{"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":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-03T20:30:09.666425Z","iopub.execute_input":"2024-12-03T20:30:09.666751Z","iopub.status.idle":"2024-12-03T20:30:21.354001Z","shell.execute_reply.started":"2024-12-03T20:30:09.666722Z","shell.execute_reply":"2024-12-03T20:30:21.353104Z"}},"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":"2024-12-03T20:30:48.029893Z","iopub.execute_input":"2024-12-03T20:30:48.030938Z","iopub.status.idle":"2024-12-03T20:30:48.034971Z","shell.execute_reply.started":"2024-12-03T20:30:48.030900Z","shell.execute_reply":"2024-12-03T20:30:48.034113Z"}},"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":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-03T20:31:34.457147Z","iopub.execute_input":"2024-12-03T20:31:34.457584Z","iopub.status.idle":"2024-12-03T20:31:49.181428Z","shell.execute_reply.started":"2024-12-03T20:31:34.457544Z","shell.execute_reply":"2024-12-03T20:31:49.180573Z"}},"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":"2024-12-03T20:31:53.775550Z","iopub.execute_input":"2024-12-03T20:31:53.775868Z","iopub.status.idle":"2024-12-03T20:32:02.959524Z","shell.execute_reply.started":"2024-12-03T20:31:53.775839Z","shell.execute_reply":"2024-12-03T20:32:02.958568Z"}},"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":"2024-12-03T20:32:59.934020Z","iopub.execute_input":"2024-12-03T20:32:59.934395Z","iopub.status.idle":"2024-12-03T20:32:59.965694Z","shell.execute_reply.started":"2024-12-03T20:32:59.934368Z","shell.execute_reply":"2024-12-03T20:32:59.965094Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> ## Show DataFrame","metadata":{}},{"cell_type":"code","source":"df.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-03T20:37:10.510852Z","iopub.execute_input":"2024-12-03T20:37:10.511566Z","iopub.status.idle":"2024-12-03T20:37:10.523491Z","shell.execute_reply.started":"2024-12-03T20:37:10.511532Z","shell.execute_reply":"2024-12-03T20:37:10.522767Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.tail()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-03T20:37:22.795765Z","iopub.execute_input":"2024-12-03T20:37:22.796507Z","iopub.status.idle":"2024-12-03T20:37:22.804005Z","shell.execute_reply.started":"2024-12-03T20:37:22.796468Z","shell.execute_reply":"2024-12-03T20:37:22.803117Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.describe()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-03T20:37:25.179090Z","iopub.execute_input":"2024-12-03T20:37:25.179717Z","iopub.status.idle":"2024-12-03T20:37:25.195435Z","shell.execute_reply.started":"2024-12-03T20:37:25.179684Z","shell.execute_reply":"2024-12-03T20:37:25.194598Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df[\"CATEGORIES\"].value_counts()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-03T20:37:29.075758Z","iopub.execute_input":"2024-12-03T20:37:29.076428Z","iopub.status.idle":"2024-12-03T20:37:29.084467Z","shell.execute_reply.started":"2024-12-03T20:37:29.076391Z","shell.execute_reply":"2024-12-03T20:37:29.083594Z"}},"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":"2024-12-03T20:38:53.395572Z","iopub.execute_input":"2024-12-03T20:38:53.396273Z","iopub.status.idle":"2024-12-03T20:38:53.623628Z","shell.execute_reply.started":"2024-12-03T20:38:53.396239Z","shell.execute_reply":"2024-12-03T20:38:53.622256Z"}},"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":"2024-12-03T20:33:22.592991Z","iopub.execute_input":"2024-12-03T20:33:22.593826Z","iopub.status.idle":"2024-12-03T20:33:50.750331Z","shell.execute_reply.started":"2024-12-03T20:33:22.593793Z","shell.execute_reply":"2024-12-03T20:33:50.749465Z"}},"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":"2024-12-03T20:46:08.379383Z","iopub.execute_input":"2024-12-03T20:46:08.380212Z","iopub.status.idle":"2024-12-03T20:46:08.659135Z","shell.execute_reply.started":"2024-12-03T20:46:08.380177Z","shell.execute_reply":"2024-12-03T20:46:08.658243Z"}},"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":"2024-12-03T20:44:42.245750Z","iopub.execute_input":"2024-12-03T20:44:42.246472Z","iopub.status.idle":"2024-12-03T20:44:42.253343Z","shell.execute_reply.started":"2024-12-03T20:44:42.246437Z","shell.execute_reply":"2024-12-03T20:44:42.252572Z"}},"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":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-03T20:47:07.783655Z","iopub.execute_input":"2024-12-03T20:47:07.784379Z","iopub.status.idle":"2024-12-03T20:47:07.794529Z","shell.execute_reply.started":"2024-12-03T20:47:07.784345Z","shell.execute_reply":"2024-12-03T20:47:07.793812Z"}},"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":"2024-12-03T20:51:13.698548Z","iopub.execute_input":"2024-12-03T20:51:13.698897Z","iopub.status.idle":"2024-12-03T20:51:13.706906Z","shell.execute_reply.started":"2024-12-03T20:51:13.698867Z","shell.execute_reply":"2024-12-03T20:51:13.706097Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_df['CATEGORIES'].value_counts().plot.bar()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-03T20:51:17.545536Z","iopub.execute_input":"2024-12-03T20:51:17.545866Z","iopub.status.idle":"2024-12-03T20:51:17.730099Z","shell.execute_reply.started":"2024-12-03T20:51:17.545838Z","shell.execute_reply":"2024-12-03T20:51:17.728975Z"}},"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":"2024-12-03T20:52:23.638181Z","iopub.execute_input":"2024-12-03T20:52:23.638569Z","iopub.status.idle":"2024-12-03T20:52:23.647825Z","shell.execute_reply.started":"2024-12-03T20:52:23.638539Z","shell.execute_reply":"2024-12-03T20:52:23.646846Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"valid_df['CATEGORIES'].value_counts().plot.bar()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-03T20:52:27.344231Z","iopub.execute_input":"2024-12-03T20:52:27.344561Z","iopub.status.idle":"2024-12-03T20:52:27.671944Z","shell.execute_reply.started":"2024-12-03T20:52:27.344537Z","shell.execute_reply":"2024-12-03T20:52:27.670969Z"}},"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":"2024-12-03T20:52:37.655167Z","iopub.execute_input":"2024-12-03T20:52:37.655744Z","iopub.status.idle":"2024-12-03T20:52:37.659902Z","shell.execute_reply.started":"2024-12-03T20:52:37.655711Z","shell.execute_reply":"2024-12-03T20:52:37.658957Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"> ## Train Generator","metadata":{}},{"cell_type":"code","source":"df.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-03T20:53:22.607069Z","iopub.execute_input":"2024-12-03T20:53:22.607407Z","iopub.status.idle":"2024-12-03T20:53:22.616358Z","shell.execute_reply.started":"2024-12-03T20:53:22.607377Z","shell.execute_reply":"2024-12-03T20:53:22.615231Z"}},"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":"2024-12-03T20:53:36.926461Z","iopub.execute_input":"2024-12-03T20:53:36.927268Z","iopub.status.idle":"2024-12-03T20:53:37.096277Z","shell.execute_reply.started":"2024-12-03T20:53:36.927234Z","shell.execute_reply":"2024-12-03T20:53:37.095358Z"}},"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":"2024-12-03T20:55:39.633018Z","iopub.execute_input":"2024-12-03T20:55:39.633842Z","iopub.status.idle":"2024-12-03T20:55:39.682722Z","shell.execute_reply.started":"2024-12-03T20:55:39.633809Z","shell.execute_reply":"2024-12-03T20:55:39.681859Z"}},"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":"2024-12-03T20:57:25.423495Z","iopub.execute_input":"2024-12-03T20:57:25.423844Z","iopub.status.idle":"2024-12-03T20:57:25.436338Z","shell.execute_reply.started":"2024-12-03T20:57:25.423814Z","shell.execute_reply":"2024-12-03T20:57:25.435567Z"}},"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":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-03T20:58:57.969843Z","iopub.execute_input":"2024-12-03T20:58:57.970551Z","iopub.status.idle":"2024-12-03T20:58:58.929156Z","shell.execute_reply.started":"2024-12-03T20:58:57.970512Z","shell.execute_reply":"2024-12-03T20:58:58.928039Z"}},"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":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-03T21:00:02.558834Z","iopub.execute_input":"2024-12-03T21:00:02.559211Z","iopub.status.idle":"2024-12-03T21:00:03.407194Z","shell.execute_reply.started":"2024-12-03T21:00:02.559179Z","shell.execute_reply":"2024-12-03T21:00:03.406516Z"}},"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":"2024-12-03T21:01:12.366997Z","iopub.execute_input":"2024-12-03T21:01:12.367852Z","iopub.status.idle":"2024-12-03T21:01:12.372552Z","shell.execute_reply.started":"2024-12-03T21:01:12.367817Z","shell.execute_reply":"2024-12-03T21:01:12.371681Z"}},"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":"2024-12-03T21:01:18.920292Z","iopub.execute_input":"2024-12-03T21:01:18.920606Z","iopub.status.idle":"2024-12-03T21:01:18.924593Z","shell.execute_reply.started":"2024-12-03T21:01:18.920580Z","shell.execute_reply":"2024-12-03T21:01:18.923704Z"}},"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":"2024-12-03T21:01:22.143447Z","iopub.execute_input":"2024-12-03T21:01:22.144