{"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":"# Import Library","metadata":{"_uuid":"fe76d1d1ded592430e7548feacfa38dc42f085d9"}},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd \nfrom keras.preprocessing.image import ImageDataGenerator, load_img\nfrom keras.utils import to_categorical\nfrom sklearn.model_selection import train_test_split\nimport matplotlib.pyplot as plt\nimport random\nimport os\nprint(os.listdir(\"../input\"))\n","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2023-02-09T12:43:47.492401Z","iopub.execute_input":"2023-02-09T12:43:47.492678Z","iopub.status.idle":"2023-02-09T12:43:49.120762Z","shell.execute_reply.started":"2023-02-09T12:43:47.492627Z","shell.execute_reply":"2023-02-09T12:43:49.119913Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Define Constants","metadata":{}},{"cell_type":"code","source":"FAST_RUN = False\nIMAGE_WIDTH=128\nIMAGE_HEIGHT=128\nIMAGE_SIZE=(IMAGE_WIDTH, IMAGE_HEIGHT)\nIMAGE_CHANNELS=3","metadata":{"execution":{"iopub.status.busy":"2023-02-09T12:44:20.896368Z","iopub.execute_input":"2023-02-09T12:44:20.896647Z","iopub.status.idle":"2023-02-09T12:44:20.900479Z","shell.execute_reply.started":"2023-02-09T12:44:20.896598Z","shell.execute_reply":"2023-02-09T12:44:20.899655Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Prepare Traning Data","metadata":{"_uuid":"7335a579cc0268fba5d34d6f7558f33c187eedb3"}},{"cell_type":"code","source":"import zipfile\npath_to_zip_file = '../input/test1.zip'\nwith zipfile.ZipFile(path_to_zip_file, 'r') as zip_ref:\n    zip_ref.extractall('.')","metadata":{"execution":{"iopub.status.busy":"2023-02-09T12:44:28.392686Z","iopub.execute_input":"2023-02-09T12:44:28.392972Z","iopub.status.idle":"2023-02-09T12:44:34.157283Z","shell.execute_reply.started":"2023-02-09T12:44:28.392919Z","shell.execute_reply":"2023-02-09T12:44:34.156269Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import zipfile\npath_to_zip_file = '../input/train.zip'\nwith zipfile.ZipFile(path_to_zip_file, 'r') as zip_ref:\n    zip_ref.extractall('.')","metadata":{"execution":{"iopub.status.busy":"2023-02-09T12:44:58.103825Z","iopub.execute_input":"2023-02-09T12:44:58.104106Z","iopub.status.idle":"2023-02-09T12:45:09.596507Z","shell.execute_reply.started":"2023-02-09T12:44:58.104055Z","shell.execute_reply":"2023-02-09T12:45:09.595705Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"filenames = os.listdir(\"train/\")\ncategories = []\nfor filename in filenames:\n    category = filename.split('.')[0]\n    if category == 'dog':\n        categories.append(1)\n    else:\n        categories.append(0)\n\ndf = pd.DataFrame({\n    'filename': filenames,\n    'category': categories\n})","metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","execution":{"iopub.status.busy":"2023-02-09T12:45:36.495543Z","iopub.execute_input":"2023-02-09T12:45:36.495820Z","iopub.status.idle":"2023-02-09T12:45:36.532451Z","shell.execute_reply.started":"2023-02-09T12:45:36.495770Z","shell.execute_reply":"2023-02-09T12:45:36.531679Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df.head()","metadata":{"_uuid":"915bb9ba7063ab4d5c07c542419ae119003a5f98","execution":{"iopub.status.busy":"2023-02-09T12:46:10.782587Z","iopub.execute_input":"2023-02-09T12:46:10.782861Z","iopub.status.idle":"2023-02-09T12:46:10.803911Z","shell.execute_reply.started":"2023-02-09T12:46:10.782813Z","shell.execute_reply":"2023-02-09T12:46:10.802991Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df.tail()","metadata":{"_uuid":"72bf69e817f67f5a2eaff8561217e22077248553","execution":{"iopub.status.busy":"2023-02-09T12:46:18.799728Z","iopub.execute_input":"2023-02-09T12:46:18.800017Z","iopub.status.idle":"2023-02-09T12:46:18.814600Z","shell.execute_reply.started":"2023-02-09T12:46:18.799967Z","shell.execute_reply":"2023-02-09T12:46:18.813736Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### See Total In