{"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":30762,"isInternetEnabled":true,"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":{"execution":{"iopub.status.busy":"2024-12-19T16:19:42.130026Z","iopub.execute_input":"2024-12-19T16:19:42.130345Z","iopub.status.idle":"2024-12-19T16:19:54.798221Z","shell.execute_reply.started":"2024-12-19T16:19:42.130306Z","shell.execute_reply":"2024-12-19T16:19:54.797303Z"},"trusted":true},"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":{"execution":{"iopub.status.busy":"2024-12-19T16:20:13.830589Z","iopub.execute_input":"2024-12-19T16:20:13.830926Z","iopub.status.idle":"2024-12-19T16:20:13.835297Z","shell.execute_reply.started":"2024-12-19T16:20:13.830895Z","shell.execute_reply":"2024-12-19T16:20:13.834399Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# 3- Load DataSet","metadata":{}},{"cell_type":"code","source":"# import zipfile\n\n# zip_files = ['test1', 'train']\n\n# for 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":{"execution":{"iopub.status.busy":"2024-12-19T16:20:16.677041Z","iopub.execute_input":"2024-12-19T16:20:16.677706Z","iopub.status.idle":"2024-12-19T16:20:16.681259Z","shell.execute_reply.started":"2024-12-19T16:20:16.677677Z","shell.execute_reply":"2024-12-19T16:20:16.680365Z"},"trusted":true},"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":{"execution":{"iopub.status.busy":"2024-12-19T16:20:18.997277Z","iopub.execute_input":"2024-12-19T16:20:18.997605Z","iopub.status.idle":"2024-12-19T16:20:31.887713Z","shell.execute_reply.started":"2024-12-19T16:20:18.997577Z","shell.execute_reply":"2024-12-19T16:20:31.886817Z"},"trusted":true},"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":{"execution":{"iopub.status.busy":"2024-12-19T16:20:36.653800Z","iopub.execute_input":"2024-12-19T16:20:36.654144Z","iopub.status.idle":"2024-12-19T16:20:36.687711Z","shell.execute_reply.started":"2024-12-19T16:20:36.654114Z","shell.execute_reply":"2024-12-19T16:20:36.686982Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> ## Show DataFrame","metadata":{}},{"cell_type":"code","source":"df.head()","metadata":{"execution":{"iopub.status.busy":"2024-12-19T16:20:40.040080Z","iopub.execute_input":"2024-12-19T16:20:40.040901Z","iopub.status.idle":"2024-12-19T16:20:40.059188Z","shell.execute_reply.started":"2024-12-19T16:20:40.040852Z","shell.execute_reply":"2024-12-19T16:20:40.058229Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.tail()","metadata":{"execution":{"iopub.status.busy":"2024-12-19T16:20:43.080052Z","iopub.execute_input":"2024-12-19T16:20:43.080392Z","iopub.status.idle":"2024-12-19T16:20:43.088798Z","shell.execute_reply.started":"2024-12-19T16:20:43.080364Z","shell.execute_reply":"2024-12-19T16:20:43.087981Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.describe()","metadata":{"execution":{"iopub.status.busy":"2024-12-19T16:20:46.920822Z","iopub.execute_input":"2024-12-19T16:20:46.921632Z","iopub.status.idle":"2024-12-19T16:20:46.938879Z","shell.execute_reply.started":"2024-12-19T16:20:46.921597Z","shell.execute_reply":"2024-12-19T16:20:46.938010Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df[\"CATEGORIES\"].value_counts()","metadata":{"execution":{"iopub.status.busy":"2024-12-19T16:20:56.188066Z","iopub.execute_input":"2024-12-19T16:20:56.188662Z","iopub.status.idle":"2024-12-19T16:20:56.199590Z","shell.execute_reply.started":"2024-12-19T16:20:56.188632Z","shell.execute_reply":"2024-12-19T16:20:56.198726Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> ## Visualize The