{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":5441,"databundleVersionId":38425,"sourceType":"competition"}],"dockerImageVersionId":30840,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"**Zipping the data through ZipFile**","metadata":{}},{"cell_type":"code","source":"import os\nfrom zipfile import ZipFile","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-06T10:33:17.171151Z","iopub.execute_input":"2025-02-06T10:33:17.17148Z","iopub.status.idle":"2025-02-06T10:33:17.175057Z","shell.execute_reply.started":"2025-02-06T10:33:17.171456Z","shell.execute_reply":"2025-02-06T10:33:17.174152Z"}},"outputs":[],"execution_count":2},{"cell_type":"code","source":"# Uploading Data \nfile_name = \"/kaggle/input/dogs-vs-cats-redux-kernels-edition/train.zip\"\n\nwith ZipFile(file_name, 'r') as zip:\n zip.extractall()\n print('Done')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-06T10:33:18.832332Z","iopub.execute_input":"2025-02-06T10:33:18.832598Z","iopub.status.idle":"2025-02-06T10:33:29.761158Z","shell.execute_reply.started":"2025-02-06T10:33:18.832579Z","shell.execute_reply":"2025-02-06T10:33:29.76003Z"}},"outputs":[{"name":"stdout","text":"Done\n","output_type":"stream"}],"execution_count":3},{"cell_type":"code","source":"data_dir_list = os.listdir(\"/kaggle/working/train\")\n# print(data_dir_list)\n\npath, dirs, files = next(os.walk(\"/kaggle/working/train\"))\nfile_count = len(files)\n# print(path)\n# print(dirs)\n# print(files)\n\nprint(file_count)\n\noriginal_dataset_dir = \"/kaggle/working/train\"\nbase_dir = \"/kaggle/working/cats_and_dogs_small\"\nos.mkdir(base_dir)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-06T10:33:37.427242Z","iopub.execute_input":"2025-02-06T10:33:37.427552Z","iopub.status.idle":"2025-02-06T10:33:37.464031Z","shell.execute_reply.started":"2025-02-06T10:33:37.427528Z","shell.execute_reply":"2025-02-06T10:33:37.463242Z"}},"outputs":[{"name":"stdout","text":"25000\n","output_type":"stream"}],"execution_count":4},{"cell_type":"code","source":"train_dir = os.path.join(base_dir, 'train')\nos.mkdir(train_dir)\n\nvalidation_dir = os.path.join(base_dir, 'validation')\nos.mkdir(validation_dir)\n\ntest_dir = os.path.join(base_dir, 'test')\nos.mkdir(test_dir)\n\ntrain_cats_dir = os.path.join(train_dir, 'cats')\nos.mkdir(train_cats_dir)\n\ntrain_dogs_dir = os.path.join(train_dir, 'dogs')\nos.mkdir(train_dogs_dir)\n\nvalidation_cats_dir = os.path.join(validation_dir, 'cats')\nos.mkdir(validation_cats_dir)\n\nvalidation_dogs_dir = os.path.join(validation_dir, 'dogs')\nos.mkdir(validation_dogs_dir)\n\ntest_cats_dir = os.path.join(test_dir, 'cats')\nos.mkdir(test_cats_dir)\n\ntest_dogs_dir = os.path.join(test_dir, 'dogs')\nos.mkdir(test_dogs_dir)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-06T10:33:46.143939Z","iopub.execute_input":"2025-02-06T10:33:46.144293Z","iopub.status.idle":"2025-02-06T10:33:46.151507Z","shell.execute_reply.started":"2025-02-06T10:33:46.144264Z","shell.execute_reply":"2025-02-06T10:33:46.150855Z"}},"outputs":[],"execution_count":5},{"cell_type":"code","source":"import shutil\n\nfnames = ['cat.{}.jpg'.format(i) for i in range(1000)]\nfor fname in fnames:\n src = os.path.join(original_dataset_dir, fname)\n dst = os.path.join(train_cats_dir, fname)\n # print(src, dst)\n shutil.copyfile(src, dst)\n \nfnames = ['cat.{}.jpg'.format(i) for i in range(1000, 1500)]\nfor fname in fnames:\n src = os.path.join(original_dataset_dir, fname)\n dst = os.path.join(validation_cats_dir, fname)\n shutil.copyfile(src,dst)\n\nfnames = ['cat.{}.jpg'.format(i) for i in range(1500, 2000)]\nfor fname in fnames:\n src = os.path.join(original_dataset_dir, fname)\n dst = os.path.join(test_cats_dir, fname)\n shutil.copyfile(src, dst)\n\nfnames = ['dog.{}.jpg'.format(i) for i in range(1000)]\nfor fname in fnames:\n src = os.path.join(original_dataset_dir, fname)\n dst = os.path.join(train_dogs_dir, fname)\n shutil.copyfile(src, dst)\n\nfnames = ['dog.{}.jpg'.format(i) for i in range(1000, 1500)]\nfor fname in fnames:\n src = os.path.join(original_dataset_dir, fname)\n dst = os.path.join(validation_dogs_dir, fname)\n shutil.copyfile(src, dst)\n\nfnames = ['dog.