count","metadata":{"_uuid":"a999484fc35b73373fafe2253ae9db7ff46fdb90"}},{"cell_type":"code","source":"df['category'].value_counts().plot.bar()","metadata":{"_uuid":"fa26f0bc7a6d835a24989790b20f3c6f32946f45","execution":{"iopub.status.busy":"2023-02-09T12:46:33.502456Z","iopub.execute_input":"2023-02-09T12:46:33.502734Z","iopub.status.idle":"2023-02-09T12:46:33.750783Z","shell.execute_reply.started":"2023-02-09T12:46:33.502685Z","shell.execute_reply":"2023-02-09T12:46:33.749708Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"From our data we have 12000 cats and 12000 dogs","metadata":{"_uuid":"3a08da58107777a1dd05c4a4bf5c484484923cac"}},{"cell_type":"markdown","source":"# See sample image","metadata":{"_uuid":"400a293df3c8499059d9175f3915187074efd971"}},{"cell_type":"code","source":"sample = random.choice(filenames)\nimage = load_img(\"train/\"+sample)\nplt.imshow(image)","metadata":{"_uuid":"602b40f7353871cb161c60b5237f0da0096b2f47","execution":{"iopub.status.busy":"2023-02-09T12:46:46.252458Z","iopub.execute_input":"2023-02-09T12:46:46.252745Z","iopub.status.idle":"2023-02-09T12:46:46.605659Z","shell.execute_reply.started":"2023-02-09T12:46:46.252697Z","shell.execute_reply":"2023-02-09T12:46:46.604874Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Build Model\n\n<img src=\"https://i.imgur.com/ebkMGGu.jpg\" width=\"100%\"/>","metadata":{"_uuid":"b244e6b7715a04fc6df92dd6dfa3d35c473ca600"}},{"cell_type":"markdown","source":"* **Input Layer**: It represent input image data. It will reshape image into single diminsion array. Example your image is 64x64 = 4096, it will convert to (4096,1) array.\n* **Conv Layer**: This layer will extract features from image.\n* **Pooling Layer**: This layerreduce the spatial volume of input image after convolution.\n* **Fully Connected Layer**: It connect the network from a layer to another layer\n* **Output Layer**: It is the predicted values layer. ","metadata":{}},{"cell_type":"code","source":"from keras.models import Sequential\nfrom keras.layers import Conv2D, MaxPooling2D, Dropout, Flatten, Dense, Activation, BatchNormalization\n\nmodel = Sequential()\n\nmodel.add(Conv2D(32, (3, 3), activation='relu', input_shape=(IMAGE_WIDTH, IMAGE_HEIGHT, IMAGE_CHANNELS)))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.25))\n\n# model.add(Conv2D(32, (3, 3), activation='relu'))\n# model.add(BatchNormalization())\n# model.add(MaxPooling2D(pool_size=(2, 2)))\n# model.add(Dropout(0.25))\n\nmodel.add(Conv2D(64, (3, 3), activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Conv2D(128, (3, 3), activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Flatten())\nmodel.add(Dense(512, activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.5))\n\n# model.add(Dense(128, activation='relu'))\n# model.add(BatchNormalization())\n# model.add(Dropout(0.5))\n\nmodel.add(Dense(2, activation='softmax')) # 2 because we have cat and dog classes\n\n#model.compile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])\n\nmodel.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])\n\nmodel.summary()","metadata":{"_uuid":"8c9f833c1441b657c779844912d0b8028218d454","execution":{"iopub.status.busy":"2023-02-09T12:46:58.398564Z","iopub.execute_input":"2023-02-09T12:46:58.398846Z","iopub.status.idle":"2023-02-09T12:47:00.943623Z","shell.execute_reply.started":"2023-02-09T12:46:58.398799Z","shell.execute_reply":"2023-02-09T12:47:00.941268Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Callbacks","metadata":{"_uuid":"bd496f6c65888a969be3703135b0b03a8a1190c8"}},{"cell_type":"code","source":"from keras.callbacks import EarlyStopping, ReduceLROnPlateau","metadata":{"_uuid":"9aa032f0f6da539d23918890d2d131cc3aac8c7a","execution":{"iopub.status.busy":"2023-02-09T12:47:21.236550Z","iopub.execute_input":"2023-02-09T12:47:21.237034Z","iopub.status.idle":"2023-02-09T12:47:21.241526Z","shell.execute_reply.started":"2023-02-09T12:47:21.236791Z","shell.execute_reply":"2023-02-09T12:47:21.240466Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Early Stop**\n\nTo prevent over fitting we will stop the learning after 10 epochs