{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.14","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":3362,"databundleVersionId":31148,"sourceType":"competition"}],"dockerImageVersionId":30761,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# 1- Import Libraries","metadata":{}},{"cell_type":"code","source":"import os\nimport numpy as np\nimport pandas as pd\nimport random as rnd\nimport matplotlib.pyplot as plt\n%matplotlib inline\n\nfrom sklearn.model_selection import train_test_split\n\nimport keras\nfrom keras.models import Sequential\nfrom keras.utils import to_categorical\nfrom keras.preprocessing.image import load_img\nfrom keras.layers import Flatten, Dense, Dropout\nfrom keras.layers import Conv2D, MaxPool2D, BatchNormalization, Activation\n\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\n\nprint(os.listdir(\"/kaggle/input/dogs-vs-cats\"))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:26:31.476869Z","iopub.execute_input":"2025-07-08T18:26:31.477146Z","iopub.status.idle":"2025-07-08T18:26:44.272863Z","shell.execute_reply.started":"2025-07-08T18:26:31.477108Z","shell.execute_reply":"2025-07-08T18:26:44.271924Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# 2- Data-Constants","metadata":{}},{"cell_type":"code","source":"FAST_RUN = False\nIMAGE_WIDTH=128\nIMAGE_HEIGHT=128\nIMAGE_CHANNELS=3\nIMAGE_SIZE=(IMAGE_WIDTH, IMAGE_HEIGHT)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:26:56.155309Z","iopub.execute_input":"2025-07-08T18:26:56.155977Z","iopub.status.idle":"2025-07-08T18:26:56.160126Z","shell.execute_reply.started":"2025-07-08T18:26:56.155943Z","shell.execute_reply":"2025-07-08T18:26:56.159243Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# 3- Load DataSet","metadata":{}},{"cell_type":"code","source":"import zipfile\n\nzip_files = ['test1', 'train']\n\nfor zip_file in zip_files:\n     with zipfile.ZipFile(f\"../input/dogs-vs-cats/{zip_file}.zip\", \"r\") as z:\n         z.extractall(\".\")\n         print(f\"{zip_file} unzipped\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:27:31.78553Z","iopub.execute_input":"2025-07-08T18:27:31.785861Z","iopub.status.idle":"2025-07-08T18:27:44.414201Z","shell.execute_reply.started":"2025-07-08T18:27:31.785834Z","shell.execute_reply":"2025-07-08T18:27:44.413249Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> ## Extract Compressed Files","metadata":{}},{"cell_type":"code","source":"import zipfile\n\npath = \"/kaggle/input/dogs-vs-cats\"\nfor zip_file in os.listdir(path)[:2]:\n    zipfile.ZipFile(f\"{path}/{zip_file}\", 'r').extractall(\".\")\n    print(f\"{path}/{zip_file}\")\n    print(f\"{zip_file} unzipped\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:28:12.479924Z","iopub.execute_input":"2025-07-08T18:28:12.480664Z","iopub.status.idle":"2025-07-08T18:28:21.726701Z","shell.execute_reply.started":"2025-07-08T18:28:12.480622Z","shell.execute_reply":"2025-07-08T18:28:21.725844Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# 4- Data Preprocessing","metadata":{}},{"cell_type":"markdown","source":"> ## Label Encoding","metadata":{}},{"cell_type":"code","source":"train_images = os.listdir(\"/kaggle/working/train\")\nCATEGORIES = []\n\nfor image_name in train_images:\n    class_name = image_name.split('.')[0]  # cat.588.jpg\n    CATEGORIES.append(0 if class_name=='cat' else 1)\n\ndf = pd.DataFrame({\"train_images\": train_images, \"CATEGORIES\": CATEGORIES})","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:33:10.926776Z","iopub.execute_input":"2025-07-08T18:33:10.927412Z","iopub.status.idle":"2025-07-08T18:33:10.959676Z","shell.execute_reply.started":"2025-07-08T18:33:10.927375Z","shell.execute_reply":"2025-07-08T18:33:10.958718Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> ## Show DataFrame","metadata":{}},{"cell_type":"code","source":"df.