{"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":"none","dataSources":[{"sourceId":3362,"databundleVersionId":31148,"sourceType":"competition"}],"dockerImageVersionId":30762,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"Yo voy a ir cambiando algunas cosas del notebook original para ver cómo influyen","metadata":{}},{"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":"2024-10-31T09:05:07.024573Z","iopub.execute_input":"2024-10-31T09:05:07.025339Z","iopub.status.idle":"2024-10-31T09:05:25.805468Z","shell.execute_reply.started":"2024-10-31T09:05:07.025289Z","shell.execute_reply":"2024-10-31T09:05:25.804487Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-10-31T09:05:25.807097Z","iopub.execute_input":"2024-10-31T09:05:25.807644Z","iopub.status.idle":"2024-10-31T09:05:25.812165Z","shell.execute_reply.started":"2024-10-31T09:05:25.807609Z","shell.execute_reply":"2024-10-31T09:05:25.811124Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-10-31T09:05:25.813655Z","iopub.execute_input":"2024-10-31T09:05:25.814072Z","iopub.status.idle":"2024-10-31T09:05:25.841214Z","shell.execute_reply.started":"2024-10-31T09:05:25.814027Z","shell.execute_reply":"2024-10-31T09:05:25.840392Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-10-31T09:05:25.843044Z","iopub.execute_input":"2024-10-31T09:05:25.843378Z","iopub.status.idle":"2024-10-31T09:05:40.793914Z","shell.execute_reply.started":"2024-10-31T09:05:25.843344Z","shell.execute_reply":"2024-10-31T09:05:40.792999Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-10-31T09:06:00.451346Z","iopub.execute_input":"2024-10-31T09:06:00.452021Z","iopub.status.idle":"2024-10-31T09:06:00.501714Z","shell.execute_reply.started":"2024-10-31T09:06:00.451979Z","shell.execute_reply":"2024-10-31T09:06:00.500767Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"> ## Show DataFrame","metadata":{}},{"cell_type":"code","source":"df.head()","metadata":{"execution":{"iopub.status.busy":"2024-10-31T09:06:56.793645Z","iopub.execute_input":"2024-10-31T09:06:56.794044Z","iopub.status.idle":"2024-10-31T09:06:56.820510Z","shell.execute_reply.started":"2024-10-31T09:06:56.794008Z","shell.execute_reply":"2024-10-31T09:06:56.819627Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df[\"CATEGORIES\"].value_counts()","metadata":{"execution":{"iopub.status.busy":"2024-10-31T09:07:19.655296Z","iopub.execute_input":"2024-10-31T09:07:19.656091Z","iopub.status.idle":"2024-10-31T09:07:19.677654Z","shell.execute_reply.started":"2024-10-31T09:07:19.656046Z","shell.execute_reply":"2024-10-31T09:07:19.676837Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"> ## Visualize The Data","metadata":{}},{"cell_type":"code","source":"df[\"CATEGORIES\"].value_counts().plot.bar()","metadata":{"execution":{"iopub.status.busy":"2024-10-31T09:07:27.447939Z","iopub.execute_input":"2024-10-31T09:07:27.448786Z","iopub.status.idle":"2024-10-31T09:07:27.733215Z","shell.execute_reply.started":"2024-10-31T09:07:27.448750Z","shell.execute_reply":"2024-10-31T09:07:27.732219Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Vemos que tenemos el mismo número de gatos que de perros (de 0 que de 1).","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":"2024-10-31T09:08:34.536586Z","iopub.execute_input":"2024-10-31T09:08:34.537177Z","iopub.status.idle":"2024-10-31T09:09:04.837148Z","shell.execute_reply.started":"2024-10-31T09:08:34.537143Z","shell.execute_reply":"2024-10-31T09:09:04.836175Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-10-31T09:08:17.396132Z","iopub.execute_input":"2024-10-31T09:08:17.397037Z","iopub.status.idle":"2024-10-31T09:08:17.627970Z","shell.execute_reply.started":"2024-10-31T09:08:17.396987Z","shell.execute_reply":"2024-10-31T09:08:17.626971Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-10-31T09:09:19.700315Z","iopub.execute_input":"2024-10-31T09:09:19.701054Z","iopub.status.idle":"2024-10-31T09:09:19.709192Z","shell.execute_reply.started":"2024-10-31T09:09:19.701014Z","shell.execute_reply":"2024-10-31T09:09:19.708243Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"> # Split Data","metadata":{}},{"cell_type":"markdown","source":"Voy a cambiar el random state y el ratio de train/test","metadata":{}},{"cell_type":"code","source":"train_df, valid_df = train_test_split(df, test_size=0.3, random_state=564236)\n\ntrain_df = train_df.reset_index(drop=True)\nvalid_df = valid_df.reset_index(drop=True)","metadata":{"execution":{"iopub.status.busy":"2024-10-31T09:10:08.012085Z","iopub.execute_input":"2024-10-31T09:10:08.013034Z","iopub.status.idle":"2024-10-31T09:10:08.034944Z","shell.execute_reply.started":"2024-10-31T09:10:08.012982Z","shell.execute_reply":"2024-10-31T09:10:08.033903Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"> # Show train target","metadata":{}},{"cell_type":"code","source":"train_df['CATEGORIES'].value_counts()","metadata":{"execution":{"iopub.status.busy":"2024-10-31T09:10:28.523808Z","iopub.execute_input":"2024-10-31T09:10:28.524762Z","iopub.status.idle":"2024-10-31T09:10:28.536263Z","shell.execute_reply.started":"2024-10-31T09:10:28.524716Z","shell.execute_reply":"2024-10-31T09:10:28.535034Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"> # Show validation target","metadata":{}},{"cell_type":"code","source":"valid_df['CATEGORIES'].value_counts()","metadata":{"execution":{"iopub.status.busy":"2024-10-31T09:10:32.363471Z","iopub.execute_input":"2024-10-31T09:10:32.363863Z","iopub.status.idle":"2024-10-31T09:10:32.373143Z","shell.execute_reply.started":"2024-10-31T09:10:32.363827Z","shell.execute_reply":"2024-10-31T09:10:32.372003Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"En ambos casos se han obtenido proporciones muy similares","metadata":{}},{"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":"2024-10-31T09:13:10.901460Z","iopub.execute_input":"2024-10-31T09:13:10.902194Z","iopub.status.idle":"2024-10-31T09:13:10.907035Z","shell.execute_reply.started":"2024-10-31T09:13:10.902154Z","shell.execute_reply":"2024-10-31T09:13:10.905986Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"> ## Train Generator","metadata":{}},{"cell_type":"code","source":"df.head()","metadata":{"execution":{"iopub.status.busy":"2024-10-31T09:13:13.420229Z","iopub.execute_input":"2024-10-31T09:13:13.420608Z","iopub.status.idle":"2024-10-31T09:13:13.430896Z","shell.execute_reply.started":"2024-10-31T09:13:13.420572Z","shell.execute_reply":"2024-10-31T09:13:13.429905Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-10-31T09:13:23.888848Z","iopub.execute_input":"2024-10-31T09:13:23.889508Z","iopub.status.idle":"2024-10-31T09:13:24.107139Z","shell.execute_reply.started":"2024-10-31T09:13:23.889471Z","shell.execute_reply":"2024-10-31T09:13:24.106110Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-10-31T09:13:34.018596Z","iopub.execute_input":"2024-10-31T09:13:34.019019Z","iopub.status.idle":"2024-10-31T09:13:34.128191Z","shell.execute_reply.started":"2024-10-31T09:13:34.018971Z","shell.execute_reply":"2024-10-31T09:13:34.127411Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-10-31T09:13:39.160252Z","iopub.execute_input":"2024-10-31T09:13:39.161041Z","iopub.status.idle":"2024-10-31T09:13:39.175633Z","shell.execute_reply.started":"2024-10-31T09:13:39.161001Z","shell.execute_reply":"2024-10-31T09:13:39.174655Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-10-31T09:14:13.392845Z","iopub.execute_input":"2024-10-31T09:14:13.393692Z","iopub.status.idle":"2024-10-31T09:14:14.384138Z","shell.execute_reply.started":"2024-10-31T09:14:13.393654Z","shell.execute_reply":"2024-10-31T09:14:14.383204Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"markdown","source":"Aquí voy a retocar yo algunos hiperparámetros para ver el cambio en el resultado","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":"2024-10-31T09:15:51.276329Z","iopub.execute_input":"2024-10-31T09:15:51.276984Z","iopub.status.idle":"2024-10-31T09:15:52.381673Z","shell.execute_reply.started":"2024-10-31T09:15:51.276929Z","shell.execute_reply":"2024-10-31T09:15:52.380662Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"> ## Callbacks","metadata":{}},{"cell_type":"code","source":"from keras.callbacks import