and val_loss value not decreased","metadata":{"_uuid":"76c9ba4fb7f930c96b2c3e0d6b68ed9fa6a4227b"}},{"cell_type":"code","source":"earlystop = EarlyStopping(patience=10)","metadata":{"_uuid":"3421c5ec428da6c0d8cc1184179a9caff1e01d1c","execution":{"iopub.status.busy":"2023-02-09T12:47:28.948795Z","iopub.execute_input":"2023-02-09T12:47:28.949081Z","iopub.status.idle":"2023-02-09T12:47:28.953494Z","shell.execute_reply.started":"2023-02-09T12:47:28.949029Z","shell.execute_reply":"2023-02-09T12:47:28.952653Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Learning Rate Reduction**\n\nWe will reduce the learning rate when then accuracy not increase for 2 steps","metadata":{"_uuid":"51d3fe52e911286433cedf6e47332948a253361e"}},{"cell_type":"code","source":"learning_rate_reduction = ReduceLROnPlateau(monitor='val_acc', \n                                            patience=2, \n                                            verbose=1, \n                                            factor=0.5, \n                                            min_lr=0.00001)","metadata":{"_uuid":"8010a5661ad8924d2db24af0f3c00b1593b38901","execution":{"iopub.status.busy":"2023-02-09T12:47:31.628179Z","iopub.execute_input":"2023-02-09T12:47:31.628470Z","iopub.status.idle":"2023-02-09T12:47:31.634475Z","shell.execute_reply.started":"2023-02-09T12:47:31.628421Z","shell.execute_reply":"2023-02-09T12:47:31.633422Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"callbacks = [earlystop, learning_rate_reduction]","metadata":{"_uuid":"a79cc604199469789f183096d863f7248e5f6aab","execution":{"iopub.status.busy":"2023-02-09T12:47:33.420057Z","iopub.execute_input":"2023-02-09T12:47:33.420355Z","iopub.status.idle":"2023-02-09T12:47:33.425516Z","shell.execute_reply.started":"2023-02-09T12:47:33.420302Z","shell.execute_reply":"2023-02-09T12:47:33.424214Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Prepare data","metadata":{}},{"cell_type":"markdown","source":"Because we will use image genaretor `with class_mode=\"categorical\"`. We need to convert column category into string. Then imagenerator will convert it one-hot encoding which is good for our classification. \n\nSo we will convert 1 to dog and 0 to cat","metadata":{}},{"cell_type":"code","source":"df[\"category\"] = df[\"category\"].replace({0: 'cat', 1: 'dog'}) ","metadata":{"execution":{"iopub.status.busy":"2023-02-09T12:47:40.469885Z","iopub.execute_input":"2023-02-09T12:47:40.470197Z","iopub.status.idle":"2023-02-09T12:47:40.478974Z","shell.execute_reply.started":"2023-02-09T12:47:40.470138Z","shell.execute_reply":"2023-02-09T12:47:40.478311Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df, validate_df = train_test_split(df, test_size=0.20, random_state=42)\ntrain_df = train_df.reset_index(drop=True)\nvalidate_df = validate_df.reset_index(drop=True)","metadata":{"_uuid":"4eeb7af8dcf02c4ef5ca744c8305c51a2f5cedef","execution":{"iopub.status.busy":"2023-02-09T12:47:46.949388Z","iopub.execute_input":"2023-02-09T12:47:46.949674Z","iopub.status.idle":"2023-02-09T12:47:46.961309Z","shell.execute_reply.started":"2023-02-09T12:47:46.949623Z","shell.execute_reply":"2023-02-09T12:47:46.960377Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df['category'].value_counts().plot.bar()","metadata":{"_uuid":"b84836337441705eda9d2e655665ffa14d9feead","execution":{"iopub.status.busy":"2023-02-09T12:47:49.291891Z","iopub.execute_input":"2023-02-09T12:47:49.292231Z","iopub.status.idle":"2023-02-09T12:47:49.573023Z","shell.execute_reply.started":"2023-02-09T12:47:49.292169Z","shell.execute_reply":"2023-02-09T12:47:49.571474Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"validate_df['category'].value_counts().plot.bar()","metadata":{"_uuid":"19cf03f9a3c39532d6e2d06bd30be49a5afd9d57","execution":{"iopub.status.busy":"2023-02-09T12:48:26.637713Z","iopub.execute_input":"2023-02-09T12:48:26.638000Z","iopub.status.idle":"2023-02-09T12:48:26.885735Z","shell.execute_reply.started":"2023-02-09T12:48:26.637951Z","shell.execute_reply":"2023-02-09T12:48:26.884613Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"validate_df.sample(10)","metadata":{"execution":{"iopub.status.busy":"2023-02-09T12:48:29.706668Z","iopub.execute_input":"2023-02-09T12:48:29.706950Z","iopub.status.idle":"2023-02-09T12:48:29.721663Z","shell.execute_reply.started":"2023-02-09T12:48:29.706898Z","shell.execute_reply":"2023-02-09T12:48:29.720930Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"total_train = train_df.shape[0]\ntotal_validate = validate_df.shape[0]\nbatch_size=15","metadata":{"_uuid":"ae3dec0361f0443132d0309d3b883ee80070cf9f","execution":{"iopub.status.busy":"2023-02-09T12:48:46.371991Z","iopub.execute_input":"2023-02-09T12:48:46.372299Z","iopub.status.idle":"2023-02-09T12:48:46.376787Z","shell.execute_reply.started":"2023-02-09T12:48:46.372247Z","shell.execute_reply":"2023-02-09T12:48:46.375479Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Traning Generator","metadata":{"_uuid":"ff760be9104f7d9492467b8d9d3405011aa77d11"}},{"cell_type":"code","source":"train_datagen = ImageDataGenerator(\n    rotation_range=15,\n    rescale=1./255,\n    shear_range=0.1,\n    zoom_range=0.2,\n    horizontal_flip=True,\n    width_shift_range=0.1,\n    height_shift_range=0.1\n)\n\ntrain_generator = train_datagen.flow_from_dataframe(\n    train_df, \n    \"train/\", \n    x_col='filename',\n    y_col='category',\n    target_size=IMAGE_SIZE,\n    class_mode='categorical',\n    batch_size=batch_size\n)","metadata":{"_uuid":"4d1c7818703a8a4bac5c036fdea45972aa9e5e9e","execution":{"iopub.status.busy":"2023-02-09T12:48:49.091397Z","iopub.execute_input":"2023-02-09T12:48:49.091682Z","iopub.status.idle":"2023-02-09T12:48:49.276308Z","shell.execute_reply.started":"2023-02-09T12:48:49.091632Z","shell.execute_reply":"2023-02-09T12:48:49.275535Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Validation Generator","metadata":{"_uuid":"859c7b2857939c19fd2e3bb32839c9f7deb5aa3f"}},{"cell_type":"code","source":"validation_datagen = ImageDataGenerator(rescale=1./255)\nvalidation_generator = validation_datagen.flow_from_dataframe(\n    validate_df, \n    \"train/\", \n    x_col='filename',\n    y_col='category',\n    target_size=IMAGE_SIZE,\n    class_mode='categorical',\n    batch_size=batch_size\n)\n","metadata":{"_uuid":"7925e16bcacc89f4484fb6fe47e54d6420af732e","execution":{"iopub.status.busy":"2023-02-09T12:48:52.698469Z","iopub.execute_input":"2023-02-09T12:48:52.698784Z","iopub.status.idle":"2023-02-09T12:48:52.764170Z","shell.execute_reply.started":"2023-02-09T12:48:52.698727Z","shell.execute_reply":"2023-02-09T12:48:52.763275Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(validation_generator.class_indices)\nprint(validation_generator.n)\nprint(len(validation_generator))","metadata":{"execution":{"iopub.status.busy":"2023-02-09T12:48:54.697074Z","iopub.execute_input":"2023-02-09T12:48:54.697409Z","iopub.status.idle":"2023-02-09T12:48:54.703042Z","shell.execute_reply.started":"2023-02-09T12:48:54.697354Z","shell.execute_reply":"2023-02-09T12:48:54.702137Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_val, y_val = validation_generator.__next__()\nprint(X_val.shape, y_val.shape)","metadata":{"execution":{"iopub.status.busy":"2023-02-09T12:48:56.986018Z","iopub.execute_input":"2023-02-09T12:48:56.986323Z","iopub.status.idle":"2023-02-09T12:48:57.041968Z","shell.execute_reply.started":"2023-02-09T12:48:56.986269Z","shell.execute_reply":"2023-02-09T12:48:57.041346Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_list = []\ny_list = []\nfor i in range(validation_generator.__len__()):\n    X, y = validation_generator.