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:30:42.599895Z","iopub.execute_input":"2025-07-08T18:30:42.60068Z","iopub.status.idle":"2025-07-08T18:30:42.608255Z","shell.execute_reply.started":"2025-07-08T18:30:42.600638Z","shell.execute_reply":"2025-07-08T18:30:42.607428Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.tail()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:30:48.409255Z","iopub.execute_input":"2025-07-08T18:30:48.409603Z","iopub.status.idle":"2025-07-08T18:30:48.418505Z","shell.execute_reply.started":"2025-07-08T18:30:48.409573Z","shell.execute_reply":"2025-07-08T18:30:48.417527Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.describe()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:30:51.549907Z","iopub.execute_input":"2025-07-08T18:30:51.550569Z","iopub.status.idle":"2025-07-08T18:30:51.566949Z","shell.execute_reply.started":"2025-07-08T18:30:51.550537Z","shell.execute_reply":"2025-07-08T18:30:51.566153Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df[\"CATEGORIES\"].value_counts()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:32:29.331002Z","iopub.execute_input":"2025-07-08T18:32:29.331387Z","iopub.status.idle":"2025-07-08T18:32:29.339253Z","shell.execute_reply.started":"2025-07-08T18:32:29.331354Z","shell.execute_reply":"2025-07-08T18:32:29.338227Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> ## Visualize The Data","metadata":{}},{"cell_type":"code","source":"df[\"CATEGORIES\"].value_counts().plot.bar()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:32:34.273973Z","iopub.execute_input":"2025-07-08T18:32:34.274307Z","iopub.status.idle":"2025-07-08T18:32:34.471964Z","shell.execute_reply.started":"2025-07-08T18:32:34.274279Z","shell.execute_reply":"2025-07-08T18:32:34.471159Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> ## *From our data we have 12500 cats and 12500 dogs*","metadata":{}},{"cell_type":"markdown","source":"> ## Show Dimensions Of Images","metadata":{}},{"cell_type":"code","source":"shapes = []\n\nfor image in df[\"train_images\"]:\n    path = os.path.join(\"/kaggle/working/train\",image)\n    image_array = plt.imread(path)\n    shapes.append(image_array.shape)\n    \nprint(pd.Series(shapes).value_counts())\n\nindex = np.argmin(shapes)\nprint(f\"\\nThe Minimum Dimension is ==> {shapes[index]}\\n\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:33:15.5213Z","iopub.execute_input":"2025-07-08T18:33:15.522121Z","iopub.status.idle":"2025-07-08T18:33:44.5201Z","shell.execute_reply.started":"2025-07-08T18:33:15.522059Z","shell.execute_reply":"2025-07-08T18:33:44.519247Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> ## **See sample image**\n","metadata":{}},{"cell_type":"code","source":"sample = rnd.choice(train_images)\nimage = load_img(os.path.join(\"/kaggle/working/train\", sample))\nprint(type(image))\nplt.imshow(image)\nplt.axis(\"off\")\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:34:06.762293Z","iopub.execute_input":"2025-07-08T18:34:06.762616Z","iopub.status.idle":"2025-07-08T18:34:06.958661Z","shell.execute_reply.started":"2025-07-08T18:34:06.762588Z","shell.execute_reply":"2025-07-08T18:34:06.957792Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> # Prepare data\n> 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> So we will convert 1 to dog and 0 to cat","metadata":{}},{"cell_type":"code","source":"df[\"CATEGORIES\"] = df[\"CATEGORIES\"].replace({0: 'cat', 1: 'dog'})","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:34:39.921867Z","iopub.execute_input":"2025-07-08T18:34:39.922223Z","iopub.status.idle":"2025-07-08T18:34:39.930337Z","shell.execute_reply.started":"2025-07-08T18:34:39.922192Z","shell.execute_reply":"2025-07-08T18:34:39.929617Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> # Split Data","metadata":{}},{"cell_type":"code","source":"train_df, valid_df = train_test_split(df, test_size=0.30, random_state=45)\n\ntrain_df = train_df.reset_index(drop=True)\nvalid_df = valid_df.reset_index(drop=True)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:35:42.462216Z","iopub.execute_input":"2025-07-08T18:35:42.46257Z","iopub.status.idle":"2025-07-08T18:35:42.473674Z","shell.execute_reply.started":"2025-07-08T18:35:42.46254Z","shell.execute_reply":"2025-07-08T18:35:42.472603Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> # Show tarin