], [ Generator :: loss: 0.162016]\nepoch: 965, [Discriminator :: d_loss: 1.343762 :: accuracy 50.000000], [ Generator :: loss: 0.155927]\nepoch: 966, [Discriminator :: d_loss: 1.416860 :: accuracy 50.000000], [ Generator :: loss: 0.147300]\nepoch: 967, [Discriminator :: d_loss: 1.311802 :: accuracy 50.000000], [ Generator :: loss: 0.147265]\nepoch: 968, [Discriminator :: d_loss: 1.366563 :: accuracy 50.000000], [ Generator :: loss: 0.148170]\nepoch: 969, [Discriminator :: d_loss: 1.307251 :: accuracy 50.000000], [ Generator :: loss: 0.154937]\nepoch: 970, [Discriminator :: d_loss: 1.314181 :: accuracy 50.000000], [ Generator :: loss: 0.151044]\nepoch: 971, [Discriminator :: d_loss: 1.348716 :: accuracy 50.000000], [ Generator :: loss: 0.149404]\nepoch: 972, [Discriminator :: d_loss: 1.329032 :: accuracy 50.000000], [ Generator :: loss: 0.148345]\nepoch: 973, [Discriminator :: d_loss: 1.301406 :: accuracy 50.000000], [ Generator :: loss: 0.149210]\nepoch: 974, [Discriminator :: d_loss: 1.268710 :: accuracy 50.000000], [ Generator :: loss: 0.146909]\nepoch: 975, [Discriminator :: d_loss: 1.380445 :: accuracy 50.000000], [ Generator :: loss: 0.156628]\nepoch: 976, [Discriminator :: d_loss: 1.295477 :: accuracy 50.000000], [ Generator :: loss: 0.165154]\n","name":"stdout"},{"output_type":"stream","text":"epoch: 977, [Discriminator :: d_loss: 1.330525 :: accuracy 50.000000], [ Generator :: loss: 0.169313]\nepoch: 978, [Discriminator :: d_loss: 1.275702 :: accuracy 50.000000], [ Generator :: loss: 0.174594]\nepoch: 979, [Discriminator :: d_loss: 1.349019 :: accuracy 50.000000], [ Generator :: loss: 0.133950]\nepoch: 980, [Discriminator :: d_loss: 1.432758 :: accuracy 50.000000], [ Generator :: loss: 0.135950]\nepoch: 981, [Discriminator :: d_loss: 1.377442 :: accuracy 50.000000], [ Generator :: loss: 0.154607]\nepoch: 982, [Discriminator :: d_loss: 1.378561 :: accuracy 50.000000], [ Generator :: loss: 0.169859]\nepoch: 983, [Discriminator :: d_loss: 1.325676 :: accuracy 50.000000], [ Generator :: loss: 0.137348]\nepoch: 984, [Discriminator :: d_loss: 1.395644 :: accuracy 50.000000], [ Generator :: loss: 0.132447]\nepoch: 985, [Discriminator :: d_loss: 1.394068 :: accuracy 50.000000], [ Generator :: loss: 0.155760]\nepoch: 986, [Discriminator :: d_loss: 1.366252 :: accuracy 50.000000], [ Generator :: loss: 0.157121]\nepoch: 987, [Discriminator :: d_loss: 1.360847 :: accuracy 50.000000], [ Generator :: loss: 0.130663]\nepoch: 988, [Discriminator :: d_loss: 1.383152 :: accuracy 50.000000], [ Generator :: loss: 0.129163]\nepoch: 989, [Discriminator :: d_loss: 1.364948 :: accuracy 50.000000], [ Generator :: loss: 0.150445]\nepoch: 990, [Discriminator :: d_loss: 1.419047 :: accuracy 50.000000], [ Generator :: loss: 0.150573]\nepoch: 991, [Discriminator :: d_loss: 1.292106 :: accuracy 50.000000], [ Generator :: loss: 0.155657]\nepoch: 992, [Discriminator :: d_loss: 1.324995 :: accuracy 50.000000], [ Generator :: loss: 0.165597]\nepoch: 993, [Discriminator :: d_loss: 1.326571 :: accuracy 50.000000], [ Generator :: loss: 0.146740]\nepoch: 994, [Discriminator :: d_loss: 1.314029 :: accuracy 50.000000], [ Generator :: loss: 0.146821]\nepoch: 995, [Discriminator :: d_loss: 1.344914 :: accuracy 50.000000], [ Generator :: loss: 0.144763]\nepoch: 996, [Discriminator :: d_loss: 1.359521 :: accuracy 50.000000], [ Generator :: loss: 0.164641]\nepoch: 997, [Discriminator :: d_loss: 1.299323 :: accuracy 50.000000], [ Generator :: loss: 0.152822]\nepoch: 998, [Discriminator :: d_loss: 1.385504 :: accuracy 50.000000], [ Generator :: loss: 0.149336]\nepoch: 999, [Discriminator :: d_loss: 1.381875 :: accuracy 50.000000], [ Generator :: loss: 0.172804]\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"noise = np.random.normal(0,1,(20,100))\nimg = gan.G.predict(noise)\n\nfor i in range(20):\n plt.subplot(4,5,i+1)\n plt.imshow(img[i].reshape((28,28)))\nplt.show()","execution_count":26,"outputs":[{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{}}]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}