__getitem__(i)\n    X_list.append(X)\n    y_list.append(y)\n\nX_val = np.concatenate(X_list, axis=0)\ny_val1 = np.concatenate(y_list, axis=0)\ny_val_argmax = np.argmax(y_val1, axis=1).astype('uint8')","metadata":{"execution":{"iopub.status.busy":"2023-02-09T12:48:58.508354Z","iopub.execute_input":"2023-02-09T12:48:58.508640Z","iopub.status.idle":"2023-02-09T12:49:14.089566Z","shell.execute_reply.started":"2023-02-09T12:48:58.508589Z","shell.execute_reply":"2023-02-09T12:49:14.088627Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_val.shape, y_val1.shape, y_val_argmax.shape, y_val_argmax[:10]","metadata":{"execution":{"iopub.status.busy":"2023-02-09T12:49:25.098886Z","iopub.execute_input":"2023-02-09T12:49:25.099199Z","iopub.status.idle":"2023-02-09T12:49:25.105480Z","shell.execute_reply.started":"2023-02-09T12:49:25.099144Z","shell.execute_reply":"2023-02-09T12:49:25.104534Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_list[0].shape","metadata":{"execution":{"iopub.status.busy":"2023-02-09T12:49:28.954397Z","iopub.execute_input":"2023-02-09T12:49:28.954687Z","iopub.status.idle":"2023-02-09T12:49:28.961605Z","shell.execute_reply.started":"2023-02-09T12:49:28.954635Z","shell.execute_reply":"2023-02-09T12:49:28.960759Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"","metadata":{}},{"cell_type":"markdown","source":"import numpy as np\nimport matplotlib.pyplot as plt\n\nnum_images = 3\n\nrandom_indices = np.random.randint(0, X_val.shape[0], 9)\n\n# Get the images and labels at those indices\nimages = X_val[random_indices]\nlabels = y_val[random_indices]\n\n# Set up the plot with 3 rows and 3 columns\nfig, axs = plt.subplots(3, 3, \n                        figsize=(10,10), \n                        dpi=300)\n\n# Display the images and labels\nfor i in range(3):\n  for j in range(3):\n    axs[i, j].imshow(images[i * 3 + j], cmap='gray')\n    axs[i, j].set_title(f\"Label: {labels[i * 3 + j]}\")\n\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-02-04T04:45:06.726748Z","iopub.execute_input":"2023-02-04T04:45:06.727177Z","iopub.status.idle":"2023-02-04T04:45:06.803696Z","shell.execute_reply.started":"2023-02-04T04:45:06.726973Z","shell.execute_reply":"2023-02-04T04:45:06.749148Z"}}},{"cell_type":"markdown","source":"# See how our generator work","metadata":{"_uuid":"6e17fc1f002fedd60febb78fee5e81770640b909"}},{"cell_type":"code","source":"example_df = train_df.sample(n=1).reset_index(drop=True)\nexample_generator = train_datagen.flow_from_dataframe(\n    example_df, \n    \"train/\", \n    x_col='filename',\n    y_col='category',\n    target_size=IMAGE_SIZE,\n    class_mode='categorical'\n)","metadata":{"_uuid":"4252cce168ab65f88e44a8ebc2672607bc852af4","execution":{"iopub.status.busy":"2023-02-09T12:49:42.843167Z","iopub.execute_input":"2023-02-09T12:49:42.843462Z","iopub.status.idle":"2023-02-09T12:49:42.857907Z","shell.execute_reply.started":"2023-02-09T12:49:42.843411Z","shell.execute_reply":"2023-02-09T12:49:42.857139Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.figure(figsize=(12, 12))\nfor i in range(0, 15):\n    plt.subplot(5, 3, i+1)\n    for X_batch, Y_batch in example_generator:\n        image = X_batch[0]\n        plt.imshow(image)\n        break\nplt.tight_layout()\nplt.show()","metadata":{"_uuid":"23d923dba747f8b47dc75569244cecc6f70df321","execution":{"iopub.status.busy":"2023-02-09T12:50:10.916337Z","iopub.execute_input":"2023-02-09T12:50:10.916619Z","iopub.status.idle":"2023-02-09T12:50:13.639650Z","shell.execute_reply.started":"2023-02-09T12:50:10.916570Z","shell.execute_reply":"2023-02-09T12:50:13.636618Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Seem to be nice ","metadata":{"_uuid":"810ddf1373d9db470ed48da4f30ca5a6c1274435"}},{"cell_type":"markdown","source":"# Fit Model","metadata":{"_uuid":"5cd8df64e794ed17de326b613a9819e7da977a0e"}},{"cell_type":"code","source":"batch_size","metadata":{"execution":{"iopub.status.busy":"2023-02-09T12:50:34.866661Z","iopub.execute_input":"2023-02-09T12:50:34.866948Z","iopub.status.idle":"2023-02-09T12:50:34.872342Z","shell.execute_reply.started":"2023-02-09T12:50:34.866898Z","shell.execute_reply":"2023-02-09T12:50:34.871401Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import tensorflow as