{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"

Imports

\n","metadata":{}},{"cell_type":"code","source":"\n\nimport os\nimport pathlib\nimport time\nimport datetime\nimport imageio\nfrom glob import glob\n\n\n\nimport tensorflow as tf\nimport numpy as np \nimport tensorflow.keras.backend as K\nimport tensorflow_addons as tfa\n\n\nfrom matplotlib import pyplot as plt\nfrom IPython import display\nfrom termcolor import colored\nfrom tqdm import tqdm\nfrom IPython.display import Image\nimport PIL\nfrom PIL import ImageDraw\nfrom IPython import display\n\ndef color_print(print_str,\n print_color='green'):\n \n '''print in given color (default green)'''\n print(colored(print_str,print_color))\n\n","metadata":{"execution":{"iopub.status.busy":"2023-04-28T08:14:55.797665Z","iopub.execute_input":"2023-04-28T08:14:55.798084Z","iopub.status.idle":"2023-04-28T08:15:02.210271Z","shell.execute_reply.started":"2023-04-28T08:14:55.797995Z","shell.execute_reply":"2023-04-28T08:15:02.209203Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\ndef set_seed(seed):\n np.random.seed(seed)\n tf.random.set_seed(seed)\n os.environ['PYTHONHASHSEED'] = str(seed)\n os.environ['TF_DETERMINISTIC_OPS'] = '1'\n print(f'setting seed to {seed}')\n \n\nclass CFG:\n \n # Dimension of image\n IMG_WIDTH = 512\n IMG_HEIGHT = 512\n \n #resize image \n resize_height = 700\n resize_width = 1200\n \n #the lambda param in loss\n LAMBDA = 10\n #--------train pipe-------------\n BUFFER_SIZE = 100\n # The batch size of 1 produced better results for the U-Net in the original pix2pix experiment\n BATCH_SIZE = 2\n \n #cache \n cache= 50\n \n #learning rate \n learning_rate = 0.00025\n \n \n seed = 7 \n \n\nset_seed(CFG.seed)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-04-28T08:15:02.212392Z","iopub.execute_input":"2023-04-28T08:15:02.213043Z","iopub.status.idle":"2023-04-28T08:15:02.221172Z","shell.execute_reply.started":"2023-04-28T08:15:02.213010Z","shell.execute_reply":"2023-04-28T08:15:02.220137Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

Data directories

\n","metadata":{}},{"cell_type":"code","source":"day_dir = '../input/daynight-cityview/day'\nnight_dir = '../input/daynight-cityview/night'\n\n\n#plotting a sample image \nplt.figure(figsize=(16,8))\n\nimg = plt.imread(day_dir + '/' + os.listdir(day_dir)[0])\nplt.imshow(img)\nplt.axis('off')\nplt.title('sample image')\nprint(f'Image dimensions {img.shape}')\nplt.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-04-28T08:15:02.223997Z","iopub.execute_input":"2023-04-28T08:15:02.225262Z","iopub.status.idle":"2023-04-28T08:15:02.931410Z","shell.execute_reply.started":"2023-04-28T08:15:02.225218Z","shell.execute_reply":"2023-04-28T08:15:02.930274Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

