04_VGG-16_with_augmentation.ipynb

{"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"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Import relevant libraries and load dataset","metadata":{}},{"cell_type":"code","source":"import warnings\nwarnings.filterwarnings(\"ignore\")\nimport os\nfrom keras.preprocessing.image import ImageDataGenerator\nimport tensorflow as tf\nfrom tensorflow.keras.applications import VGG16\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.layers import Flatten, Conv2D, BatchNormalization, Dropout, Dense\nfrom tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint, ReduceLROnPlateau\nimport matplotlib.pyplot as plt\nfrom sklearn.metrics import confusion_matrix\nimport numpy as np\nimport seaborn as sns","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2023-08-05T14:54:19.149000Z","iopub.execute_input":"2023-08-05T14:54:19.149607Z","iopub.status.idle":"2023-08-05T14:54:29.132696Z","shell.execute_reply.started":"2023-08-05T14:54:19.149561Z","shell.execute_reply":"2023-08-05T14:54:29.131697Z"},"trusted":true},"execution_count":1,"outputs":[]},{"cell_type":"code","source":"# generate batches of tensor image data with real-time data augmentation\n\ndatagen = ImageDataGenerator(rescale=1./255,\n                            shear_range=0.2,\n                            zoom_range=0.2,\n                             horizontal_flip=True,\n                             validation_split=0.2)\n\ntrain_generator = datagen.flow_from_directory(\n\"/kaggle/input/kermany2018/OCT2017 /train\",\ntarget_size = (224, 224),\nbatch_size = 128,\nclass_mode = \"categorical\",\nsubset = \"training\")\n\nvalidation_generator = datagen.flow_from_directory(\n\"/kaggle/input/kermany2018/OCT2017 /train\",\ntarget_size = (224, 224),\nbatch_size = 128,\nclass_mode = \"categorical\",\nsubset = \"validation\")","metadata":{"execution":{"iopub.status.busy":"2023-08-05T14:54:29.134165Z","iopub.execute_input":"2023-08-05T14:54:29.134791Z","iopub.status.idle":"2023-08-05T14:55:50.901109Z","shell.execute_reply.started":"2023-08-05T14:54:29.134756Z","shell.execute_reply":"2023-08-05T14:55:50.900151Z"},"trusted":true},"execution_count":2,"outputs":[{"name":"stdout","text":"Found 66788 images belonging to 4 classes.\nFound 16696 images belonging to 4 classes.\n","output_type":"stream"}]},{"cell_type":"code","source":"vgg16_model = VGG16(include_top=False, weights=\"imagenet\", pooling=None,input_shape=(224, 224, 3))","metadata":{"execution":{"iopub.status.busy":"2023-08-05T14:55:50.903630Z","iopub.execute_input":"2023-08-05T14:55:50.905249Z","iopub.status.idle":"2023-08-05T14:55:54.785685Z","shell.execute_reply.started":"2023-08-05T14:55:50.905214Z","shell.execute_reply":"2023-08-05T14:55:54.784649Z"},"trusted":true},"execution_count":3,"outputs":[{"name":"stdout","text":"Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/vgg16/vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5\n58889256/58889256 [==============================] - 0s 0us/step\n","output_type":"stream"}]},{"cell_type":"code","source":"for layer in vgg16_model.layers:\n    layer.trainable = False","metadata":{"execution":{"iopub.status.busy":"2023-08-05T14:55:54.787557Z","iopub.execute_input":"2023-08-05T14:55:54.788186Z","iopub.status.idle":"2023-08-05T14:55:54.795065Z","shell.execute_reply.started":"2023-08-05T14:55:54.788140Z","shell.execute_reply":"2023-08-05T14:55:54.793939Z"},"trusted":true},"execution_count":4,"outputs":[]},{"cell_type":"code","source":"vgg16_model.summary()","metadata":{"execution":{"iopub.status.busy":"2023-08-05T14:55:54.796633Z","iopub.execute_input":"2023-08-05T14:55:54.797091Z","iopub.status.idle":"2023-08-05T14:55:54.845488Z","shell.execute_reply.started":"2023-08-05T14:55:54.797059Z","shell.execute_reply":"2023-08-05T14:55:54.844708Z"},"trusted":true},"execution_count":5,"outputs":[{"name":"stdout","text":"Model: \"vgg16\"\n_________________________________________________________________\n Layer (type)                Output Shape              Param #   \n=================================================================\n input_1 (InputLayer)        [(None, 224, 224, 3)]     0         \n                                                                 \n block1_conv1 (Conv2D)       (None, 224, 224, 64)      1792      \n                                                                 \n block1_conv2 (Conv2D)       (None, 224, 224, 64)      36928     \n                                                                 \n block1_pool (MaxPooling2D)  (None, 112, 112, 64)      0         \n                                                                 \n block2_conv1 (Conv2D)       (None, 112, 112, 128)     73856     \n                                                                 \n block2_conv2 (Conv2D)       (None, 112, 112, 128)     147584    \n                                                                 \n block2_pool (MaxPooling2D)  (None, 56, 56, 128)       0         \n                                                                 \n block3_conv1 (Conv2D)       (None, 56, 56, 256)       295168    \n                                                                 \n block3_conv2 (Conv2D)       (None, 56, 56, 256)       590080    \n                                                                 \n block3_conv3 (Conv2D)       (None, 56, 56, 256)       590080    \n                                                                 \n block3_pool (MaxPooling2D)  (None, 28, 28, 256)       0         \n                                                                 \n block4_conv1 (Conv2D)       (None, 28, 28, 512)       1180160   \n                                                                 \n block4_conv2 (Conv2D)       (None, 28, 28, 512)       2359808   \n                                                                 \n block4_conv3 (Conv2D)       (None, 28, 28, 512)       2359808   \n                                                                 \n block4_pool (MaxPooling2D)  (None, 14, 14, 512)       0         \n                                                                 \n block5_conv1 (Conv2D)       (None, 14, 14, 512)       2359808   \n                                                                 \n block5_conv2 (Conv2D)       (None, 14, 14, 512)       2359808   \n                                                                 \n block5_conv3 (Conv2D)       (None, 14, 14, 512)       2359808   \n                                                                 \n block5_pool (MaxPooling2D)  (None, 7, 7, 512)         0         \n                                                                 \n=================================================================\nTotal params: 14,714,688\nTrainable params: 0\nNon-trainable params: 14,714,688\n_________________________________________________________________\n","output_type":"stream"}]},{"cell_type":"code","source":"# Flatten Layer\nflatten = Flatten()(vgg16_model.output)\n\n# Dense Layer\nDense1 = Dense(256, activation=\"relu\")(flatten)\n\n# Batch Normalization\nBatchNormalization = BatchNormalization()(Dense1)\n\n# Dropout Layer\ndropout = Dropout(rate=0.5)(BatchNormalization)\n\n# Dense Layer\nDense2 = Dense(128, activation=\"relu\")(dropout)\n\n# Dropout Layer\ndropout = Dropout(rate=0.5)(Dense2)\n\n# Dense Layer\nDense3 = Dense(16, activation=\"relu\")(dropout)\n\n# Dense Layer\nOutput_Layer = Dense(4, activation=\"softmax\")(Dense3)\n\n# Creating a model\nmodel3 = Model(inputs=vgg16_model.input,outputs=Output_Layer)","metadata":{"execution":{"iopub.status.busy":"2023-08-05T14:55:54.846554Z","iopub.execute_input":"2023-08-05T14:55:54.847148Z","iopub.status.idle":"2023-08-05T14:55:54.957028Z","shell.execute_reply.started":"2023-08-05T14:55:54.847112Z","shell.execute_reply":"2023-08-05T14:55:54.956062Z"},"trusted":true},"execution_count":6,"outputs":[]},{"cell_type":"code","source":"model3.summary()","metadata":{"execution":{"iopub.status.busy":"2023-08-05T14:55:54.958505Z","iopub.execute_input":"2023-08-05T14:55:54.958878Z","iopub.status.idle":"2023-08-05T14:55:55.013539Z","shell.execute_reply.started":"2023-08-05T14:55:54.958845Z","shell.execute_reply":"2023-08-05T14:55:55.012748Z"},"trusted":true},"execution_count":7,"outputs":[{"name":"stdout","text":"Model: \"model\"\n_________________________________________________________________\n Layer (type)                Output Shape              Param #   \n=================================================================\n input_1 (InputLayer)        [(None, 224, 224, 3)]     0         \n                                                                 \n block1_conv1 (Conv2D)       (None, 224, 224, 64)      1792      \n                                                                 \n block1_conv2 (Conv2D)       (None, 224, 224, 64)      36928     \n                                                                 \n block1_pool (MaxPooling2D)  (None, 112, 112, 64)      0         \n                                                                 \n block2_conv1 (Conv2D)       (None, 112, 112, 128)     73856     \n                                                                 \n block2_conv2 (Conv2D)       (None, 112, 112, 128)     147584    \n                                                                 \n block2_pool (MaxPooling2D)  (None, 56, 56, 128)       0         \n                                                                 \n block3_conv1 (Conv2D)       (None, 56, 56, 256)       295168    \n                                                                 \n block3_conv2 (Conv2D)       (None, 56, 56, 256)       590080    \n                                                                 \n block3_conv3 (Conv2D)       (None, 56, 56, 256)       590080    \n                                                                 \n block3_pool (MaxPooling2D)  (None, 28, 28, 256)       0         \n                                                                 \n block4_conv1 (Conv2D)       (None, 28, 28, 512)       1180160   \n                                                                 \n block4_conv2 (Conv2D)       (None, 28, 28, 512)       2359808   \n                                                                 \n block4_conv3 (Conv2D)       (None, 28, 28, 512)       2359808   \n                                                                 \n block4_pool (MaxPooling2D)  (None, 14, 14, 512)       0         \n                                                                 \n block5_conv1 (Conv2D)       (None, 14, 14, 512)       2359808   \n                                                                 \n block5_conv2 (Conv2D)       (None, 14, 14, 512)       2359808   \n                                                                 \n block5_conv3 (Conv2D)       (None, 14, 14, 512)       2359808   \n                                                                 \n block5_pool (MaxPooling2D)  (None, 7, 7, 512)         0         \n                                                                 \n flatten (Flatten)           (None, 25088)             0         \n                                                                 \n dense (Dense)               (None, 256)               6422784   \n                                                                 \n batch_normalization (BatchN  (None, 256)              1024      \n ormalization)                                                   \n                                                                 \n dropout (Dropout)           (None, 256)               