tf\nprint(tf.test.gpu_device_name())","metadata":{"execution":{"iopub.status.busy":"2023-02-09T12:50:36.680774Z","iopub.execute_input":"2023-02-09T12:50:36.681063Z","iopub.status.idle":"2023-02-09T12:50:36.688225Z","shell.execute_reply.started":"2023-02-09T12:50:36.681010Z","shell.execute_reply":"2023-02-09T12:50:36.687321Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.reset_states()","metadata":{"execution":{"iopub.status.busy":"2023-02-09T12:50:50.937572Z","iopub.execute_input":"2023-02-09T12:50:50.937899Z","iopub.status.idle":"2023-02-09T12:50:50.942340Z","shell.execute_reply.started":"2023-02-09T12:50:50.937839Z","shell.execute_reply":"2023-02-09T12:50:50.941383Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\nepochs=3 if FAST_RUN else 10\nwith tf.device('/device:GPU:0'):\n    history = model.fit_generator(\n        train_generator, \n        epochs=epochs,\n        validation_data=validation_generator,\n        validation_steps=total_validate//batch_size,\n        steps_per_epoch=total_train//batch_size,\n        callbacks=callbacks\n    )","metadata":{"_uuid":"0836a4cc8aa0abf603e0f96573c0c4ff383ad56b","execution":{"iopub.status.busy":"2023-02-09T12:51:09.440003Z","iopub.execute_input":"2023-02-09T12:51:09.440328Z","iopub.status.idle":"2023-02-09T13:20:27.784051Z","shell.execute_reply.started":"2023-02-09T12:51:09.440275Z","shell.execute_reply":"2023-02-09T13:20:27.783347Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Save Model","metadata":{"_uuid":"aa1fbc4081ae0de2993188b2bf658a0be5bc0687"}},{"cell_type":"code","source":"model.save_weights(\"model.h5\")","metadata":{"_uuid":"67575a4decdaf79a915d23151626b784ffa82642","execution":{"iopub.status.busy":"2023-02-09T13:21:32.059266Z","iopub.execute_input":"2023-02-09T13:21:32.059571Z","iopub.status.idle":"2023-02-09T13:21:32.298271Z","shell.execute_reply.started":"2023-02-09T13:21:32.059518Z","shell.execute_reply":"2023-02-09T13:21:32.297454Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Virtualize Training","metadata":{"_uuid":"1b76c0a9040bc0babf0a453e567e41e22f8a1e0e"}},{"cell_type":"code","source":"fig, (ax1, ax2) = plt.subplots(2, 1, figsize=(12, 12), dpi=300)\nax1.plot(history.history['loss'], color='b', label=\"Training loss\")\nax1.plot(history.history['val_loss'], color='r', label=\"validation loss\")\nax1.set_xticks(np.arange(1, epochs, 1))\nax1.set_yticks(np.arange(0, 1, 0.1))\n\nax2.plot(history.history['acc'], color='b', label=\"Training accuracy\")\nax2.plot(history.history['val_acc'], color='r',label=\"Validation accuracy\")\nax2.set_xticks(np.arange(1, epochs, 1))\n\nlegend = plt.legend(loc='best', shadow=True)\nplt.tight_layout()\nplt.show()","metadata":{"_uuid":"79055f2dc3e2abb47bea758e0464c86ca42ab431","execution":{"iopub.status.busy":"2023-02-09T13:21:36.156237Z","iopub.execute_input":"2023-02-09T13:21:36.156541Z","iopub.status.idle":"2023-02-09T13:21:40.072770Z","shell.execute_reply.started":"2023-02-09T13:21:36.156488Z","shell.execute_reply":"2023-02-09T13:21:40.068280Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Prepare Testing Data","metadata":{"_uuid":"764dc66e4b2bc558f3a0f90b80bb802f5b3d45a8"}},{"cell_type":"code","source":"test_filenames = os.listdir(\"test1/\")\ntest_df = pd.DataFrame({\n    'filename': test_filenames\n})\nnb_samples = test_df.shape[0]","metadata":{"_uuid":"c35e70d3e1e4834dbbf840fa0ea08c049bfcd915","execution":{"iopub.status.busy":"2023-02-09T13:21:51.740374Z","iopub.execute_input":"2023-02-09T13:21:51.740661Z","iopub.status.idle":"2023-02-09T13:21:51.754516Z","shell.execute_reply.started":"2023-02-09T13:21:51.740609Z","shell.execute_reply":"2023-02-09T13:21:51.753531Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Create Testing Generator","metadata":{"_uuid":"291bc3996dce8d05e174b27d64f03996d3e8038e"}},{"cell_type":"code","source":"test_gen = ImageDataGenerator(rescale=1./255)\ntest_generator = test_gen.flow_from_dataframe(\n    test_df, \n    \"test1/\", \n    x_col='filename',\n    y_col=None,\n    class_mode=None,\n    target_size=IMAGE_SIZE,\n    batch_size=batch_size,\n    shuffle=False\n)","metadata":{"_uuid":"52249ec1c35fb1be3adef386be245de3794e55aa","execution":{"iopub.status.busy":"2023-02-09T13:22:17.972289Z","iopub.execute_input":"2023-02-09T13:22:17.972595Z","iopub.status.idle":"2023-02-09T13:22:18.074025Z","shell.execute_reply.started":"2023-02-09T13:22:17.972541Z","shell.execute_reply":"2023-02-09T13:22:18.073251Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Performance model evaluation","metadata":{}},{"cell_type":"code","source":"preds = model.predict_generator(validation_generator, \n                                  steps=total_validate//batch_size + 1,\n                                  verbose=1)","metadata":{"execution":{"iopub.status.busy":"2023-02-09T13:22:23.827456Z","iopub.execute_input":"2023-02-09T13:22:23.827737Z","iopub.status.idle":"2023-02-09T13:22:39.762749Z","shell.execute_reply.started":"2023-02-09T13:22:23.827690Z","shell.execute_reply":"2023-02-09T13:22:39.761947Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"preds.shape","metadata":{"execution":{"iopub.status.busy":"2023-02-09T13:23:22.714173Z","iopub.execute_input":"2023-02-09T13:23:22.714467Z","iopub.status.idle":"2023-02-09T13:23:22.719591Z","shell.execute_reply.started":"2023-02-09T13:23:22.714417Z","shell.execute_reply":"2023-02-09T13:23:22.718766Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_val_pred = np.argmax(preds, axis=1)\nprint(y_val_pred.shape)","metadata":{"execution":{"iopub.status.busy":"2023-02-09T13:23:24.273980Z","iopub.execute_input":"2023-02-09T13:23:24.274307Z","iopub.status.idle":"2023-02-09T13:23:24.279457Z","shell.execute_reply.started":"2023-02-09T13:23:24.274251Z","shell.execute_reply":"2023-02-09T13:23:24.278485Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"len(y_val_pred), len(y_val_argmax)","metadata":{"execution":{"iopub.status.busy":"2023-02-09T13:23:26.969680Z","iopub.execute_input":"2023-02-09T13:23:26.969973Z","iopub.status.idle":"2023-02-09T13:23:26.976366Z","shell.execute_reply.started":"2023-02-09T13:23:26.969920Z","shell.execute_reply":"2023-02-09T13:23:26.975439Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_val_pred[:10], y_val_argmax[:10]","metadata":{"execution":{"iopub.status.busy":"2023-02-09T13:23:28.784983Z","iopub.execute_input":"2023-02-09T13:23:28.785349Z","iopub.status.idle":"2023-02-09T13:23:28.791817Z","shell.execute_reply.started":"2023-02-09T13:23:28.785272Z","shell.execute_reply":"2023-02-09T13:23:28.790857Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Performance Evaluation","metadata":{}},{"cell_type":"code","source":"from sklearn.metrics import classification_report\n#(y_true, y_pred, *, labels=None, target_names=None, sample_weight=None, digits=2, output_dict=False, zero_division='warn')[source]¶\ntarget_names = ['cat', 'dog']\ny_true = y_val_argmax\ny_pred = y_val_pred\n\nprint(classification_report(y_true, y_pred, target_names=target_names))","metadata":{"execution":{"iopub.status.busy":"2023-02-09T13:23:30.977929Z","iopub.execute_input":"2023-02-09T13:23:30.978236Z","iopub.status.idle":"2023-02-09T13:23:30.992412Z","shell.execute_reply.started":"2023-02-09T13:23:30.978181Z","shell.execute_reply":"2023-02-09T13:23:30.991120Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Predict","metadata":{"_uuid":"2fa580afca2931ec5ce374e732d8c1789d03f2ed"}},{"cell_type":"code","source":"predict = model.predict_generator(test_generator, steps=np.ceil(nb_samples/batch_size),\n                                 verbose=1)","metadata":{"_uuid":"4782eb23fa7d003f0e2415d995894017edb2d896","execution":{"iopub.status.busy":"2023-02-09T13:23:32.803887Z","iopub.execute_input":"2023-02-09T13:23:32.804311Z","iopub.status.idle":"2023-02-09T13:24:21.713462Z","shell.execute_reply.started":"2023-02-09T13:23:32.804239Z","shell.execute_reply":"2023-02-09T13:24:21.712696Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"For categoral classication the prediction will come with probability of each category. So we will pick the category that have the highest probability with numpy