Data","metadata":{}},{"cell_type":"code","source":"df[\"CATEGORIES\"].value_counts().plot.bar()","metadata":{"execution":{"iopub.status.busy":"2024-12-19T16:20:59.044880Z","iopub.execute_input":"2024-12-19T16:20:59.045721Z","iopub.status.idle":"2024-12-19T16:20:59.266797Z","shell.execute_reply.started":"2024-12-19T16:20:59.045673Z","shell.execute_reply":"2024-12-19T16:20:59.265922Z"},"trusted":true},"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":{"execution":{"iopub.status.busy":"2024-12-19T16:21:03.194606Z","iopub.execute_input":"2024-12-19T16:21:03.194957Z","iopub.status.idle":"2024-12-19T16:21:31.082069Z","shell.execute_reply.started":"2024-12-19T16:21:03.194914Z","shell.execute_reply":"2024-12-19T16:21:31.081133Z"},"trusted":true},"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":{"execution":{"iopub.status.busy":"2024-12-19T16:21:36.509863Z","iopub.execute_input":"2024-12-19T16:21:36.510251Z","iopub.status.idle":"2024-12-19T16:21:36.771688Z","shell.execute_reply.started":"2024-12-19T16:21:36.510220Z","shell.execute_reply":"2024-12-19T16:21:36.770628Z"},"trusted":true},"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":{"execution":{"iopub.status.busy":"2024-12-19T16:21:42.028460Z","iopub.execute_input":"2024-12-19T16:21:42.028791Z","iopub.status.idle":"2024-12-19T16:21:42.035566Z","shell.execute_reply.started":"2024-12-19T16:21:42.028762Z","shell.execute_reply":"2024-12-19T16:21:42.034731Z"},"trusted":true},"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=0.20, random_state=42)\n\ntrain_df = train_df.reset_index(drop=True)\nvalid_df = valid_df.reset_index(drop=True)","metadata":{"execution":{"iopub.status.busy":"2024-12-19T16:21:46.025515Z","iopub.execute_input":"2024-12-19T16:21:46.026317Z","iopub.status.idle":"2024-12-19T16:21:46.040017Z","shell.execute_reply.started":"2024-12-19T16:21:46.026266Z","shell.execute_reply":"2024-12-19T16:21:46.039074Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> # Show tarin DataFrame","metadata":{}},{"cell_type":"code","source":"train_df['CATEGORIES'].value_counts()","metadata":{"execution":{"iopub.status.busy":"2024-12-19T16:21:48.606784Z","iopub.execute_input":"2024-12-19T16:21:48.607124Z","iopub.status.idle":"2024-12-19T16:21:48.615815Z","shell.execute_reply.started":"2024-12-19T16:21:48.607096Z","shell.execute_reply":"2024-12-19T16:21:48.614767Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_df['CATEGORIES'].value_counts().plot.bar()","metadata":{"execution":{"iopub.status.busy":"2024-12-19T16:21:51.651861Z","iopub.execute_input":"2024-12-19T16:21:51.652241Z","iopub.status.idle":"2024-12-19T16:21:51.872139Z","shell.execute_reply.started":"2024-12-19T16:21:51.652212Z","shell.execute_reply":"2024-12-19T16:21:51.870439Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> # Show valid DataFrame","metadata":{}},{"cell_type":"code","source":"valid_df['CATEGORIES'].value_counts()","metadata":{"execution":{"iopub.status.busy":"2024-12-19T16:21:56.109777Z","iopub.execute_input":"2024-12-19T16:21:56.110654Z","iopub.status.idle":"2024-12-19T16:21:56.117876Z","shell.execute_reply.started":"2024-12-19T16:21:56.110616Z","shell.execute_reply":"2024-12-19T16:21:56.116988Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"valid_df['CATEGORIES'].value_counts().plot.bar()","metadata":{"execution":{"iopub.status.busy":"2024-12-19T16:21:58.702398Z","iopub.execute_input":"2024-12-19T16:21:58.703236Z","iopub.status.idle":"2024-12-19T16:21:58.828442Z","shell.execute_reply.started":"2024-12-19T16:21:58.703205Z","shell.execute_reply":"2024-12-19T16:21:58.827653Z"},"trusted":true},"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":{"execution":{"iopub.status.busy":"2024-12-19T16:22:03.312196Z","iopub.execute_input":"2024-12-19T16:22:03.312553Z","iopub.status.idle":"2024-12-19T16:22:03.316820Z","shell.execute_reply.started":"2024-12-19T16:22:03.312522Z","shell.execute_reply":"2024-12-19T16:22:03.315943Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> ## Train