building data loading pipeline

\n","metadata":{}},{"cell_type":"code","source":"def load_image(image_file):\n '''load a image file'''\n image = tf.io.read_file(image_file)\n image = tf.io.decode_jpeg(image)\n \n return image\n\n\ndef random_crop(image):\n '''randomly crop image into defined size '''\n cropped_image = tf.image.random_crop(image, size=[CFG.IMG_HEIGHT, CFG.IMG_WIDTH, 3])\n\n return cropped_image\n\n\ndef normalize(image):\n '''normalizing the images to [-1, 1]'''\n image = tf.cast(image, tf.float32)\n image = (image / 127.5) - 1\n return image\n\n\ndef de_normalize(image):\n '''De normalize the image to be in range (0,1)'''\n \n return (image * 0.5) + 0.5\n ","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-04-28T08:15:02.933477Z","iopub.execute_input":"2023-04-28T08:15:02.933896Z","iopub.status.idle":"2023-04-28T08:15:02.942758Z","shell.execute_reply.started":"2023-04-28T08:15:02.933863Z","shell.execute_reply":"2023-04-28T08:15:02.941912Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def image_augmentations(image):\n '''perform spatial augmentations (rotation and flips) on input image\n \n from : https://www.kaggle.com/code/dimitreoliveira/improving-cyclegan-monet-paintings'''\n \n \n # --------------------rotations----------\n #rotation probabliity\n p_rotate = tf.random.uniform([], 0, 1.0, dtype=tf.float32)\n \n if p_rotate > .8:\n image = tf.image.rot90(image, k=3) # rotate 270º\n elif p_rotate > .6:\n image = tf.image.rot90(image, k=2) # rotate 180º\n elif p_rotate > .4:\n image = tf.image.rot90(image, k=1) # rotate 90º\n \n \n \n # ----------------------Flips---------------------\n p_flip = tf.random.uniform([], 0, 1.0, dtype=tf.float32)\n \n if p_flip > 0.7: \n image = tf.image.random_flip_left_right(image)\n elif p_flip < 0.3:\n image = tf.image.random_flip_up_down(image)\n \n return image","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-04-28T08:15:02.944162Z","iopub.execute_input":"2023-04-28T08:15:02.944680Z","iopub.status.idle":"2023-04-28T08:15:03.098378Z","shell.execute_reply.started":"2023-04-28T08:15:02.944648Z","shell.execute_reply":"2023-04-28T08:15:03.097313Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def random_jitter(image):\n '''resize and randommly crop the input image'''\n \n# # resizing image\n image = tf.image.resize(image, size=(CFG.resize_height, CFG.resize_width),\n method=tf.image.ResizeMethod.NEAREST_NEIGHBOR)\n\n # randomly cropping to 512,512\n image = random_crop(image)\n \n return image\n\n\ndef preprocess_image_train(image):\n image = load_image(image)\n image = random_jitter(image)\n image= image_augmentations(image)\n image = normalize(image)\n return image\n\n\n#same function, withou the augemntation\ndef preprocess_image_eval(image):\n image = load_image(image)\n image = random_jitter(image)\n image = normalize(image)\n return image\n\n","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-04-28T08:15:03.099820Z","iopub.execute_input":"2023-04-28T08:15:03.100312Z","iopub.status.idle":"2023-04-28T08:15:03.110949Z","shell.execute_reply.started":"2023-04-28T08:15:03.100267Z","shell.execute_reply":"2023-04-28T08:15:03.110080Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\n\ndef create_img_dataset(directory,\n image_preprocess_fn,\n image_extension = 'jpg', \n repeat=True\n ):\n '''create a tf dataset object from a directory of images'''\n img_list = glob(directory+f'/*{image_extension}')\n \n dataset = tf.data.Dataset.list_files(img_list)\n \n dataset = dataset.map(image_preprocess_fn,\n num_parallel_calls=tf.data.AUTOTUNE)\n \n if repeat :\n dataset = dataset.repeat()\n \n dataset = dataset.shuffle(CFG.BUFFER_SIZE) \n dataset = dataset.batch(CFG.BATCH_SIZE)\n return dataset\n\n\nDay_Dataset = create_img_dataset(directory = day_dir,image_preprocess_fn = preprocess_image_train)\n\n#without augmentation\nDay_eval = create_img_dataset(directory = day_dir,\n image_preprocess_fn = preprocess_image_eval)\n\n\n\nfig,ax = plt.subplots(figsize=(16,8))\n \ninp_img = next(iter(Day_Dataset))\nplt.imshow(de_normalize(inp_img[0]))\nplt.title('Sample Day image')\nplt.axis('off')\n\nplt.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-04-28T08:15:03.116878Z","iopub.execute_input":"2023-04-28T08:15:03.118550Z","iopub.status.idle":"2023-04-28T08:15:14.172113Z","shell.execute_reply.started":"2023-04-28T08:15:03.118511Z","shell.execute_reply":"2023-04-28T08:15:14.171253Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"Night_Dataset = create_img_dataset(directory = night_dir,image_preprocess_fn = preprocess_image_train)\nNight_eval = create_img_dataset(directory = night_dir,\n image_preprocess_fn = preprocess_image_eval)\nfig,ax = plt.subplots(figsize=(16,8))\n\n\ninp_img = next(iter(Night_Dataset))\nplt.imshow(de_normalize(inp_img[0]))\nplt.title('Sample Night image')\nplt.axis('off')\n\nplt.show()\n","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-04-28T08:15:14.173385Z","iopub.execute_input":"2023-04-28T08:15:14.174145Z","iopub.status.idle":"2023-04-28T08:15:20.016721Z","shell.execute_reply.started":"2023-04-28T08:15:14.174089Z","shell.execute_reply":"2023-04-28T08:15:20.015885Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# train data set \n\nTrain_Dataset = tf.data.Dataset.zip((Day_Dataset,Night_Dataset))","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-04-28T08:15:20.017946Z","iopub.execute_input":"2023-04-28T08:15:20.018789Z","iopub.status.idle":"2023-04-28T08:15:20.025810Z","shell.execute_reply.started":"2023-04-28T08:15:20.018749Z","shell.execute_reply":"2023-04-28T08:15:20.025062Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

Building Model

\n","metadata":{}},{"cell_type":"markdown","source":"**Upsampling and downsampling blocks**","metadata":{}},{"cell_type":"code","source":"\n#conv weights initilaizer\nconv_initializer = tf.random_normal_initializer(mean=0.0,\n stddev=0.02)\n\n#init for intance normalization\ngamma_initializer = tf.keras.initializers.RandomNormal(mean=0.0, \n stddev=0.02)\n \n \n \n \ndef downsample(input_layer,\n filters,\n name,\n size=3, \n strides=2, \n activation=tf.keras.layers.ReLU(), \n ):\n \n '''perform a downsampling by applying a convolution,followed by instance norm and activation'''\n conv = tf.keras.layers.Conv2D(filters, \n size, \n strides=strides, \n padding='same', \n use_bias=False, \n kernel_initializer=conv_initializer, \n name=f'encoder_{name}')(input_layer)\n\n \n conv = tfa.layers.InstanceNormalization(axis=-1,gamma_initializer=gamma_initializer)(conv)\n \n conv = activation(conv)\n\n return conv\n\n\ndef upsample(input_layer,\n filters,\n name,\n size=3,\n strides=2,\n activation='relu'):\n \n res = tf.keras.layers.Conv2DTranspose(filters, size, \n strides=strides, \n padding='same', \n use_bias=False, \n kernel_initializer=conv_initializer, \n name=f'decoder_{name}')(input_layer)\n\n res = tfa.layers.InstanceNormalization(gamma_initializer=gamma_initializer)(res)\n\n res = tf.keras.layers.Activation(activation)(res)\n \n return res","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-04-28T08:15:20.027667Z","iopub.execute_input":"2023-04-28T08:15:20.028091Z","iopub.status.idle":"2023-04-28T08:15:20.058313Z","shell.execute_reply.started":"2023-04-28T08:15:20.028055Z","shell.execute_reply":"2023-04-28T08:15:20.057461Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Residual block**","metadata":{}},{"cell_type":"code","source":"\ndef residual_block(input_layer, \n size=3, \n strides=1, \n name='block_x'):\n '''performs 2 convolutions followed by an added skip connection with the input'''\n \n \n filters = input_layer.shape[-1]\n block = tf.keras.layers.Conv2D(filters, \n size,\n strides=strides,\n padding='same',\n use_bias=False, \n kernel_initializer=conv_initializer,\n name=f'residual_{name}')(input_layer)\n \n block = tf.keras.layers.Activation('relu')(block)\n block = tf.keras.layers.Conv2D(filters, size, strides=strides, padding='same', use_bias=False, \n kernel_initializer=conv_initializer, name=f'transformer_{name}_2')(block) \n \n #skip connection\n res = tf.keras.layers.Add()([block, input_layer])\n\n return res\n\n\ndef concat_layer(layer_1,layer_2,name):\n '''concatenation of layers for skip connections'''\n return tf.keras.layers.Concatenate(name=name)([layer_1,layer_2])\n","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-04-28T08:15:20.063297Z","iopub.execute_input":"2023-04-28T08:15:20.063603Z","iopub.status.idle":"2023-04-28T08:15:20.072650Z","shell.execute_reply.started":"2023-04-28T08:15:20.063578Z","shell.execute_reply":"2023-04-28T08:15:20.071629Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