average max","metadata":{}},{"cell_type":"code","source":"test_df['category'] = np.argmax(predict, axis=-1)","metadata":{"execution":{"iopub.status.busy":"2023-02-09T13:24:32.554409Z","iopub.execute_input":"2023-02-09T13:24:32.554693Z","iopub.status.idle":"2023-02-09T13:24:32.559668Z","shell.execute_reply.started":"2023-02-09T13:24:32.554645Z","shell.execute_reply":"2023-02-09T13:24:32.558895Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"We will convert the predict category back into our generator classes by using `train_generator.class_indices`. It is the classes that image generator map while converting data into computer vision","metadata":{}},{"cell_type":"code","source":"label_map = dict((v,k) for k,v in train_generator.class_indices.items())\ntest_df['category'] = test_df['category'].replace(label_map)","metadata":{"execution":{"iopub.status.busy":"2023-02-09T13:24:35.705700Z","iopub.execute_input":"2023-02-09T13:24:35.706384Z","iopub.status.idle":"2023-02-09T13:24:35.721641Z","shell.execute_reply.started":"2023-02-09T13:24:35.706324Z","shell.execute_reply":"2023-02-09T13:24:35.720891Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"From our prepare data part. We map data with `{1: 'dog', 0: 'cat'}`. Now we will map the result back to dog is 1 and cat is 0","metadata":{}},{"cell_type":"code","source":"test_df['category'] = test_df['category'].replace({ 'dog': 1, 'cat': 0 })","metadata":{"execution":{"iopub.status.busy":"2023-02-09T13:24:37.985193Z","iopub.execute_input":"2023-02-09T13:24:37.985492Z","iopub.status.idle":"2023-02-09T13:24:37.995671Z","shell.execute_reply.started":"2023-02-09T13:24:37.985442Z","shell.execute_reply":"2023-02-09T13:24:37.994661Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Virtaulize Result","metadata":{"_uuid":"b00add65fe765529e637c3a9904d710bb7eff1d8"}},{"cell_type":"code","source":"test_df['category'].value_counts().plot.bar()","metadata":{"_uuid":"d0bf6dd5ff344092fa0121f70bdd60fa5a40e29c","execution":{"iopub.status.busy":"2023-02-09T13:24:40.482227Z","iopub.execute_input":"2023-02-09T13:24:40.482511Z","iopub.status.idle":"2023-02-09T13:24:40.725284Z","shell.execute_reply.started":"2023-02-09T13:24:40.482463Z","shell.execute_reply":"2023-02-09T13:24:40.724194Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### See predicted result with images","metadata":{"_uuid":"ce72a83f80d6e012b12b82c8ee3365d671a3b307"}},{"cell_type":"code","source":"sample_test = test_df.head(18)\nsample_test.head()\nplt.figure(figsize=(12, 24))\nfor index, row in sample_test.iterrows():\n    filename = row['filename']\n    category = row['category']\n    img = load_img(\"test1/\"+filename, target_size=IMAGE_SIZE)\n    plt.subplot(6, 3, index+1)\n    plt.imshow(img)\n    plt.xlabel(filename + '(' + \"{}\".format(category) + ')' )\nplt.tight_layout()\nplt.show()","metadata":{"_uuid":"98b41dc83075e6297137fb45bf703c313dd4ae28","execution":{"iopub.status.busy":"2023-02-09T13:24:43.099268Z","iopub.execute_input":"2023-02-09T13:24:43.099555Z","iopub.status.idle":"2023-02-09T13:24:47.122433Z","shell.execute_reply.started":"2023-02-09T13:24:43.099507Z","shell.execute_reply":"2023-02-09T13:24:47.121772Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Submission","metadata":{"_uuid":"d1ca25943e73aa20a37f9fb8670ee430caeaaf1f"}},{"cell_type":"code","source":"submission_df = test_df.copy()\nsubmission_df['id'] = submission_df['filename'].str.split('.').str[0]\nsubmission_df['label'] = submission_df['category']\nsubmission_df.drop(['filename', 'category'], axis=1, inplace=True)\nsubmission_df.to_csv('submission.csv', index=False)","metadata":{"_uuid":"cce9f3e2ffff0693d79d84590ed71fbbca7c3c7c","execution":{"iopub.status.busy":"2023-02-09T13:24:57.234639Z","iopub.execute_input":"2023-02-09T13:24:57.234924Z","iopub.status.idle":"2023-02-09T13:24:57.595362Z","shell.execute_reply.started":"2023-02-09T13:24:57.234873Z","shell.execute_reply":"2023-02-09T13:24:57.594538Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}