{}.jpg'.format(i) for i in range(1500, 2000)]\nfor fname in fnames:\n src = os.path.join(original_dataset_dir, fname)\n dst = os.path.join(test_dogs_dir, fname)\n shutil.copyfile(src, dst)\n\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-06T10:33:49.503862Z","iopub.execute_input":"2025-02-06T10:33:49.504128Z","iopub.status.idle":"2025-02-06T10:33:49.885851Z","shell.execute_reply.started":"2025-02-06T10:33:49.504109Z","shell.execute_reply":"2025-02-06T10:33:49.885241Z"}},"outputs":[],"execution_count":6},{"cell_type":"code","source":"print('total training cats images:', len(os.listdir(train_cats_dir)))\nprint('total testing cats images', len(os.listdir(test_cats_dir)))\nprint('total validation cats images', len(os.listdir(validation_cats_dir)))\n\nprint('total training dogs images', len(os.listdir(train_dogs_dir)))\nprint('total testing dogs images', len(os.listdir(test_dogs_dir)))\nprint('total validation dogs images', len(os.listdir(validation_dogs_dir)))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-06T10:33:53.183486Z","iopub.execute_input":"2025-02-06T10:33:53.183751Z","iopub.status.idle":"2025-02-06T10:33:53.193786Z","shell.execute_reply.started":"2025-02-06T10:33:53.183733Z","shell.execute_reply":"2025-02-06T10:33:53.192949Z"}},"outputs":[{"name":"stdout","text":"total training cats images: 1000\ntotal testing cats images 500\ntotal validation cats images 500\ntotal training dogs images 1000\ntotal testing dogs images 500\ntotal validation dogs images 500\n","output_type":"stream"}],"execution_count":7},{"cell_type":"code","source":"from keras import layers, models\n\nmodel = models.Sequential()\nmodel.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(150, 150, 3)))\nmodel.add(layers.MaxPooling2D((2, 2)))\nmodel.add(layers.Conv2D(64, (3, 3), activation='relu'))\nmodel.add(layers.MaxPooling2D((2, 2)))\nmodel.add(layers.Conv2D(128, (3, 3), activation='relu'))\nmodel.add(layers.MaxPooling2D((2, 2)))\nmodel.add(layers.Conv2D(128, (3, 3), activation='relu'))\nmodel.add(layers.MaxPooling2D((2, 2)))\nmodel.add(layers.Flatten())\nmodel.add(layers.Dense(512, activation='relu'))\nmodel.add(layers.Dense(1, activation='sigmoid'))\nmodel.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-06T09:21:58.820459Z","iopub.execute_input":"2025-02-06T09:21:58.820824Z","iopub.status.idle":"2025-02-06T09:22:01.124263Z","shell.execute_reply.started":"2025-02-06T09:21:58.820797Z","shell.execute_reply":"2025-02-06T09:22:01.123645Z"}},"outputs":[{"name":"stderr","text":"/usr/local/lib/python3.10/dist-packages/keras/src/layers/convolutional/base_conv.py:107: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":"\u001b[1mModel: \"sequential\"\u001b[0m\n","text/html":"
Model: \"sequential\"\n
\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓\n┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩\n│ conv2d (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m148\u001b[0m, \u001b[38;5;34m148\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m896\u001b[0m │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m74\u001b[0m, \u001b[38;5;34m74\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ conv2d_1 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m72\u001b[0m, \u001b[38;5;34m72\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m18,496\u001b[0m │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ max_pooling2d_1 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m36\u001b[0m, \u001b[38;5;34m36\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ conv2d_2 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m34\u001b[0m, \u001b[38;5;34m34\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m73,856\u001b[0m │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ max_pooling2d_2 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m17\u001b[0m, \u001b[38;5;34m17\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ conv2d_3 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m15\u001b[0m, \u001b[38;5;34m15\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m147,584\u001b[0m │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ max_pooling2d_3 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m7\u001b[0m, \u001b[38;5;34m7\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ flatten (\u001b[38;5;33mFlatten\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m6272\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ dense (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m) │ \u001b[38;5;34m3,211,776\u001b[0m │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ dense_1 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m) │ \u001b[38;5;34m513\u001b[0m │\n└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n","text/html":"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓\n┃ Layer (type)                         ┃ Output Shape                ┃         Param # ┃\n┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩\n│ conv2d (Conv2D)                      │ (None, 148, 148, 32)        │             896 │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ max_pooling2d (MaxPooling2D)         │ (None, 74, 74, 32)          │               0 │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ conv2d_1 (Conv2D)                    │ (None, 72, 72, 64)          │          18,496 │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ max_pooling2d_1 (MaxPooling2D)       │ (None, 36, 36, 64)          │               0 │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ conv2d_2 (Conv2D)                    │ (None, 34, 34, 128)         │          73,856 │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ max_pooling2d_2 (MaxPooling2D)       │ (None, 17, 17, 128)         │               0 │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ conv2d_3 (Conv2D)                    │ (None, 15, 15, 128)         │         147,584 │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ max_pooling2d_3 (MaxPooling2D)       │ (None, 7, 7, 128)           │               0 │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ flatten (Flatten)                    │ (None, 6272)                │               0 │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ dense (Dense)                        │ (None, 512)                 │       3,211,776 │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ dense_1 (Dense)                      │ (None, 1)                   │             513 │\n└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n
\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"\u001b[1m Total params: \u001b[0m\u001b[38;5;34m3,453,121\u001b[0m (13.17 MB)\n","text/html":"
 Total params: 3,453,121 (13.17 MB)\n
\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m3,453,121\u001b[0m (13.17 MB)\n","text/html":"
 Trainable params: 3,453,121 (13.17 MB)\n
\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n","text/html":"
 Non-trainable params: 0 (0.00 B)\n
\n"},"metadata":{}}],"execution_count":17},{"cell_type":"code","source":"# compilations:\n\nfrom keras import optimizers\n\nmodel.compile(loss='binary_crossentropy',\n optimizer=optimizers.RMSprop(learning_rate=1e-4),\n metrics=['acc'])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-06T09:26:06.957358Z","iopub.execute_input":"2025-02-06T09:26:06.957731Z","iopub.status.idle":"2025-02-06T09:26:06.970463Z","shell.execute_reply.started":"2025-02-06T09:26:06.957701Z","shell.execute_reply":"2025-02-06T09:26:06.969627Z"}},"outputs":[],"execution_count":20},{"cell_type":"code","source":"train_datagen = ImageDataGenerator(rescale=1./255)\ntest_datagen = ImageDataGenerator(rescale=1./255)\n\ntrain_generator = train_datagen.flow_from_directory(train_dir,\n target_size=(150, 150),\n batch_size= 20,\n class_mode = \"binary\")\n\nvalidation_generator = test_datagen.flow_from_directory(validation_dir,\n target_size=(150, 150),\n batch_size= 20,\n class_mode = \"binary\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-06T09:31:33.955001Z","iopub.execute_input":"2025-02-06T09:31:33.955389Z","iopub.status.idle":"2025-02-06T09:31:34.011814Z","shell.execute_reply.started":"2025-02-06T09:31:33.955358Z","shell.execute_reply":"2025-02-06T09:31:34.011215Z"}},"outputs":[{"name":"stdout","text":"Found 2000 images belonging to 2 classes.\nFound 1000 images belonging to 2 classes.