Building Generator

\n","metadata":{}},{"cell_type":"code","source":"def get_generator(num_residual_connections=6):\n \n input_ = tf.keras.layers.Input(shape=(CFG.IMG_WIDTH,CFG.IMG_HEIGHT,3), \n name='input_layer')\n \n #-----------------------ENCODER-------------------------------\n #downsample images \n enc1 = downsample(input_layer = input_, filters=64, strides = 1, size=7, name='dwn_1') # (bs, 512,512, 64)\n enc2 = downsample(input_layer=enc1,filters= 128,size = 3, strides = 2, name='dwn_2') # (bs, 256, 256, 128)\n enc3 = downsample(input_layer=enc2, filters=256,size = 3, strides =2, name='dwn_3') # (bs, 128,128,256)\n enc4 = downsample(input_layer=enc3, filters=256,size = 3, strides =2, name='dwn_4') # (bs, 64,64,256)\n \n \n #-----------------------Residual connections-------------------------------\n x = enc4\n for n in range(num_residual_connections):\n x = residual_block(input_layer=x, name=f'res_block_{n+1}') # (bs, 64, 64, 256)\n\n #-----------------------DECODER-------------------------------\n #UNET like skip connection \n #upsample 1\n x_skip = concat_layer(layer_1=x,layer_2=enc4,name='skip_1') \n dec1 = upsample(x_skip,filters=256 ,name='upsam_1') # (bs, 128, 128, 256)\n \n #upsample 2\n x_skip = concat_layer(layer_1=dec1,layer_2=enc3,name='skip_2') \n dec_2 = upsample(x_skip, filters=128,name='upsam_2') # (bs, 256, 256, 128)\n \n #upsample 3\n x_skip = concat_layer(layer_1=dec_2,layer_2=enc2,name='skip_3') \n dec_3 = upsample(x_skip, filters= 64,name='upsam_3') # (bs, 512, 512, 64)\n \n #penultimate\n x_skip = concat_layer(layer_1=dec_3,\n layer_2=enc1,\n name='skip_final')\n\n output = tf.keras.layers.Conv2D(filters = 3,kernel_size = 7, strides=1, padding='same', \n kernel_initializer=conv_initializer, use_bias=False, activation='tanh', \n name='output_layer')(x_skip) \n\n \n return tf.keras.models.Model(inputs=input_,outputs=output)\n\n\n\n\n# day images -> night images \nday2night_gen = get_generator()\n\n# night images -> day images \nnight2day_gen = get_generator()\n\n\n#plot model\n# tf.keras.utils.plot_model(day2night_gen)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-04-28T08:15:20.074032Z","iopub.execute_input":"2023-04-28T08:15:20.074807Z","iopub.status.idle":"2023-04-28T08:15:21.108480Z","shell.execute_reply.started":"2023-04-28T08:15:20.074770Z","shell.execute_reply":"2023-04-28T08:15:21.107510Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#passing in a input to generator for check \n#plot a sample output\ngen_output = night2day_gen(inp_img, training=False)[0]\nplt.subplots(1,2,figsize=(16,8))\n\n\nplt.subplot(1,2,1)\nplt.imshow(gen_output.numpy().squeeze())\nplt.title('Untrained Night2Day Generator output')\nplt.axis('off')\n\n\nplt.subplot(1,2,2)\nplt.imshow(de_normalize(inp_img[0]))\nplt.title('Original Night image')\nplt.axis('off')\n\nplt.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-04-28T08:15:21.110136Z","iopub.execute_input":"2023-04-28T08:15:21.110565Z","iopub.status.idle":"2023-04-28T08:15:28.893659Z","shell.execute_reply.started":"2023-04-28T08:15:21.110525Z","shell.execute_reply":"2023-04-28T08:15:28.892835Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