DataFrame","metadata":{}},{"cell_type":"code","source":"train_df['CATEGORIES'].value_counts()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:35:45.030023Z","iopub.execute_input":"2025-07-08T18:35:45.030699Z","iopub.status.idle":"2025-07-08T18:35:45.038343Z","shell.execute_reply.started":"2025-07-08T18:35:45.030665Z","shell.execute_reply":"2025-07-08T18:35:45.037409Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_df['CATEGORIES'].value_counts().plot.bar()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:35:48.512162Z","iopub.execute_input":"2025-07-08T18:35:48.512506Z","iopub.status.idle":"2025-07-08T18:35:48.949509Z","shell.execute_reply.started":"2025-07-08T18:35:48.512476Z","shell.execute_reply":"2025-07-08T18:35:48.948567Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> # Show valid DataFrame","metadata":{}},{"cell_type":"code","source":"valid_df['CATEGORIES'].value_counts()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:35:56.621114Z","iopub.execute_input":"2025-07-08T18:35:56.621954Z","iopub.status.idle":"2025-07-08T18:35:56.629195Z","shell.execute_reply.started":"2025-07-08T18:35:56.621923Z","shell.execute_reply":"2025-07-08T18:35:56.628293Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"valid_df['CATEGORIES'].value_counts().plot.bar()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:35:59.742032Z","iopub.execute_input":"2025-07-08T18:35:59.742384Z","iopub.status.idle":"2025-07-08T18:35:59.951571Z","shell.execute_reply.started":"2025-07-08T18:35:59.742358Z","shell.execute_reply":"2025-07-08T18:35:59.95063Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> # Data Augmentation","metadata":{}},{"cell_type":"code","source":"total_train = train_df.shape[0]\ntotal_validate = valid_df.shape[0]\nbatch_size=15","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:36:05.289953Z","iopub.execute_input":"2025-07-08T18:36:05.290307Z","iopub.status.idle":"2025-07-08T18:36:05.294439Z","shell.execute_reply.started":"2025-07-08T18:36:05.290277Z","shell.execute_reply":"2025-07-08T18:36:05.293556Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> ## Train Generator","metadata":{}},{"cell_type":"code","source":"df.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:36:07.319861Z","iopub.execute_input":"2025-07-08T18:36:07.320669Z","iopub.status.idle":"2025-07-08T18:36:07.328585Z","shell.execute_reply.started":"2025-07-08T18:36:07.320633Z","shell.execute_reply":"2025-07-08T18:36:07.327701Z"}},"outputs":[],"execution_count":null},{"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    \"/kaggle/working/train\", \n    x_col='train_images',\n    y_col='CATEGORIES',\n    target_size=IMAGE_SIZE,\n    class_mode='categorical',\n    batch_size=batch_size\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:36:15.649166Z","iopub.execute_input":"2025-07-08T18:36:15.649842Z","iopub.status.idle":"2025-07-08T18:36:15.802724Z","shell.execute_reply.started":"2025-07-08T18:36:15.649811Z","shell.execute_reply":"2025-07-08T18:36:15.801786Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> # Valid Generator","metadata":{}},{"cell_type":"code","source":"valid_datagen = ImageDataGenerator(rescale=1./255)\n\nvalid_generator = valid_datagen.flow_from_dataframe(\n    valid_df, \n    \"/kaggle/working/train\", \n    x_col='train_images',\n    y_col='CATEGORIES',\n    target_size=IMAGE_SIZE,\n    class_mode='categorical',\n    batch_size=batch_size\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:45:14.445872Z","iopub.execute_input":"2025-07-08T18:45:14.446283Z","iopub.status.idle":"2025-07-08T18:45:14.516924Z","shell.execute_reply.started":"2025-07-08T18:45:14.446252Z","shell.execute_reply":"2025-07-08T18:45:14.516306Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> # See how our generator work","metadata":{}},{"cell_type":"code","source":"example_df = train_df.sample(n=1) # take 1 image-sample\nprint(example_df, \"\\n\")\n\nexample_df= example_df.reset_index(drop=True)\nprint(example_df, \"\\n\")\n\nexample_generator = train_datagen.flow_from_dataframe(\n    example_df, \n    \"/kaggle/working/train\", \n    x_col='train_images',\n    y_col='CATEGORIES',\n    target_size=IMAGE_SIZE,\n    