\n","output_type":"stream"}],"execution_count":24},{"cell_type":"code","source":"import warnings\nwarnings.filterwarnings(\"ignore\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-06T10:41:44.390617Z","iopub.execute_input":"2025-02-06T10:41:44.390955Z","iopub.status.idle":"2025-02-06T10:41:44.394575Z","shell.execute_reply.started":"2025-02-06T10:41:44.390928Z","shell.execute_reply":"2025-02-06T10:41:44.393697Z"}},"outputs":[],"execution_count":21},{"cell_type":"code","source":"history = model.fit(train_generator,\n steps_per_epoch = 100,\n epochs = 30,\n validation_data = validation_generator,\n validation_steps = 10)\n\nmodel.save('cats_and_dogs_small_1.h5')","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\n# Get the available epochs for training and validation\ntrain_epochs = range(1, len(history.history['acc']) + 1)\nval_epochs = range(1, len(history.history['val_acc']) + 1)\n\n# Plot training accuracy\nplt.plot(train_epochs, history.history['acc'], 'bo', label=\"Training acc\")\n\n# Plot validation accuracy, ensuring matching length\nplt.plot(val_epochs, history.history['val_acc'], 'b', label='Validation acc')\n\nplt.title(\"Training and validation accuracy\")\nplt.legend()\nplt.show()\n\n# Repeat for loss\nplt.figure()\ntrain_epochs_loss = range(1, len(history.history['loss']) + 1)\nval_epochs_loss = range(1, len(history.history['val_loss']) + 1)\n\nplt.plot(train_epochs_loss, history.history['loss'], 'bo', label=\"Training loss\")\nplt.plot(val_epochs_loss, history.history['val_loss'], 'b', label='Validation loss')\n\nplt.title(\"Training and validation loss\")\nplt.legend()\nplt.show()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-06T09:47:39.684829Z","iopub.execute_input":"2025-02-06T09:47:39.685175Z","iopub.status.idle":"2025-02-06T09:47:40.02807Z","shell.execute_reply.started":"2025-02-06T09:47:39.685144Z","shell.execute_reply":"2025-02-06T09:47:40.027276Z"}},"outputs":[{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{}}],"execution_count":32},{"cell_type":"code","source":"from keras import layers, models\n\n\nmodel = models.Sequential()\nmodel.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(150, 150, 3)))\nmodel.add(layers.MaxPooling2D((2, 2)))\nmodel.add(layers.Conv2D(64, (3, 3), activation='relu'))\nmodel.add(layers.MaxPooling2D((2, 2)))\nmodel.add(layers.Conv2D(128, (3, 3),activation='relu'))\nmodel.add(layers.MaxPooling2D((2, 2)))\nmodel.add(layers.Conv2D(128, (3, 3), activation='relu'))\nmodel.add(layers.MaxPooling2D((2, 2)))\nmodel.add(layers.Flatten())\nmodel.add(layers.Dropout(0.5))\nmodel.add(layers.Dense(512, activation='relu'))\nmodel.add(layers.Dense(1, activation='sigmoid'))\nmodel.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-06T10:35:34.446727Z","iopub.execute_input":"2025-02-06T10:35:34.447016Z","iopub.status.idle":"2025-02-06T10:35:36.741934Z","shell.execute_reply.started":"2025-02-06T10:35:34.446995Z","shell.execute_reply":"2025-02-06T10:35:36.741324Z"}},"outputs":[{"name":"stderr","text":"/usr/local/lib/python3.10/dist-packages/keras/src/layers/convolutional/base_conv.py:107: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":"\u001b[1mModel: \"sequential_1\"\u001b[0m\n","text/html":"
Model: \"sequential_1\"\n
\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓\n┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩\n│ conv2d_1 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m148\u001b[0m, \u001b[38;5;34m148\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m896\u001b[0m │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m74\u001b[0m, \u001b[38;5;34m74\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ conv2d_2 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m72\u001b[0m, \u001b[38;5;34m72\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m18,496\u001b[0m │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ max_pooling2d_1 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m36\u001b[0m, \u001b[38;5;34m36\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ conv2d_3 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m34\u001b[0m, \u001b[38;5;34m34\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m73,856\u001b[0m │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ max_pooling2d_2 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m17\u001b[0m, \u001b[38;5;34m17\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ conv2d_4 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m15\u001b[0m, \u001b[38;5;34m15\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m147,584\u001b[0m │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ max_pooling2d_3 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m7\u001b[0m, \u001b[38;5;34m7\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ flatten (\u001b[38;5;33mFlatten\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m6272\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ dropout (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m6272\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ dense (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m) │ \u001b[38;5;34m3,211,776\u001b[0m │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ dense_1 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m) │ \u001b[38;5;34m513\u001b[0m │\n└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n","text/html":"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓\n┃ Layer (type)                         ┃ Output Shape                ┃         Param # ┃\n┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩\n│ conv2d_1 (Conv2D)                    │ (None, 148, 148, 32)        │             896 │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ max_pooling2d (MaxPooling2D)         │ (None, 74, 74, 32)          │               0 │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ conv2d_2 (Conv2D)                    │ (None, 72, 72, 64)          │          18,496 │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ max_pooling2d_1 (MaxPooling2D)       │ (None, 36, 36, 64)          │               0 │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ conv2d_3 (Conv2D)                    │ (None, 34, 34, 128)         │          73,856 │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ max_pooling2d_2 (MaxPooling2D)       │ (None, 17, 17, 128)         │               0 │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ conv2d_4 (Conv2D)                    │ (None, 15, 15, 128)         │         147,584 │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ max_pooling2d_3 (MaxPooling2D)       │ (None, 7, 7, 128)           │               0 │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ flatten (Flatten)                    │ (None, 6272)                │               0 │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ dropout (Dropout)                    │ (None, 6272)                │               0 │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ dense (Dense)                        │ (None, 512)                 │       3,211,776 │\n├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n│ dense_1 (Dense)                      │ (None, 1)                   │             513 │\n└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n
\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"\u001b[1m Total params: \u001b[0m\u001b[38;5;34m3,453,121\u001b[0m (13.17 MB)\n","text/html":"
 Total params: 3,453,121 (13.17 MB)\n
\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m3,453,121\u001b[0m (13.17 MB)\n","text/html":"
 Trainable params: 3,453,121 (13.17 MB)\n
\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n","text/html":"
 Non-trainable params: 0 (0.00 B)\n
\n"},"metadata":{}}],"execution_count":10},{"cell_type":"code","source":"from keras import optimizers\n\nmodel.compile(loss='binary_crossentropy',\n optimizer=optimizers.RMSprop(learning_rate=1e-4),\n metrics=['acc'])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-06T10:36:00.376612Z","iopub.execute_input":"2025-02-06T10:36:00.376897Z","iopub.status.idle":"2025-02-06T10:36:00.389079Z","shell.execute_reply.started":"2025-02-06T10:36:00.376876Z","shell.execute_reply":"2025-02-06T10:36:00.388398Z"}},"outputs":[],"execution_count":12},{"cell_type":"code","source":"train_datagen = ImageDataGenerator(rescale=1./255,\n rotation_range = 40,\n width_shift_range = 0.2,\n height_shift_range = 0.2,\n shear_range = 0.2,\n zoom_range = 0.2,\n horizontal_flip = True,)\n\n\n#test_datagen = ImageDataGenerator(rescale=1./255)\n\ntrain_generator = train_datagen.flow_from_directory(train_dir,\n target_size= (150, 150),\n batch_size = 32,\n class_mode = \"binary\")\n\nvalidation_generator = test_datagen.flow_from_directory(validation_dir,\n target_size = (150, 150),\n batch_size = 32,\n class_mode = \"binary\")\n\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-06T10:39:41.641578Z","iopub.execute_input":"2025-02-06T10:39:41.64187Z","iopub.status.idle":"2025-02-06T10:39:41.696299Z","shell.execute_reply.started":"2025-02-06T10:39:41.641848Z","shell.execute_reply":"2025-02-06T10:39:41.695689Z"}},"outputs":[{"name":"stdout","text":"Found 2000 images belonging to 2 classes.