Building Discriminator

\n","metadata":{}},{"cell_type":"code","source":"\n\ndef PATCH_discriminator(leak_rate = 0.2):\n '''PATCH discriminator network'''\n leaky_relu = tf.keras.layers.LeakyReLU(leak_rate)\n\n \n input_ = tf.keras.layers.Input(shape=(CFG.IMG_WIDTH,CFG.IMG_HEIGHT,3), \n name='input_layer')\n # Encoder \n # Input image 512,512\n x = downsample(input_layer = input_, filters=64, strides = 2, size=4, name='dwn_1',activation = leaky_relu) #h,w =256\n x = downsample(input_layer = x, filters=128, strides = 2, size=4, name='dwn_2',activation = leaky_relu) #h,w =128\n x = downsample(input_layer = x, filters=256, strides = 2, size=4, name='dwn_3',activation = leaky_relu) #h,w = 64\n x = downsample(input_layer = x, filters=512, strides = 2, size=4, name='dwn_4',activation = leaky_relu) #h,w = 32\n x = downsample(input_layer = x, filters=512, strides = 1, size=4, name='dwn_5',activation = leaky_relu) #h,w = 32\n \n \n output = tf.keras.layers.Conv2D(1, 4, strides=1, padding='valid', kernel_initializer=conv_initializer)(x) #(29, 29, 1)\n \n return tf.keras.models.Model(inputs=input_,outputs=output)\n\n\n\n#create instance of discriminators \nday2night_disc = PATCH_discriminator() # identify night images\nnight2day_disc = PATCH_discriminator() # identify day images\n","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-04-28T08:15:28.894983Z","iopub.execute_input":"2023-04-28T08:15:28.896364Z","iopub.status.idle":"2023-04-28T08:15:29.194616Z","shell.execute_reply.started":"2023-04-28T08:15:28.896326Z","shell.execute_reply":"2023-04-28T08:15:29.193648Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#check on dicriminator \n\ndisc_output = day2night_disc(inp_img, training=False)\nplt.subplots(1,1,figsize=(8,8))\n\nplt.imshow(disc_output.numpy().mean(axis=0),cmap='gray')\nplt.title('Untrained Night2Day disc output')\nplt.axis('off')\n\nplt.show()","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-04-28T08:15:29.195977Z","iopub.execute_input":"2023-04-28T08:15:29.196977Z","iopub.status.idle":"2023-04-28T08:15:29.475973Z","shell.execute_reply.started":"2023-04-28T08:15:29.196920Z","shell.execute_reply":"2023-04-28T08:15:29.474511Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def generate_cycle(gen_1,gen_2,input_image):\n '''generate a full cycle of images using given generators'''\n gen_img_1 = gen_1(input_image,training=True)\n gen_img_2 = gen_2(gen_img_1,training=True)\n \n return gen_img_1,gen_img_2\n\n\ndef calc_and_apply_gradients(tape,\n model,\n loss,\n optimizer):\n '''Apply gradients for a given model using given optimizer'''\n \n #calculate gradients of loss function\n gradients = tape.gradient(loss,model.trainable_variables)\n \n #apply gradients \n optimizer.apply_gradients(zip(gradients,model.trainable_variables))\n return ","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-04-28T08:15:29.483125Z","iopub.execute_input":"2023-04-28T08:15:29.487328Z","iopub.status.idle":"2023-04-28T08:15:29.494793Z","shell.execute_reply.started":"2023-04-28T08:15:29.487266Z","shell.execute_reply":"2023-04-28T08:15:29.493918Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

losses

","metadata":{}},{"cell_type":"code","source":"def discriminator_loss(real, generated):\n '''discriminator Binary CrossEntropy loss'''\n real_loss = tf.keras.losses.BinaryCrossentropy(from_logits=True)(tf.ones_like(real), real)\n\n generated_loss = tf.keras.losses.BinaryCrossentropy(from_logits=True)(tf.zeros_like(generated), generated)\n\n total_disc_loss = real_loss + generated_loss\n\n return total_disc_loss * 0.5\n\n# Generator Adverserial loss\ndef generator_loss(generated):\n '''adverserial generator loss (BCE)'''\n return tf.keras.losses.BinaryCrossentropy(from_logits=True)(tf.ones_like(generated), generated)\n\n \n# Cycle consistency loss \n \ndef calc_cycle_loss(real_image, cycled_image, LAMBDA):\n '''pixel wise cycle loss between original image and cycled image'''\n mae_loss = tf.reduce_mean(tf.abs(real_image - cycled_image))\n\n return LAMBDA * mae_loss\n\n\n# identity loss\ndef identity_loss(real_image, same_image, LAMBDA): \n mae_loss = tf.reduce_mean(tf.abs(real_image - same_image))\n return LAMBDA * 0.5 * mae_loss","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-04-28T08:15:29.498082Z","iopub.execute_input":"2023-04-28T08:15:29.498848Z","iopub.status.idle":"2023-04-28T08:15:29.509366Z","shell.execute_reply.started":"2023-04-28T08:15:29.498804Z","shell.execute_reply":"2023-04-28T08:15:29.508587Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