0         \n                                                                 \n dense_1 (Dense)             (None, 128)               32896     \n                                                                 \n dropout_1 (Dropout)         (None, 128)               0         \n                                                                 \n dense_2 (Dense)             (None, 16)                2064      \n                                                                 \n dense_3 (Dense)             (None, 4)                 68        \n                                                                 \n=================================================================\nTotal params: 21,173,524\nTrainable params: 6,458,324\nNon-trainable params: 14,715,200\n_________________________________________________________________\n","output_type":"stream"}]},{"cell_type":"code","source":"earlystop = EarlyStopping(monitor='val_accuracy', min_delta=0, patience=3, verbose=1)\n\n# Creating model3_with_augmentation_save folder before running the code.\nfilepath=\"vgg_16_model4_with_augmentation_save/weights-{epoch:02d}-{val_accuracy:.4f}.hdf5\"\ncheckpoint = ModelCheckpoint(filepath=filepath, monitor='val_accuracy',verbose=1, save_best_only=True, mode='max')\n\n# Callbacks\noptimizer = tf.keras.optimizers.Adam()\nmodel3.compile(optimizer=optimizer,loss=\"categorical_crossentropy\",metrics=[\"accuracy\"])\n\n# Creating a list with all the callbacks we want\ncallback_list = [earlystop, checkpoint]\n\ntrain_samples = 66788\nvalidation_samples = 16696\nbatch_size = 128\nmodel3.fit(train_generator, validation_data= validation_generator, steps_per_epoch=train_samples//batch_size, callbacks=callback_list, epochs=50)","metadata":{"execution":{"iopub.status.busy":"2023-08-05T14:55:55.016283Z","iopub.execute_input":"2023-08-05T14:55:55.017001Z","iopub.status.idle":"2023-08-05T17:25:57.040779Z","shell.execute_reply.started":"2023-08-05T14:55:55.016953Z","shell.execute_reply":"2023-08-05T17:25:57.039651Z"},"trusted":true},"execution_count":8,"outputs":[{"name":"stdout","text":"Epoch 1/50\n521/521 [==============================] - ETA: 0s - loss: 0.5961 - accuracy: 0.7869\nEpoch 1: val_accuracy improved from -inf to 0.86943, saving model to vgg_16_model4_with_augmentation_save/weights-01-0.8694.hdf5\n521/521 [==============================] - 1647s 3s/step - loss: 0.5961 - accuracy: 0.7869 - val_loss: 0.3673 - val_accuracy: 0.8694\nEpoch 2/50\n521/521 [==============================] - ETA: 0s - loss: 0.4112 - accuracy: 0.8526\nEpoch 2: val_accuracy improved from 0.86943 to 0.87913, saving model to vgg_16_model4_with_augmentation_save/weights-02-0.8791.hdf5\n521/521 [==============================] - 1234s 2s/step - loss: 0.4112 - accuracy: 0.8526 - val_loss: 0.3494 - val_accuracy: 0.8791\nEpoch 3/50\n521/521 [==============================] - ETA: 0s - loss: 0.3759 - accuracy: 0.8664\nEpoch 3: val_accuracy did not improve from 0.87913\n521/521 [==============================] - 1239s 2s/step - loss: 0.3759 - accuracy: 0.8664 - val_loss: 0.3415 - val_accuracy: 0.8754\nEpoch 4/50\n521/521 [==============================] - ETA: 0s - loss: 0.3557 - accuracy: 0.8755\nEpoch 4: val_accuracy improved from 0.87913 to 0.89393, saving model to vgg_16_model4_with_augmentation_save/weights-04-0.8939.hdf5\n521/521 [==============================] - 1204s 2s/step - loss: 0.3557 - accuracy: 0.8755 - val_loss: 0.3060 - val_accuracy: 0.8939\nEpoch 5/50\n521/521 [==============================] - ETA: 0s - loss: 0.3354 - accuracy: 0.8801\nEpoch 5: val_accuracy did not improve from 0.89393\n521/521 [==============================] - 1196s 2s/step - loss: 0.3354 - accuracy: 0.8801 - val_loss: 0.7527 - val_accuracy: 0.7344\nEpoch 6/50\n521/521 [==============================] - ETA: 0s - loss: 0.3289 - accuracy: 0.8841\nEpoch 6: val_accuracy