\nFound 1000 images belonging to 2 classes.\n","output_type":"stream"}],"execution_count":18},{"cell_type":"code","source":"history = model.fit(train_generator,\n steps_per_epoch = 100,\n epochs = 30,\n validation_data = validation_generator,\n validation_steps=50)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-06T10:41:52.77996Z","iopub.execute_input":"2025-02-06T10:41:52.780301Z","iopub.status.idle":"2025-02-06T10:48:09.279377Z","shell.execute_reply.started":"2025-02-06T10:41:52.780277Z","shell.execute_reply":"2025-02-06T10:48:09.278645Z"}},"outputs":[{"name":"stdout","text":"Epoch 1/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m14s\u001b[0m 130ms/step - acc: 0.5263 - loss: 0.6916 - val_acc: 0.5000 - val_loss: 0.6889\nEpoch 2/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m13s\u001b[0m 115ms/step - acc: 0.5271 - loss: 0.6906 - val_acc: 0.5370 - val_loss: 0.6824\nEpoch 3/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m13s\u001b[0m 112ms/step - acc: 0.5650 - loss: 0.6810 - val_acc: 0.5980 - val_loss: 0.6658\nEpoch 4/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m13s\u001b[0m 112ms/step - acc: 0.5827 - loss: 0.6780 - val_acc: 0.5360 - val_loss: 0.6829\nEpoch 5/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m13s\u001b[0m 114ms/step - acc: 0.5732 - loss: 0.6730 - val_acc: 0.5970 - val_loss: 0.6496\nEpoch 6/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m13s\u001b[0m 113ms/step - acc: 0.5971 - loss: 0.6628 - val_acc: 0.6050 - val_loss: 0.6598\nEpoch 7/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m13s\u001b[0m 113ms/step - acc: 0.5940 - loss: 0.6620 - val_acc: 0.5500 - val_loss: 0.6890\nEpoch 8/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m13s\u001b[0m 113ms/step - acc: 0.5953 - loss: 0.6613 - val_acc: 0.5610 - val_loss: 0.6749\nEpoch 9/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 112ms/step - acc: 0.5936 - loss: 0.6518 - val_acc: 0.6070 - val_loss: 0.6517\nEpoch 10/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 111ms/step - acc: 0.6300 - loss: 0.6441 - val_acc: 0.6160 - val_loss: 0.6403\nEpoch 11/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 111ms/step - acc: 0.6409 - loss: 0.6349 - val_acc: 0.6520 - val_loss: 0.6148\nEpoch 12/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 112ms/step - acc: 0.6247 - loss: 0.6336 - val_acc: 0.6620 - val_loss: 0.6117\nEpoch 13/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 111ms/step - acc: 0.6251 - loss: 0.6345 - val_acc: 0.6640 - val_loss: 0.6012\nEpoch 14/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 112ms/step - acc: 0.6614 - loss: 0.6144 - val_acc: 0.5820 - val_loss: 0.7133\nEpoch 15/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 111ms/step - acc: 0.6694 - loss: 0.6090 - val_acc: 0.6820 - val_loss: 0.5878\nEpoch 16/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 110ms/step - acc: 0.6675 - loss: 0.5954 - val_acc: 0.6520 - val_loss: 0.6026\nEpoch 17/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 112ms/step - acc: 0.6790 - loss: 0.6071 - val_acc: 0.7020 - val_loss: 0.5714\nEpoch 18/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 110ms/step - acc: 0.6676 - loss: 0.6037 - val_acc: 0.6710 - val_loss: 0.5836\nEpoch 19/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 110ms/step - acc: 0.6852 - loss: 0.6001 - val_acc: 0.6910 - val_loss: 0.5665\nEpoch 20/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 111ms/step - acc: 0.6934 - loss: 0.5852 - val_acc: 0.7030 - val_loss: 0.5707\nEpoch 21/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 112ms/step - acc: 0.6786 - loss: 0.5896 - val_acc: 0.7190 - val_loss: 0.5532\nEpoch 22/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 111ms/step - acc: 0.6921 - loss: 0.5880 - val_acc: 0.6920 - val_loss: 0.5645\nEpoch 23/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 111ms/step - acc: 0.7140 - loss: 0.5641 - val_acc: 0.7070 - val_loss: 0.5575\nEpoch 24/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 