Cycle GAN

\n","metadata":{}},{"cell_type":"code","source":"class CycleGAN(tf.keras.models.Model):\n def __init__(self,\n lambda_cycle=10):\n super(CycleGAN, self).__init__()\n self.gen_d2n = day2night_gen # Day -> Night \n self.gen_n2d = night2day_gen # Night -> Day\n self.disc_d2n = day2night_disc # Classifies Night Images\n self.disc_n2d = night2day_disc # Classifier Day Images \n self.lambda_cycle = lambda_cycle #lambda in cycle consistancy loss\n \n \n \n def compile(self,\n gen_loss_fn,\n disc_loss_fn,\n cycle_loss_fn,\n identity_loss_fn,\n common_opt = tf.keras.optimizers.Adam(learning_rate = CFG.learning_rate,beta_1 = 0.5)):\n \n super(CycleGAN, self).compile()\n \n # -------optimizers ---------\n self.opt_gen_d2n = common_opt\n self.opt_gen_n2d = common_opt\n self.opt_disc_d2n = common_opt\n self.opt_disc_n2d = common_opt\n \n \n # -------losses ---------\n self.gen_loss_fn = gen_loss_fn\n self.disc_loss_fn = disc_loss_fn\n self.cycle_loss_fn = cycle_loss_fn\n self.identity_loss_fn = identity_loss_fn\n \n \n def train_step(self, batch_data):\n day_image, night_image = batch_data\n \n with tf.GradientTape(persistent=True) as tape:\n \n #-----day->night->day\n fake_night,cycled_day = generate_cycle(self.gen_d2n,\n self.gen_n2d,\n day_image)\n \n\n # --------night -> day- > night\n fake_day,cycled_night = generate_cycle(self.gen_n2d,\n self.gen_d2n,\n night_image)\n \n #---------- generating itself (for identity loss)\n iden_day = self.gen_d2n(night_image, training=True)\n iden_night = self.gen_n2d(day_image, training=True)\n\n # -----------discriminator on real images\n disc_night = self.disc_d2n(night_image, training=True)\n disc_day = self.disc_n2d(day_image, training=True)\n\n # -----------discriminator on fake images-----------------\n disc_fake_night = self.disc_d2n(fake_night, training=True)\n disc_fake_day = self.disc_n2d(fake_day, training=True)\n\n # -------------------------generator loss-------------\n #---1)adverserial loss\n night_gen_loss = self.gen_loss_fn(disc_fake_night) \n day_gen_loss = self.gen_loss_fn(disc_fake_day)\n\n #---2)Cycle loss loss\n total_cycle_loss = self.cycle_loss_fn(night_image, cycled_night, self.lambda_cycle) + self.cycle_loss_fn(day_image, cycled_day, self.lambda_cycle)\n\n # +++++3) Total Gen loss (day gen and night gen)\n total_gen_d2n_loss = night_gen_loss + total_cycle_loss + self.identity_loss_fn(night_image, iden_night,self.lambda_cycle)\n total_gen_n2d_loss = day_gen_loss + total_cycle_loss + self.identity_loss_fn(day_image, iden_day, self.lambda_cycle)\n \n \n # -------------------------Discriminator loss-------------\n night_disc_loss = self.disc_loss_fn(disc_night, disc_fake_night) # check classifying generated and real night\n day_disc_loss = self.disc_loss_fn(disc_day, disc_fake_day) # check classifying generated and real day\n\n ## ------------------------- Calculating and Updating gradients------------------\n \n # day->night gen gradeints\n _ = calc_and_apply_gradients(tape=tape,\n model= self.gen_d2n,\n loss = total_gen_d2n_loss,\n optimizer = self.opt_gen_d2n)\n \n # night - >day gen gradeints\n _ = calc_and_apply_gradients(tape=tape,\n model= self.gen_n2d,\n loss = total_gen_n2d_loss,\n optimizer = self.opt_gen_n2d)\n \n # discrim gradients (classifies night images)\n _ = calc_and_apply_gradients(tape=tape,\n model= self.disc_d2n,\n loss = night_disc_loss,\n optimizer = self.opt_disc_d2n)\n \n # Day discrim gradients (classifies day images)\n _ = calc_and_apply_gradients(tape=tape,\n model= self.disc_n2d,\n loss = day_disc_loss,\n optimizer = self.opt_disc_n2d)\n \n \n return {'gen_D2N_loss': total_gen_d2n_loss,\n 'gen_N2D_loss': total_gen_n2d_loss,\n 'disc_day_loss': day_disc_loss,\n 'disc_night_loss': night_disc_loss\n }\n \n \n ","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-04-28T08:15:29.511332Z","iopub.execute_input":"2023-04-28T08:15:29.512061Z","iopub.status.idle":"2023-04-28T08:15:29.534869Z","shell.execute_reply.started":"2023-04-28T08:15:29.512021Z","shell.execute_reply":"2023-04-28T08:15:29.533824Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#creat a instance of Cycle gan \ngan = CycleGAN()\n\n\n#complie with the losses \ngan.compile(gen_loss_fn=generator_loss,\n disc_loss_fn=discriminator_loss,\n cycle_loss_fn=calc_cycle_loss,\n identity_loss_fn=identity_loss)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-04-28T08:15:29.536306Z","iopub.execute_input":"2023-04-28T08:15:29.537063Z","iopub.status.idle":"2023-04-28T08:15:29.565883Z","shell.execute_reply.started":"2023-04-28T08:15:29.537023Z","shell.execute_reply":"2023-04-28T08:15:29.564772Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