class_mode='categorical'\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:45:19.656774Z","iopub.execute_input":"2025-07-08T18:45:19.657143Z","iopub.status.idle":"2025-07-08T18:45:19.668746Z","shell.execute_reply.started":"2025-07-08T18:45:19.657104Z","shell.execute_reply":"2025-07-08T18:45:19.667808Z"}},"outputs":[],"execution_count":null},{"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        plt.axis('off')\n        break\nplt.tight_layout()\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:45:21.976809Z","iopub.execute_input":"2025-07-08T18:45:21.97757Z","iopub.status.idle":"2025-07-08T18:45:23.084056Z","shell.execute_reply.started":"2025-07-08T18:45:21.977534Z","shell.execute_reply":"2025-07-08T18:45:23.083146Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> # Show Generated Images from One-Image","metadata":{}},{"cell_type":"markdown","source":"# 5- Build The Model","metadata":{}},{"cell_type":"markdown","source":"![image](https://i.imgur.com/ebkMGGu.jpg)","metadata":{}},{"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":"markdown","source":"> # Fit Model","metadata":{}},{"cell_type":"code","source":"model = Sequential([\n    Conv2D(32, (3, 3), activation='relu', input_shape=(IMAGE_WIDTH, IMAGE_HEIGHT, IMAGE_CHANNELS)),\n#     BatchNormalization(),\n    MaxPool2D(pool_size=(4,4)),\n    Dropout(rate=0.25),\n    \n    Conv2D(64, (3, 3), activation='relu'),\n    BatchNormalization(),\n    MaxPool2D(pool_size=(4,4)),\n    Dropout(rate=0.25),\n    \n    Conv2D(128, (3, 3), activation='relu'),\n    BatchNormalization(),\n    MaxPool2D(pool_size=(4,4)),\n    Dropout(rate=0.25),\n    \n    Flatten(),\n    \n    Dense(512, activation='relu'),\n    Dropout(rate=0.5),\n\n    Dense(2, activation='softmax') # 2 because we have cat and dog classes\n\n])\n\n# Compile\nmodel.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])\n\n# Summary of Model\nmodel.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:45:40.99654Z","iopub.execute_input":"2025-07-08T18:45:40.997194Z","iopub.status.idle":"2025-07-08T18:45:41.082316Z","shell.execute_reply.started":"2025-07-08T18:45:40.997156Z","shell.execute_reply":"2025-07-08T18:45:41.081497Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> ## Callbacks","metadata":{}},{"cell_type":"code","source":"from keras.callbacks import EarlyStopping, ReduceLROnPlateau","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:45:54.220964Z","iopub.execute_input":"2025-07-08T18:45:54.221794Z","iopub.status.idle":"2025-07-08T18:45:54.225581Z","shell.execute_reply.started":"2025-07-08T18:45:54.221761Z","shell.execute_reply":"2025-07-08T18:45:54.224576Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> ### Early Stop\n> To prevent over fitting we will stop the learning after 10 epochs and val_loss value not decreased","metadata":{}},{"cell_type":"code","source":"earlystop = EarlyStopping(patience=5)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:45:57.904208Z","iopub.execute_input":"2025-07-08T18:45:57.904682Z","iopub.status.idle":"2025-07-08T18:45:57.909373Z","shell.execute_reply.started":"2025-07-08T18:45:57.90465Z","shell.execute_reply":"2025-07-08T18:45:57.908258Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> ### Learning Rate Reduction\n> We will reduce the learning rate when then accuracy not increase for 2 steps","metadata":{}},{"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)\n\ncallbacks = [earlystop, learning_rate_reduction]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:45:59.763188Z","iopub.execute_input":"2025-07-08T18:45:59.76388Z","iopub.status.idle":"2025-07-08T18:45:59.768034Z","shell.execute_reply.started":"2025-07-08T18:45:59.763844Z","shell.execute_reply":"2025-07-08T18:45:59.76711Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"epochs = 3 if FAST_RUN else 10\n\nhistory = model.fit(train_generator,\n                    epochs=epochs,\n                    validation_data=valid_generator,\n#                     validation_steps=total_validate//batch_size, # 5000//15  = 333\n#                     steps_per_epoch=total_train//batch_size,     # 20000//15 = 1333\n                    