EarlyStopping, ReduceLROnPlateau","metadata":{"execution":{"iopub.status.busy":"2024-10-31T09:15:56.962754Z","iopub.execute_input":"2024-10-31T09:15:56.963659Z","iopub.status.idle":"2024-10-31T09:15:56.968445Z","shell.execute_reply.started":"2024-10-31T09:15:56.963618Z","shell.execute_reply":"2024-10-31T09:15:56.967326Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-10-31T09:16:07.302451Z","iopub.execute_input":"2024-10-31T09:16:07.303422Z","iopub.status.idle":"2024-10-31T09:16:07.307532Z","shell.execute_reply.started":"2024-10-31T09:16:07.303381Z","shell.execute_reply":"2024-10-31T09:16:07.306614Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-10-31T09:16:12.474024Z","iopub.execute_input":"2024-10-31T09:16:12.474396Z","iopub.status.idle":"2024-10-31T09:16:12.479849Z","shell.execute_reply.started":"2024-10-31T09:16:12.474361Z","shell.execute_reply":"2024-10-31T09:16:12.478618Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-10-31T09:16:17.647292Z","iopub.execute_input":"2024-10-31T09:16:17.647675Z","iopub.status.idle":"2024-10-31T09:33:45.518245Z","shell.execute_reply.started":"2024-10-31T09:16:17.647638Z","shell.execute_reply":"2024-10-31T09:33:45.517179Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-10-31T09:34:02.506353Z","iopub.execute_input":"2024-10-31T09:34:02.507121Z","iopub.status.idle":"2024-10-31T09:34:02.946607Z","shell.execute_reply.started":"2024-10-31T09:34:02.507078Z","shell.execute_reply":"2024-10-31T09:34:02.945646Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Se puede atisbar el inicio asintótico en el train (tanto en precisión como en pérdida), en cambio, estas métricas en la validación son irregulares con este número de epochs.","metadata":{}},{"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":"2024-10-31T09:36:27.448218Z","iopub.execute_input":"2024-10-31T09:36:27.448637Z","iopub.status.idle":"2024-10-31T09:36:27.463042Z","shell.execute_reply.started":"2024-10-31T09:36:27.448599Z","shell.execute_reply":"2024-10-31T09:36:27.462120Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-10-31T09:36:33.670108Z","iopub.execute_input":"2024-10-31T09:36:33.671049Z","iopub.status.idle":"2024-10-31T09:36:33.805608Z","shell.execute_reply.started":"2024-10-31T09:36:33.671008Z","shell.execute_reply":"2024-10-31T09:36:33.804834Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"> # Predict","metadata":{}},{"cell_type":"code","source":"predictions = model.predict(test_generator)","metadata":{"execution":{"iopub.status.busy":"2024-10-31T09:36:35.897200Z","iopub.execute_input":"2024-10-31T09:36:35.897571Z","iopub.status.idle":"2024-10-31T09:36:55.119851Z","shell.execute_reply.started":"2024-10-31T09:36:35.897536Z","shell.execute_reply":"2024-10-31T09:36:55.118799Z"},"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[\"CATEGORIES\"] = np.argmax(predictions, axis=1)","metadata":{"execution":{"iopub.status.busy":"2024-10-31T09:36:55.121611Z","iopub.execute_input":"2024-10-31T09:36:55.121991Z","iopub.status.idle":"2024-10-31T09:36:55.127687Z","shell.execute_reply.started":"2024-10-31T09:36:55.121934Z","shell.execute_reply":"2024-10-31T09:36:55.126790Z"},"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['CATEGORIES'] = test_df['CATEGORIES'].replace(label_map)","metadata":{"execution":{"iopub.status.busy":"2024-10-31T09:37:08.175907Z","iopub.execute_input":"2024-10-31T09:37:08.176777Z","iopub.status.idle":"2024-10-31T09:37:08.184200Z","shell.execute_reply.started":"2024-10-31T09:37:08.176734Z","shell.execute_reply":"2024-10-31T09:37:08.183124Z"},"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\n\n","metadata":{}},{"cell_type":"code","source":"test_df['CATEGORIES'] = test_df['CATEGORIES'].replace({ 'dog': 1, 'cat': 0 })","metadata":{"execution":{"iopub.status.busy":"2024-10-31T09:37:11.213741Z","iopub.execute_input":"2024-10-31T09:37:11.214116Z","iopub.status.idle":"2024-10-31T09:37:11.229565Z","shell.execute_reply.started":"2024-10-31T09:37:11.214076Z","shell.execute_reply":"2024-10-31T09:37:11.228644Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-10-31T09:37:15.297333Z","iopub.execute_input":"2024-10-31T09:37:15.297708Z","iopub.status.idle":"2024-10-31T09:37:15.538724Z","shell.execute_reply.started":"2024-10-31T09:37:15.297672Z","shell.execute_reply":"2024-10-31T09:37:15.537712Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-10-31T09:37:32.060647Z","iopub.execute_input":"2024-10-31T09:37:32.061058Z","iopub.status.idle":"2024-10-31T09:37:35.974680Z","shell.execute_reply.started":"2024-10-31T09:37:32.061021Z","shell.execute_reply":"2024-10-31T09:37:35.973164Z"},"trusted":true},"execution_count":null,"outputs":[]}]}