Callbacks

\n\n For reducing Learning Rate,stopping training and Visulization","metadata":{}},{"cell_type":"code","source":"#learning rate schedule \n\ndef scheduler(epoch, \n lr,\n decay_rate = 0.05,\n warm_up_period = 10):\n \n if epoch < warm_up_period:\n return lr\n elif (epoch > warm_up_period and epoch<40):\n return lr * tf.math.exp(decay_rate)\n else:\n return lr * tf.math.exp(decay_rate*2)\n \n \n \n \nlr_scheduler = tf.keras.callbacks.LearningRateScheduler(scheduler,\n verbose = 0)\n\n\n#early stopping \n\n# early_stop = tf.keras.callbacks.EarlyStopping(monitor = 'gen_N2D_loss',\n# mode = 'min',\n# patience = 10,\n# restore_best_weights = True)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-04-28T08:15:29.567259Z","iopub.execute_input":"2023-04-28T08:15:29.567894Z","iopub.status.idle":"2023-04-28T08:15:29.575436Z","shell.execute_reply.started":"2023-04-28T08:15:29.567858Z","shell.execute_reply":"2023-04-28T08:15:29.574341Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# early stopping : from https://stackoverflow.com/questions/64556120/early-stopping-with-multiple-conditions\n\nclass CustomEarlyStopping(tf.keras.callbacks.Callback):\n def __init__(self, patience=0):\n super(CustomEarlyStopping, self).__init__()\n self.patience = patience\n self.best_weights = None\n \n def on_train_begin(self, logs=None):\n \n # The number of epoch it has waited when loss is no longer minimum.\n self.wait = 0\n # The epoch the training stops at.\n self.stopped_epoch = 0\n # Initialize the best as infinity.\n self.n2d_loss = np.Inf\n self.d2n_loss = np.Inf\n\n def on_epoch_end(self, epoch, logs=None): \n n2d_loss=logs.get('gen_N2D_loss')\n d2n_loss=logs.get('gen_D2N_loss')\n\n # If both the conditions are met, continue training\n if (np.less(n2d_loss, self.n2d_loss) and np.less(d2n_loss, self.d2n_loss)):\n self.d2n_loss = d2n_loss\n self.n2d_loss = n2d_loss\n self.wait = 0\n # Record the best weights if current results is better (less).\n self.best_weights = self.model.get_weights()\n \n # if above xondition not met, continue training till patiance epochs\n else:\n self.wait += 1\n if self.wait >= self.patience:\n self.stopped_epoch = epoch\n self.model.stop_training = True\n print(\"Restoring model weights from the end of the best epoch.\")\n self.model.set_weights(self.best_weights)\n \n def on_train_end(self, logs=None):\n if self.stopped_epoch > 0:\n print(\"Epoch %05d: early stopping\" % (self.stopped_epoch + 1))\n","metadata":{"execution":{"iopub.status.busy":"2023-04-28T08:15:29.577109Z","iopub.execute_input":"2023-04-28T08:15:29.577829Z","iopub.status.idle":"2023-04-28T08:15:29.591207Z","shell.execute_reply.started":"2023-04-28T08:15:29.577793Z","shell.execute_reply":"2023-04-28T08:15:29.590140Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#--------------------------------------Viz Callbacks : from https://www.kaggle.com/code/dimitreoliveira/improving-cyclegan-monet-paintings -----------------------------------------\ndef display_samples(ds, n_samples):\n ds_iter = iter(ds)\n for n_sample in range(n_samples):\n example_sample = next(ds_iter)\n plt.subplot(121)\n plt.imshow(example_sample[0] * 0.5 + 0.5)\n plt.axis('off')\n plt.show()\n \ndef display_generated_samples(ds, model, n_samples):\n ds_iter = iter(ds)\n for n_sample in range(n_samples):\n example_sample = next(ds_iter)\n generated_sample = model.predict(example_sample)\n \n f = plt.figure(figsize=(16,8))\n \n plt.subplot(121)\n plt.title('Input image')\n plt.imshow(example_sample[0] * 0.5 + 0.5)\n plt.axis('off')\n \n plt.subplot(122)\n plt.title('Generated image')\n plt.imshow(generated_sample[0] * 0.5 + 0.5)\n plt.axis('off')\n plt.show()\n \ndef evaluate_cycle(ds, generator_a, generator_b, n_samples=1):\n fig, axes = plt.subplots(n_samples, 3, figsize=(22, (n_samples*6)))\n axes = axes.flatten()\n \n ds_iter = iter(ds)\n for n_sample in range(n_samples):\n idx = n_sample*3\n example_sample = next(ds_iter)\n generated_a_sample = generator_a.predict(example_sample)\n generated_b_sample = generator_b.predict(generated_a_sample)\n \n axes[idx].set_title('Input image', fontsize=18)\n axes[idx].imshow(example_sample[0] * 0.5 + 0.5)\n axes[idx].axis('off')\n \n axes[idx+1].set_title('Generated image', fontsize=18)\n axes[idx+1].imshow(generated_a_sample[0] * 0.5 + 0.5)\n axes[idx+1].axis('off')\n \n axes[idx+2].set_title('Cycled image', fontsize=18)\n axes[idx+2].imshow(generated_b_sample[0] * 0.5 + 0.5)\n axes[idx+2].axis('off')\n \n plt.show()\n \ndef predict_and_save(input_ds, generator_model, output_path):\n i = 1\n for img in input_ds:\n prediction = generator_model(img, training=False)[0].numpy() # make predition\n prediction = (prediction * 127.5 + 127.5).astype(np.uint8) # re-scale\n im = PIL.Image.fromarray(prediction)\n im.save(f'{output_path}{str(i)}.jpg')\n i += 1\n\n# Callback\nclass GANMonitor(tf.keras.callbacks.Callback):\n \"\"\"A callback to generate and save images after each epoch\"\"\"\n\n def __init__(self, \n num_img=1, \n day_paths='generated_day', \n night_paths='generated_night'):\n self.num_img = num_img\n self.day_paths = day_paths\n self.night_paths = night_paths\n \n # dir to save genereated day images\n if not os.path.exists(self.day_paths):\n os.makedirs(self.day_paths)\n \n \n # dir to save genereated night images\n if not os.path.exists(self.night_paths):\n os.makedirs(self.night_paths)\n\n \n \n def on_epoch_end(self, epoch, logs=None):\n #generated night \n for i, img in enumerate(Day_eval.take(self.num_img)):\n \n \n prediction = day2night_gen(img, training=False)[0].numpy()\n prediction = (prediction * 127.5 + 127.5).astype(np.uint8)\n prediction = PIL.Image.fromarray(prediction)\n prediction.save(f'{self.night_paths}/generated_{i}_{epoch+1}.png')\n \n # generated day images \n for i, img in enumerate(Night_eval.take(self.num_img)):\n prediction = night2day_gen(img, training=False)[0].numpy()\n prediction = (prediction * 127.5 + 127.5).astype(np.uint8)\n prediction = PIL.Image.fromarray(prediction)\n prediction.save(f'{self.day_paths}/generated_{i}_{epoch+1}.png')","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-04-28T08:15:29.593130Z","iopub.execute_input":"2023-04-28T08:15:29.593942Z","iopub.status.idle":"2023-04-28T08:15:29.622476Z","shell.execute_reply.started":"2023-04-28T08:15:29.593904Z","shell.execute_reply":"2023-04-28T08:15:29.621479Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