callbacks=callbacks)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T18:46:02.075168Z","iopub.execute_input":"2025-07-08T18:46:02.075891Z","iopub.status.idle":"2025-07-08T19:00:42.308956Z","shell.execute_reply.started":"2025-07-08T18:46:02.075861Z","shell.execute_reply":"2025-07-08T19:00:42.30823Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> # Visualize The Performance","metadata":{}},{"cell_type":"code","source":"accuracy = history.history[\"accuracy\"]\nval_accuracy = history.history[\"val_accuracy\"]\n\nloss = history.history[\"loss\"]\nval_loss = history.history[\"val_loss\"]\n\nepochs = range(len(accuracy))\n\nplt.figure(figsize=(12,6))\n\nplt.subplot(1,2,1)\nplt.plot(epochs, accuracy, 'bo', label=\"Train_Acc\")\nplt.plot(epochs, val_accuracy, 'r', label=\"val_Acc\")\nplt.legend(loc='best', shadow=True)\n\nplt.subplot(1,2,2)\nplt.plot(epochs, loss, 'bo', label=\"Train_Loss\")\nplt.plot(epochs, val_loss, 'r', label=\"val_Loss\")\nplt.legend(loc='best', shadow=True)\n\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T19:03:03.520155Z","iopub.execute_input":"2025-07-08T19:03:03.521268Z","iopub.status.idle":"2025-07-08T19:03:03.868313Z","shell.execute_reply.started":"2025-07-08T19:03:03.521233Z","shell.execute_reply":"2025-07-08T19:03:03.867544Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> # The Epochs = 10 Only. We Can Increase The number of Epochs to Reach Suitable Accuracy.","metadata":{}},{"cell_type":"markdown","source":"> # Prepare Testing Data","metadata":{}},{"cell_type":"code","source":"test_file_names = os.listdir(\"/kaggle/working/test1\")\ntest_df = pd.DataFrame({'file_name': test_file_names})\n\ntotal_testing = test_df.shape[0]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T19:03:09.468068Z","iopub.execute_input":"2025-07-08T19:03:09.468446Z","iopub.status.idle":"2025-07-08T19:03:09.480817Z","shell.execute_reply.started":"2025-07-08T19:03:09.468416Z","shell.execute_reply":"2025-07-08T19:03:09.480095Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> # Test The Model","metadata":{}},{"cell_type":"markdown","source":"> # Create Testing Generator","metadata":{}},{"cell_type":"code","source":"test_gen = ImageDataGenerator(rescale=1./255)\ntest_generator = test_gen.flow_from_dataframe(\n    test_df, \n    \"/kaggle/working/test1\", \n    x_col='file_name',\n    y_col=None,\n    class_mode=None,\n    target_size=IMAGE_SIZE,\n    batch_size=batch_size,\n    shuffle=False\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T19:03:11.950772Z","iopub.execute_input":"2025-07-08T19:03:11.951495Z","iopub.status.idle":"2025-07-08T19:03:12.044471Z","shell.execute_reply.started":"2025-07-08T19:03:11.951459Z","shell.execute_reply":"2025-07-08T19:03:12.043535Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> # Predict","metadata":{}},{"cell_type":"code","source":"predictions = model.predict(test_generator)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T19:03:14.637154Z","iopub.execute_input":"2025-07-08T19:03:14.637993Z","iopub.status.idle":"2025-07-08T19:03:31.259175Z","shell.execute_reply.started":"2025-07-08T19:03:14.637957Z","shell.execute_reply":"2025-07-08T19:03:31.25821Z"}},"outputs":[],"execution_count":null},{"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[\"CATEGORIES\"] = np.argmax(predictions, axis=1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T19:04:35.006487Z","iopub.execute_input":"2025-07-08T19:04:35.007284Z","iopub.status.idle":"2025-07-08T19:04:35.011979Z","shell.execute_reply.started":"2025-07-08T19:04:35.007249Z","shell.execute_reply":"2025-07-08T19:04:35.011032Z"}},"outputs":[],"execution_count":null},{"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['CATEGORIES'] = test_df['CATEGORIES'].replace(label_map)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T19:04:38.586639Z","iopub.execute_input":"2025-07-08T19:04:38.587133Z","iopub.status.idle":"2025-07-08T19:04:38.596276Z","shell.execute_reply.started":"2025-07-08T19:04:38.587069Z","shell.execute_reply":"2025-07-08T19:04:38.595299Z"}},"outputs":[],"execution_count":null},{"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\n\n","metadata":{}},{"cell_type":"code","source":"import pandas as pd\npd.set_option('future.no_silent_downcasting', True)\n\ntest_df['CATEGORIES'] = test_df['CATEGORIES'].replace({ 