022Z","iopub.status.idle":"2024-12-03T21:01:22.148678Z","shell.execute_reply.started":"2024-12-03T21:01:22.143984Z","shell.execute_reply":"2024-12-03T21:01:22.147802Z"}},"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":"2024-12-03T21:01:27.863968Z","iopub.execute_input":"2024-12-03T21:01:27.864344Z","iopub.status.idle":"2024-12-03T21:17:14.666886Z","shell.execute_reply.started":"2024-12-03T21:01:27.864312Z","shell.execute_reply":"2024-12-03T21:17:14.665948Z"}},"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":"2024-12-03T21:17:35.579558Z","iopub.execute_input":"2024-12-03T21:17:35.579886Z","iopub.status.idle":"2024-12-03T21:17:35.922407Z","shell.execute_reply.started":"2024-12-03T21:17:35.579856Z","shell.execute_reply":"2024-12-03T21:17:35.921598Z"}},"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":"2024-12-03T21:17:45.777996Z","iopub.execute_input":"2024-12-03T21:17:45.778356Z","iopub.status.idle":"2024-12-03T21:17:45.790633Z","shell.execute_reply.started":"2024-12-03T21:17:45.778327Z","shell.execute_reply":"2024-12-03T21:17:45.789690Z"}},"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":"2024-12-03T21:17:50.290434Z","iopub.execute_input":"2024-12-03T21:17:50.290771Z","iopub.status.idle":"2024-12-03T21:17:50.380303Z","shell.execute_reply.started":"2024-12-03T21:17:50.290743Z","shell.execute_reply":"2024-12-03T21:17:50.379576Z"}},"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":"2024-12-03T21:17:53.402790Z","iopub.execute_input":"2024-12-03T21:17:53.403146Z","iopub.status.idle":"2024-12-03T21:18:09.628110Z","shell.execute_reply.started":"2024-12-03T21:17:53.403116Z","shell.execute_reply":"2024-12-03T21:18:09.627344Z"}},"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":"2024-12-03T21:18:37.666595Z","iopub.execute_input":"2024-12-03T21:18:37.667356Z","iopub.status.idle":"2024-12-03T21:18:37.672572Z","shell.execute_reply.started":"2024-12-03T21:18:37.667323Z","shell.execute_reply":"2024-12-03T21:18:37.671853Z"}},"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":"2024-12-03T21:18:40.993796Z","iopub.execute_input":"2024-12-03T21:18:40.994427Z","iopub.status.idle":"2024-12-03T21:18:41.000766Z","shell.execute_reply.started":"2024-12-03T21:18:40.994394Z","shell.execute_reply":"2024-12-03T21:18:41.000015Z"}},"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":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-03T21:18:44.193821Z","iopub.execute_input":"2024-12-03T21:18:44.194250Z","iopub.status.idle":"2024-12-03T21:18:44.204984Z","shell.execute_reply.started":"2024-12-03T21:18:44.194217Z","shell.execute_reply":"2024-12-03T21:18:44.204079Z"}},"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":"2024-12-03T21:19:12.034158Z","iopub.execute_input":"2024-12-03T21:19:12.034487Z","iopub.status.idle":"2024-12-03T21:19:12.218831Z","shell.execute_reply.started":"2024-12-03T21:19:12.034459Z","shell.execute_reply":"2024-12-03T21:19:12.218027Z"}},"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":"2024-12-03T21:19:22.825687Z","iopub.execute_input":"2024-12-03T21:19:22.826063Z","iopub.status.idle":"2024-12-03T21:19:26.251728Z","shell.execute_reply.started":"2024-12-03T21:19:22.826000Z","shell.execute_reply":"2024-12-03T21:19:26.250507Z"}},"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":"2024-12-03T21:19:33.409401Z","iopub.execute_input":"2024-12-03T21:19:33.409745Z","iopub.status.idle":"2024-12-03T21:19:33.508317Z","shell.execute_reply.started":"2024-12-03T21:19:33.409715Z","shell.execute_reply":"2024-12-03T21:19:33.507615Z"}},"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":"2024-12-03T21:19:39.313291Z","iopub.execute_input":"2024-12-03T21:19:39.313608Z","iopub.status.idle":"2024-12-03T21:19:39.344657Z","shell.execute_reply.started":"2024-12-03T21:19:39.313583Z","shell.execute_reply":"2024-12-03T21:19:39.343978Z"}},"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":"2024-12-03T21:19:41.402110Z","iopub.execute_input":"2024-12-03T21:19:41.402918Z","iopub.status.idle":"2024-12-03T21:19:43.246882Z","shell.execute_reply.started":"2024-12-03T21:19:41.402868Z","shell.execute_reply":"2024-12-03T21:19:43.245749Z"}},"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,"execution":{"iopub.status.busy":"2024-12-03T21:20:01.409266Z","iopub.execute_input":"2024-12-03T21:20:01.409801Z","iopub.status.idle":"2024-12-03T21:20:03.019334Z","shell.execute_reply.started":"2024-12-03T21:20:01.409749Z","shell.execute_reply":"2024-12-03T21:20:03.018408Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}