Fitting the model

\n","metadata":{}},{"cell_type":"code","source":"EPOCHS = 75\ncallbacks = [lr_scheduler,GANMonitor(),CustomEarlyStopping(patience = 10)]\nsteps_per_epoch = 200\n\n\nhistory = gan.fit(Train_Dataset,\n epochs = EPOCHS,\n steps_per_epoch=steps_per_epoch,\n callbacks = callbacks)","metadata":{"execution":{"iopub.status.busy":"2023-04-28T08:15:29.624191Z","iopub.execute_input":"2023-04-28T08:15:29.625041Z","iopub.status.idle":"2023-04-28T10:04:20.876112Z","shell.execute_reply.started":"2023-04-28T08:15:29.625003Z","shell.execute_reply":"2023-04-28T10:04:20.875028Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

Visualizing Training Progress

","metadata":{}},{"cell_type":"markdown","source":"

Visualizing Training Progress for Night -> Day generator

\n\n","metadata":{}},{"cell_type":"code","source":"\n\n# from https://www.kaggle.com/code/dimitreoliveira/improving-cyclegan-monet-paintings\ndef create_gif(images_path, gif_path):\n images = []\n filenames = glob(images_path)\n filenames.sort(key=lambda x: int(''.join(filter(str.isdigit, x))))\n for epoch, filename in enumerate(filenames):\n img = PIL.ImageDraw.Image.open(filename)\n ImageDraw.Draw(img).text((0, 0), # Coordinates\n f'Epoch {epoch+1}')\n images.append(img)\n imageio.mimsave(gif_path, images, fps=2) # Save gif\n \n \n \ncreate_gif('./generated_day/*.png', 'day.gif')\n\nprint('Training progress for Night -> Day Generator')\ndisplay.Image('./day.gif')","metadata":{"execution":{"iopub.status.busy":"2023-04-28T10:04:20.877569Z","iopub.execute_input":"2023-04-28T10:04:20.878243Z","iopub.status.idle":"2023-04-28T10:05:21.477422Z","shell.execute_reply.started":"2023-04-28T10:04:20.878204Z","shell.execute_reply":"2023-04-28T10:05:21.476112Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"","metadata":{}},{"cell_type":"markdown","source":"

Visualizing Training Progress for Day -> Night generator

\n","metadata":{}},{"cell_type":"code","source":"create_gif('./generated_night/*.png', 'night.gif')\n\n\nprint('Training progress for Day-> Generator')\ndisplay.Image('./night.gif')","metadata":{"execution":{"iopub.status.busy":"2023-04-28T10:05:21.479670Z","iopub.execute_input":"2023-04-28T10:05:21.480570Z","iopub.status.idle":"2023-04-28T10:05:24.964812Z","shell.execute_reply.started":"2023-04-28T10:05:21.480527Z","shell.execute_reply":"2023-04-28T10:05:24.962022Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

Results

\n","metadata":{}},{"cell_type":"markdown","source":"

Evaluating Day -> Night Generator

\n","metadata":{}},{"cell_type":"code","source":"display_generated_samples(Day_eval.take(2), day2night_gen, 2)","metadata":{"execution":{"iopub.status.busy":"2023-04-28T10:05:24.966707Z","iopub.execute_input":"2023-04-28T10:05:24.967497Z","iopub.status.idle":"2023-04-28T10:05:31.428369Z","shell.execute_reply.started":"2023-04-28T10:05:24.967445Z","shell.execute_reply":"2023-04-28T10:05:31.427222Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display_generated_samples(Day_eval.take(2), day2night_gen, 2)","metadata":{"execution":{"iopub.status.busy":"2023-04-28T10:05:31.430399Z","iopub.execute_input":"2023-04-28T10:05:31.430975Z","iopub.status.idle":"2023-04-28T10:05:37.247188Z","shell.execute_reply.started":"2023-04-28T10:05:31.430924Z","shell.execute_reply":"2023-04-28T10:05:37.246111Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display_generated_samples(Day_eval.take(2), day2night_gen, 2)","metadata":{"execution":{"iopub.status.busy":"2023-04-28T10:05:37.249526Z","iopub.execute_input":"2023-04-28T10:05:37.250005Z","iopub.status.idle":"2023-04-28T10:05:47.490393Z","shell.execute_reply.started":"2023-04-28T10:05:37.249944Z","shell.execute_reply":"2023-04-28T10:05:47.489274Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

Evaluating Night -> Day Generator

\n","metadata":{}},{"cell_type":"code","source":"display_generated_samples(Night_eval.take(2), night2day_gen, 2)","metadata":{"execution":{"iopub.status.busy":"2023-04-28T10:05:47.492583Z","iopub.execute_input":"2023-04-28T10:05:47.493073Z","iopub.status.idle":"2023-04-28T10:05:53.743231Z","shell.execute_reply.started":"2023-04-28T10:05:47.493037Z","shell.execute_reply":"2023-04-28T10:05:53.742264Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display_generated_samples(Night_eval.take(2), night2day_gen, 2)","metadata":{"execution":{"iopub.status.busy":"2023-04-28T10:05:53.744984Z","iopub.execute_input":"2023-04-28T10:05:53.745680Z","iopub.status.idle":"2023-04-28T10:06:03.989705Z","shell.execute_reply.started":"2023-04-28T10:05:53.745645Z","shell.execute_reply":"2023-04-28T10:06:03.988670Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display_generated_samples(Night_eval.take(2), night2day_gen, 2)","metadata":{"execution":{"iopub.status.busy":"2023-04-28T10:06:03.992032Z","iopub.execute_input":"2023-04-28T10:06:03.992720Z","iopub.status.idle":"2023-04-28T10:06:14.236502Z","shell.execute_reply.started":"2023-04-28T10:06:03.992681Z","shell.execute_reply":"2023-04-28T10:06:14.235442Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