did not improve from 0.89393\n521/521 [==============================] - 1181s 2s/step - loss: 0.3289 - accuracy: 0.8841 - val_loss: 0.3246 - val_accuracy: 0.8849\nEpoch 7/50\n521/521 [==============================] - ETA: 0s - loss: 0.3172 - accuracy: 0.8886\nEpoch 7: val_accuracy did not improve from 0.89393\n521/521 [==============================] - 1209s 2s/step - loss: 0.3172 - accuracy: 0.8886 - val_loss: 0.3137 - val_accuracy: 0.8876\nEpoch 7: early stopping\n","output_type":"stream"},{"execution_count":8,"output_type":"execute_result","data":{"text/plain":"<keras.callbacks.History at 0x7d18d014db40>"},"metadata":{}}]},{"cell_type":"code","source":"# Plot training & validation acc values\nplt.figure(figsize=(30, 5))\nplt.subplot(121)\nplt.plot(model3.history.history['accuracy'])\nplt.plot(model3.history.history['val_accuracy'])\nplt.title('Model Accuracy')\nplt.ylabel('Accuracy')\nplt.xlabel('Epoch')\nplt.legend(['Train', 'Test'], loc='upper left')\n\n# Plot training & validation loss values\nplt.subplot(122)\nplt.plot(model3.history.history['loss'])\nplt.plot(model3.history.history['val_loss'])\nplt.title('Model loss')\nplt.ylabel('Loss')\nplt.xlabel('Epoch')\nplt.legend(['Train', 'Test'], loc='upper left')\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-08-05T17:25:57.042463Z","iopub.execute_input":"2023-08-05T17:25:57.042844Z","iopub.status.idle":"2023-08-05T17:25:57.710640Z","shell.execute_reply.started":"2023-08-05T17:25:57.042810Z","shell.execute_reply":"2023-08-05T17:25:57.709717Z"},"trusted":true},"execution_count":9,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 3000x500 with 2 Axes>","image/png":"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"},"metadata":{}}]},{"cell_type":"code","source":"# Accuracy on test dataset\n\ntest_generator = datagen.flow_from_directory(\n    \"/kaggle/input/kermany2018/OCT2017 /test\",\n    target_size = (224, 224),\n    batch_size=128,\n    class_mode = \"categorical\",\n    shuffle = False)\ntest_samples = 968\nbatch_size = 128\n\nresult = model3.evaluate(test_generator, steps = test_samples // batch_size+1, verbose = 1)\nprint(\"Accuracy on Test Dataset:{0}, Loss on Test Dataset: {1}\".format(result[1]*100,result[0]))","metadata":{"execution":{"iopub.status.busy":"2023-08-05T17:25:57.714949Z","iopub.execute_input":"2023-08-05T17:25:57.717226Z","iopub.status.idle":"2023-08-05T17:26:23.803510Z","shell.execute_reply.started":"2023-08-05T17:25:57.717190Z","shell.execute_reply":"2023-08-05T17:26:23.802475Z"},"trusted":true},"execution_count":10,"outputs":[{"name":"stdout","text":"Found 968 images belonging to 4 classes.\n8/8 [==============================] - 23s 3s/step - loss: 0.2463 - accuracy: 0.9039\nAccuracy on Test Dataset:90.39255976676941, Loss on Test Dataset: 0.2462962567806244\n","output_type":"stream"}]},{"cell_type":"code","source":"# predicted values\ny_pred = model3.predict(test_generator, test_samples // batch_size+1)\npredicted_values = np.argmax(y_pred, axis=1)\n\nconfusionmatrix = confusion_matrix(test_generator.classes,predicted_values)\nplt.title(\"VGG16 Transfer Learning with Image Augmentation\")\nsns.heatmap(confusionmatrix, annot=True, cmap=\"YlGnBu\")\nplt.xlabel('Predicted Values')\nplt.ylabel('Actual Values')\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-08-05T17:26:23.805190Z","iopub.execute_input":"2023-08-05T17:26:23.805935Z","iopub.status.idle":"2023-08-05T17:26:39.500569Z","shell.execute_reply.started":"2023-08-05T17:26:23.805900Z","shell.execute_reply":"2023-08-05T17:26:39.499625Z"},"trusted":true},"execution_count":11,"outputs":[{"name":"stdout","text":"8/8 [==============================] - 14s 2s/step\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":"<Figure size 640x480 with 2 Axes>","image/png":"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"},"metadata":{}}]}]}