110ms/step - acc: 0.6919 - loss: 0.5808 - val_acc: 0.6950 - val_loss: 0.5564\nEpoch 25/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m13s\u001b[0m 112ms/step - acc: 0.7032 - loss: 0.5647 - val_acc: 0.7080 - val_loss: 0.5610\nEpoch 26/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 110ms/step - acc: 0.7035 - loss: 0.5696 - val_acc: 0.7090 - val_loss: 0.5599\nEpoch 27/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 111ms/step - acc: 0.7183 - loss: 0.5535 - val_acc: 0.7240 - val_loss: 0.5371\nEpoch 28/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m12s\u001b[0m 110ms/step - acc: 0.7279 - loss: 0.5417 - val_acc: 0.6970 - val_loss: 0.5564\nEpoch 29/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m13s\u001b[0m 112ms/step - acc: 0.7129 - loss: 0.5555 - val_acc: 0.7080 - val_loss: 0.5461\nEpoch 30/30\n\u001b[1m100/100\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m13s\u001b[0m 113ms/step - acc: 0.7210 - loss: 0.5517 - val_acc: 0.7070 - val_loss: 0.5487\n","output_type":"stream"}],"execution_count":22},{"cell_type":"code","source":"model.save('cats_and_dogs.h5')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-06T10:49:19.894002Z","iopub.execute_input":"2025-02-06T10:49:19.89433Z","iopub.status.idle":"2025-02-06T10:49:19.977316Z","shell.execute_reply.started":"2025-02-06T10:49:19.894304Z","shell.execute_reply":"2025-02-06T10:49:19.976586Z"}},"outputs":[],"execution_count":23},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\n# Get the available epochs for training and validation\ntrain_epochs = range(1, len(history.history['acc']) + 1)\nval_epochs = range(1, len(history.history['val_acc']) + 1)\n\n# Plot training accuracy\nplt.plot(train_epochs, history.history['acc'], 'bo', label=\"Training acc\")\n\n# Plot validation accuracy, ensuring matching length\nplt.plot(val_epochs, history.history['val_acc'], 'b', label='Validation acc')\n\nplt.title(\"Training and validation accuracy\")\nplt.legend()\nplt.show()\n\n# Repeat for loss\nplt.figure()\ntrain_epochs_loss = range(1, len(history.history['loss']) + 1)\nval_epochs_loss = range(1, len(history.history['val_loss']) + 1)\n\nplt.plot(train_epochs_loss, history.history['loss'], 'bo', label=\"Training loss\")\nplt.plot(val_epochs_loss, history.history['val_loss'], 'b', label='Validation loss')\n\nplt.title(\"Training and validation loss\")\nplt.legend()\nplt.show()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-06T10:49:36.892478Z","iopub.execute_input":"2025-02-06T10:49:36.892766Z","iopub.status.idle":"2025-02-06T10:49:37.272944Z","shell.execute_reply.started":"2025-02-06T10:49:36.892745Z","shell.execute_reply":"2025-02-06T10:49:37.272257Z"}},"outputs":[{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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\n"},"metadata":{}}],"execution_count":24},{"cell_type":"code","source":"from keras.models import load_model\n\n# Load the trained model\nmodel = load_model('cats_and_dogs.h5')\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-06T10:56:25.919996Z","iopub.execute_input":"2025-02-06T10:56:25.920328Z","iopub.status.idle":"2025-02-06T10:56:26.049031Z","shell.execute_reply.started":"2025-02-06T10:56:25.920304Z","shell.execute_reply":"2025-02-06T10:56:26.048167Z"}},"outputs":[],"execution_count":26},{"cell_type":"code","source":"# Uploading Data \nfile_name = \"/kaggle/input/dogs-vs-cats-redux-kernels-edition/test.zip\"\n\nwith ZipFile(file_name, 'r') as zip:\n zip.extractall()\n print('Done')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-06T10:57:24.872543Z","iopub.execute_input":"2025-02-06T10:57:24.87284Z","iopub.status.idle":"2025-02-06T10:57:30.155539Z","shell.execute_reply.started":"2025-02-06T10:57:24.87282Z","shell.execute_reply":"2025-02-06T10:57:30.154718Z"}},"outputs":[{"name":"stdout","text":"Done\n","output_type":"stream"}],"execution_count":27},{"cell_type":"code","source":"import os\nimport numpy as no\nfrom keras.preprocessing import image\n\ntest_dir = '/kaggle/working/test'\n\ntest_filenames = os.listdir(test_dir)\n# print(test_filenames)\n\nfilenames = []\npredictions = []\n\nfor filename in test_filenames:\n img_path = os.path.join(test_dir, filename)\n\n # Load the preprocess the image:\n img = image.load_img(img_path, target_size=(150, 