Generator","metadata":{}},{"cell_type":"code","source":"df.head()","metadata":{"execution":{"iopub.status.busy":"2024-12-19T16:22:08.360495Z","iopub.execute_input":"2024-12-19T16:22:08.361500Z","iopub.status.idle":"2024-12-19T16:22:08.371848Z","shell.execute_reply.started":"2024-12-19T16:22:08.361449Z","shell.execute_reply":"2024-12-19T16:22:08.371195Z"},"trusted":true},"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":{"execution":{"iopub.status.busy":"2024-12-19T16:22:12.040783Z","iopub.execute_input":"2024-12-19T16:22:12.041492Z","iopub.status.idle":"2024-12-19T16:22:12.206706Z","shell.execute_reply.started":"2024-12-19T16:22:12.041459Z","shell.execute_reply":"2024-12-19T16:22:12.206125Z"},"trusted":true},"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":{"execution":{"iopub.status.busy":"2024-12-19T16:22:32.260526Z","iopub.execute_input":"2024-12-19T16:22:32.261329Z","iopub.status.idle":"2024-12-19T16:22:32.310080Z","shell.execute_reply.started":"2024-12-19T16:22:32.261296Z","shell.execute_reply":"2024-12-19T16:22:32.309317Z"},"trusted":true},"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":{"execution":{"iopub.status.busy":"2024-12-19T16:22:37.921138Z","iopub.execute_input":"2024-12-19T16:22:37.921473Z","iopub.status.idle":"2024-12-19T16:22:37.934267Z","shell.execute_reply.started":"2024-12-19T16:22:37.921446Z","shell.execute_reply":"2024-12-19T16:22:37.933183Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> # Show Generated Images from One-Image","metadata":{}},{"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":{"execution":{"iopub.status.busy":"2024-12-19T16:22:42.182082Z","iopub.execute_input":"2024-12-19T16:22:42.182461Z","iopub.status.idle":"2024-12-19T16:22:43.220098Z","shell.execute_reply.started":"2024-12-19T16:22:42.182429Z","shell.execute_reply":"2024-12-19T16:22:43.219000Z"},"trusted":true},"outputs":[],"execution_count":null},{"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":{"execution":{"iopub.status.busy":"2024-12-19T16:22:50.753586Z","iopub.execute_input":"2024-12-19T16:22:50.753926Z","iopub.status.idle":"2024-12-19T16:22:51.592835Z","shell.execute_reply.started":"2024-12-19T16:22:50.753895Z","shell.execute_reply":"2024-12-19T16:22:51.592015Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> ## Callbacks","metadata":{}},{"cell_type":"code","source":"from keras.callbacks import EarlyStopping, ReduceLROnPlateau","metadata":{"execution":{"iopub.status.busy":"2024-12-19T16:23:00.246516Z","iopub.execute_input":"2024-12-19T16:23:00.246852Z","iopub.status.idle":"2024-12-19T16:23:00.251697Z","shell.execute_reply.started":"2024-12-19T16:23:00.246823Z","shell.execute_reply":"2024-12-19T16:23:00.250809Z"},"trusted":true},"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":{"execution":{"iopub.status.busy":"2024-12-19T16:23:04.399773Z","iopub.execute_input":"2024-12-19T16:23:04.400430Z","iopub.status.idle":"2024-12-19T16:23:04.404293Z","shell.execute_reply.started":"2024-12-19T16:23:04.400397Z","shell.execute_reply":"2024-12-19T16:23:04.403358Z"},"trusted":true},"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":{"execution":{"iopub.status.busy":"2024-12-19T16:23:09.591422Z","iopub.execute_input":"2024-12-19T16:23:09.591737Z","iopub.status.idle":"2024-12-19T16:23:09.596199Z","shell.execute_reply.started":"2024-12-19T16:23:09.591712Z","shell.execute_reply":"2024-12-19T16:23:09.595087Z"},"trusted":true},"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":{"execution":{"iopub.status.busy":"2024-12-19T16:23:11.729078Z","iopub.execute_input":"2024-12-19T16:23:11.729418Z","iopub.status.idle":"2024-12-19T16:39:07.773877Z","shell.execute_reply.started":"2024-12-19T16:23:11.729389Z","shell.execute_reply":"2024-12-19T16:39:07.773198Z"},"trusted":true},"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":{"execution":{"iopub.status.busy":"2024-12-19T16:50:16.039378Z","iopub.execute_input":"2024-12-19T16:50:16.040337Z","iopub.status.idle":"2024-12-19T16:50:16.380894Z","shell.execute_reply.started":"2024-12-19T16:50:16.040302Z","shell.execute_reply":"2024-12-19T16:50:16.380068Z"},"trusted":true},"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":{"execution":{"iopub.status.busy":"2024-12-19T16:50:20.721772Z","iopub.execute_input":"2024-12-19T16:50:20.722100Z","iopub.status.idle":"2024-12-19T16:50:20.734704Z","shell.execute_reply.started":"2024-12-19T16:50:20.722071Z","shell.execute_reply":"2024-12-19T16:50:20.733795Z"},"trusted":true},"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":{"execution":{"iopub.status.busy":"2024-12-19T16:50:40.564544Z","iopub.execute_input":"2024-12-19T16:50:40.565125Z","iopub.status.idle":"2024-12-19T16:50:40.658409Z","shell.execute_reply.started":"2024-12-19T16:50:40.565091Z","shell.execute_reply":"2024-12-19T16:50:40.657504Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> # Predict","metadata":{}},{"cell_type":"code","source":"predictions = model.predict(test_generator)","metadata":{"execution":{"iopub.status.busy":"2024-12-19T16:50:44.325889Z","iopub.execute_input":"2024-12-19T16:50:44.326241Z","iopub.status.idle":"2024-12-19T16:51:00.376269Z","shell.execute_reply.started":"2024-12-19T16:50:44.326213Z","shell.execute_reply":"2024-12-19T16:51:00.375465Z"},"trusted":true},"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":{"execution":{"iopub.status.busy":"2024-12-19T16:51:09.470334Z","iopub.execute_input":"2024-12-19T16:51:09.470688Z","iopub.status.idle":"2024-12-19T16:51:09.476681Z","shell.execute_reply.started":"2024-12-19T16:51:09.470658Z","shell.execute_reply":"2024-12-19T16:51:09.475828Z"},"trusted":true},"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":{"execution":{"iopub.status.busy":"2024-12-19T16:51:12.932050Z","iopub.execute_input":"2024-12-19T16:51:12.932382Z","iopub.status.idle":"2024-12-19T16:51:12.939685Z","shell.execute_reply.started":"2024-12-19T16:51:12.932353Z","shell.execute_reply":"2024-12-19T16:51:12.938902Z"},"trusted":true},"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":"test_df['CATEGORIES'] = test_df['CATEGORIES'].replace({ 'dog': 1, 'cat': 0 })","metadata":{"execution":{"iopub.status.busy":"2024-12-19T16:51:15.930867Z","iopub.execute_input":"2024-12-19T16:51:15.931251Z","iopub.status.idle":"2024-12-19T16:51:15.942016Z","shell.execute_reply.started":"2024-12-19T16:51:15.931222Z","shell.execute_reply":"2024-12-19T16:51:15.941170Z"},"trusted":true},"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":{"execution":{"iopub.status.busy":"2024-12-19T16:51:21.273487Z","iopub.execute_input":"2024-12-19T16:51:21.274085Z","iopub.status.idle":"2024-12-19T16:51:21.406231Z","shell.execute_reply.started":"2024-12-19T16:51:21.274053Z","shell.execute_reply":"2024-12-19T16:51:21.405309Z"},"trusted":true},"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":{"execution":{"iopub.status.busy":"2024-12-19T16:51:24.575358Z","iopub.execute_input":"2024-12-19T16:51:24.576158Z","iopub.status.idle":"2024-12-19T16:51:27.737051Z","shell.execute_reply.started":"2024-12-19T16:51:24.576124Z","shell.execute_reply":"2024-12-19T16:51:27.736141Z"},"trusted":true},"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":{"execution":{"iopub.status.busy":"2024-12-19T16:51:38.127440Z","iopub.execute_input":"2024-12-19T16:51:38.128183Z","iopub.status.idle":"2024-12-19T16:51:38.227024Z","shell.execute_reply.started":"2024-12-19T16:51:38.128145Z","shell.execute_reply":"2024-12-19T16:51:38.226346Z"},"trusted":true},"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":{"execution":{"iopub.status.busy":"2024-12-19T16:51:41.755709Z","iopub.execute_input":"2024-12-19T16:51:41.756068Z","iopub.status.idle":"2024-12-19T16:51:41.786676Z","shell.execute_reply.started":"2024-12-19T16:51:41.756037Z","shell.execute_reply":"2024-12-19T16:51:41.785981Z"},"trusted":true},"outputs":[],"execution_count":null}]}