Evaluating Identity for Day to Night Generator so that Night -> Night

\n","metadata":{}},{"cell_type":"code","source":"display_generated_samples(Night_eval.take(2), day2night_gen, 2)","metadata":{"execution":{"iopub.status.busy":"2023-04-28T10:06:14.243547Z","iopub.execute_input":"2023-04-28T10:06:14.243855Z","iopub.status.idle":"2023-04-28T10:06:24.488090Z","shell.execute_reply.started":"2023-04-28T10:06:14.243829Z","shell.execute_reply":"2023-04-28T10:06:24.486919Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display_generated_samples(Night_eval.take(2), day2night_gen, 2)","metadata":{"execution":{"iopub.status.busy":"2023-04-28T10:06:24.490677Z","iopub.execute_input":"2023-04-28T10:06:24.491616Z","iopub.status.idle":"2023-04-28T10:06:34.736752Z","shell.execute_reply.started":"2023-04-28T10:06:24.491573Z","shell.execute_reply":"2023-04-28T10:06:34.735674Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display_generated_samples(Night_eval.take(2), day2night_gen, 2)","metadata":{"execution":{"iopub.status.busy":"2023-04-28T10:06:34.739864Z","iopub.execute_input":"2023-04-28T10:06:34.740571Z","iopub.status.idle":"2023-04-28T10:06:44.983525Z","shell.execute_reply.started":"2023-04-28T10:06:34.740533Z","shell.execute_reply":"2023-04-28T10:06:44.982486Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

Evaluating Identity for Night to Day Generator so that Day -> Day

\n","metadata":{}},{"cell_type":"code","source":"display_generated_samples(Day_eval.take(2), night2day_gen, 2)","metadata":{"execution":{"iopub.status.busy":"2023-04-28T10:06:44.986895Z","iopub.execute_input":"2023-04-28T10:06:44.987284Z","iopub.status.idle":"2023-04-28T10:06:55.230702Z","shell.execute_reply.started":"2023-04-28T10:06:44.987254Z","shell.execute_reply":"2023-04-28T10:06:55.229598Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display_generated_samples(Day_eval.take(2), night2day_gen, 2)","metadata":{"execution":{"iopub.status.busy":"2023-04-28T10:06:55.233012Z","iopub.execute_input":"2023-04-28T10:06:55.233632Z","iopub.status.idle":"2023-04-28T10:07:05.480133Z","shell.execute_reply.started":"2023-04-28T10:06:55.233591Z","shell.execute_reply":"2023-04-28T10:07:05.478982Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display_generated_samples(Day_eval.take(2), night2day_gen, 2)","metadata":{"execution":{"iopub.status.busy":"2023-04-28T10:07:05.482186Z","iopub.execute_input":"2023-04-28T10:07:05.482883Z","iopub.status.idle":"2023-04-28T10:07:11.558897Z","shell.execute_reply.started":"2023-04-28T10:07:05.482844Z","shell.execute_reply":"2023-04-28T10:07:11.558040Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

Cycle : Day(real image) -> Night -> Day

\n","metadata":{}},{"cell_type":"code","source":"evaluate_cycle(Day_eval.take(2),\n day2night_gen, \n night2day_gen, \n n_samples=2)","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2023-04-28T10:07:11.560950Z","iopub.execute_input":"2023-04-28T10:07:11.561772Z","iopub.status.idle":"2023-04-28T10:07:17.968647Z","shell.execute_reply.started":"2023-04-28T10:07:11.561734Z","shell.execute_reply":"2023-04-28T10:07:17.967705Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"evaluate_cycle(Day_eval.take(2),\n day2night_gen, \n night2day_gen, \n n_samples=2)","metadata":{"execution":{"iopub.status.busy":"2023-04-28T10:07:17.970632Z","iopub.execute_input":"2023-04-28T10:07:17.971475Z","iopub.status.idle":"2023-04-28T10:07:24.728742Z","shell.execute_reply.started":"2023-04-28T10:07:17.971438Z","shell.execute_reply":"2023-04-28T10:07:24.727320Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"

Cycle : Day(real image) -> Night -> Day

\n","metadata":{}},{"cell_type":"code","source":"evaluate_cycle(Night_eval.take(2),\n night2day_gen, \n day2night_gen, \n n_samples=2)\n","metadata":{"execution":{"iopub.status.busy":"2023-04-28T10:07:24.731107Z","iopub.execute_input":"2023-04-28T10:07:24.731551Z","iopub.status.idle":"2023-04-28T10:07:35.053704Z","shell.execute_reply.started":"2023-04-28T10:07:24.731514Z","shell.execute_reply":"2023-04-28T10:07:35.052664Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"evaluate_cycle(Night_eval.take(2),\n night2day_gen, \n day2night_gen, \n n_samples=2)","metadata":{"execution":{"iopub.status.busy":"2023-04-28T10:07:35.055816Z","iopub.execute_input":"2023-04-28T10:07:35.056550Z","iopub.status.idle":"2023-04-28T10:07:41.536506Z","shell.execute_reply.started":"2023-04-28T10:07:35.056510Z","shell.execute_reply":"2023-04-28T10:07:41.535415Z"},"trusted":true},"execution_count":null,"outputs":[]}]}