150))\n img_array = image.img_to_array(img) / 255.0 \n img_arry = np.expand_dims(img_array, axis = 0)\n\n # predict:\n prediction = model.predict(img_array)\n label = 1 if prediction[0] > 0.5 else 0 \n\n\n # Append:\n filenames.append(filename)\n predictions.append(label)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-06T11:07:06.636567Z","iopub.execute_input":"2025-02-06T11:07:06.636858Z","iopub.status.idle":"2025-02-06T11:07:06.715201Z","shell.execute_reply.started":"2025-02-06T11:07:06.636837Z","shell.execute_reply":"2025-02-06T11:07:06.714022Z"}},"outputs":[{"traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)","\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 20\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 21\u001b[0m \u001b[0;31m# predict:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 22\u001b[0;31m \u001b[0mprediction\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mimg_array\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 23\u001b[0m \u001b[0mlabel\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m1\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mprediction\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m>\u001b[0m \u001b[0;36m0.5\u001b[0m \u001b[0;32melse\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 24\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.10/dist-packages/keras/src/utils/traceback_utils.py\u001b[0m in \u001b[0;36merror_handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 120\u001b[0m \u001b[0;31m# To get the full stack trace, call:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 121\u001b[0m \u001b[0;31m# `keras.config.disable_traceback_filtering()`\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 122\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwith_traceback\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfiltered_tb\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 123\u001b[0m \u001b[0;32mfinally\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 124\u001b[0m \u001b[0;32mdel\u001b[0m \u001b[0mfiltered_tb\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;32m/usr/local/lib/python3.10/dist-packages/keras/src/models/functional.py\u001b[0m in \u001b[0;36m_adjust_input_rank\u001b[0;34m(self, flat_inputs)\u001b[0m\n\u001b[1;32m 242\u001b[0m \u001b[0madjusted\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mops\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexpand_dims\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m-\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 243\u001b[0m \u001b[0;32mcontinue\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 244\u001b[0;31m raise ValueError(\n\u001b[0m\u001b[1;32m 245\u001b[0m \u001b[0;34mf\"Invalid input shape for input {x}. Expected shape \"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 246\u001b[0m \u001b[0;34mf\"{ref_shape}, but input has incompatible shape {x.shape}\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n","\u001b[0;31mValueError\u001b[0m: Exception encountered when calling Sequential.call().\n\n\u001b[1mInvalid input shape for input Tensor(\"data:0\", shape=(32, 150, 3), dtype=float32). Expected shape (None, 150, 150, 3), but input has incompatible shape (32, 150, 3)\u001b[0m\n\nArguments received by Sequential.call():\n • inputs=tf.Tensor(shape=(32, 150, 3), dtype=float32)\n • training=False\n • mask=None"],"ename":"ValueError","evalue":"Exception encountered when calling Sequential.call().\n\n\u001b[1mInvalid input shape for input Tensor(\"data:0\", shape=(32, 150, 3), dtype=float32). Expected shape (None, 150, 150, 3), but input has incompatible shape (32, 150, 3)\u001b[0m\n\nArguments received by Sequential.call():\n • inputs=tf.Tensor(shape=(32, 150, 3), dtype=float32)\n • training=False\n • mask=None","output_type":"error"}],"execution_count":32},{"cell_type":"code","source":"","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-06T11:07:03.424164Z","iopub.execute_input":"2025-02-06T11:07:03.424516Z","iopub.status.idle":"2025-02-06T11:07:03.428957Z","shell.execute_reply.started":"2025-02-06T11:07:03.42449Z","shell.execute_reply":"2025-02-06T11:07:03.428102Z"}},"outputs":[],"execution_count":31},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}