'dog': 1, 'cat': 0 })","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T19:07:14.474406Z","iopub.execute_input":"2025-07-08T19:07:14.475015Z","iopub.status.idle":"2025-07-08T19:07:14.479947Z","shell.execute_reply.started":"2025-07-08T19:07:14.47498Z","shell.execute_reply":"2025-07-08T19:07:14.479098Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# 6- Visualize The Result","metadata":{}},{"cell_type":"code","source":"test_df[\"CATEGORIES\"].value_counts().plot.bar()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T19:07:22.087888Z","iopub.execute_input":"2025-07-08T19:07:22.088413Z","iopub.status.idle":"2025-07-08T19:07:22.297143Z","shell.execute_reply.started":"2025-07-08T19:07:22.088376Z","shell.execute_reply":"2025-07-08T19:07:22.296202Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> # Show Predicted Images","metadata":{}},{"cell_type":"code","source":"sample_test = test_df.head(36)\n\nplt.figure(figsize=(15,15))\n\nfor index, row in sample_test.iterrows():\n    file_name = row['file_name']\n    category = row['CATEGORIES']\n    path = os.path.join(\"/kaggle/working/test1\", file_name)\n    img = load_img(path, target_size=IMAGE_SIZE)\n    plt.subplot(6,6,index+1)\n    plt.imshow(img)\n    plt.title(f\"{file_name}\\n is ==> {'cat' if category==0 else 'dog'}\")\n    plt.axis('off')\nplt.tight_layout()\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T19:07:27.933833Z","iopub.execute_input":"2025-07-08T19:07:27.934209Z","iopub.status.idle":"2025-07-08T19:07:30.839449Z","shell.execute_reply.started":"2025-07-08T19:07:27.934175Z","shell.execute_reply":"2025-07-08T19:07:30.838484Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# 7- Save The Model","metadata":{}},{"cell_type":"code","source":"model.save(\"CNN.h5\")\nmodel.save_weights(\"CNN.weights.h5\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T19:07:59.526151Z","iopub.execute_input":"2025-07-08T19:07:59.526508Z","iopub.status.idle":"2025-07-08T19:07:59.607648Z","shell.execute_reply.started":"2025-07-08T19:07:59.526479Z","shell.execute_reply":"2025-07-08T19:07:59.606911Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# 8- Submission","metadata":{}},{"cell_type":"code","source":"submission_df = test_df.copy()\nsubmission_df['id'] = submission_df['file_name'].str.split('.').str[0]\nsubmission_df['label'] = submission_df['CATEGORIES']\nsubmission_df.drop(['file_name', 'CATEGORIES'], axis=1, inplace=True)\nsubmission_df.to_csv(\"submission.csv\", index=False)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T19:08:02.121227Z","iopub.execute_input":"2025-07-08T19:08:02.122054Z","iopub.status.idle":"2025-07-08T19:08:02.546374Z","shell.execute_reply.started":"2025-07-08T19:08:02.122015Z","shell.execute_reply":"2025-07-08T19:08:02.545618Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!wget https://wl-genial.cf.tsp.li/resize/728x/jpg/27e/3ac/d457dd54cdbe4443445792ccb8.jpg\nimagen = load_img('d457dd54cdbe4443445792ccb8.jpg', target_size=IMAGE_SIZE)\nimg = np.expand_dims(imagen, 0) # make 'batch' of 1\npred = model.predict(img)\n#pred = labels[\"label_names\"][np.argmax(pred)]\ncategory = np.argmax(pred)\nplt.imshow(imagen)\nplt.title(f\"esa imagen es \\n ==> {'cat' if category==0 else 'dog'}\")\nplt.axis('off')\nplt.tight_layout()\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-07-08T19:08:04.664358Z","iopub.execute_input":"2025-07-08T19:08:04.66472Z","iopub.status.idle":"2025-07-08T19:08:37.844843Z","shell.execute_reply.started":"2025-07-08T19:08:04.664688Z","shell.execute_reply":"2025-07-08T19:08:37.843525Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!wget https://oglebay.com/wp-content/uploads/2022/06/IMG_5670_M-e1654806092422.jpg\nimagen = load_img('IMG_5670_M-e1654806092422.jpg', target_size=IMAGE_SIZE)\nimg = np.expand_dims(imagen, 0) # make 'batch' of 1\npred = model.predict(img)\n#pred = labels[\"label_names\"][np.argmax(pred)]\ncategory = np.argmax(pred)\nplt.imshow(imagen)\nplt.title(f\"esa imagen es \\n ==> {'cat' if category==0 else 'dog'}\")\nplt.axis('off')\nplt.tight_layout()\nplt.show()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{},"outputs":[],"execution_count":null}]}