{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "8d79b30e", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Keras version: 3.10.0\n", "\n", "TensorFlow version: 2.19.0\n" ] } ], "source": [ "import os\n", "import matplotlib.pyplot as plt\n", "import tensorflow as tf\n", "from tensorflow import keras\n", "from tensorflow.keras.models import Sequential\n", "from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense,Dropout,BatchNormalization\n", "from tensorflow.keras import regularizers\n", "from tensorflow.keras.optimizers import Adam, RMSprop, SGD\n", "\n", "print('Keras version: ',keras.__version__)\n", "print()\n", "print('TensorFlow version: ',tf.__version__)" ] }, { "cell_type": "code", "execution_count": 2, "id": "65762078", "metadata": {}, "outputs": [ { "ename": "FileNotFoundError", "evalue": "[WinError 3] The system cannot find the path specified: './dataset/train'", "output_type": "error", "traceback": [ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[1;31mFileNotFoundError\u001b[0m Traceback (most recent call last)", "Cell \u001b[1;32mIn[2], line 9\u001b[0m\n\u001b[0;32m 4\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mkeras\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mpreprocessing\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mimage\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m ImageDataGenerator, load_img\n\u001b[0;32m 5\u001b[0m train_datagen \u001b[38;5;241m=\u001b[39m ImageDataGenerator(rescale\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m1.\u001b[39m\u001b[38;5;241m/\u001b[39m\u001b[38;5;241m255\u001b[39m,\n\u001b[0;32m 6\u001b[0m zoom_range\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m0.3\u001b[39m,\n\u001b[0;32m 7\u001b[0m horizontal_flip\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[1;32m----> 9\u001b[0m training_set \u001b[38;5;241m=\u001b[39m train_datagen\u001b[38;5;241m.\u001b[39mflow_from_directory(train_dir,\n\u001b[0;32m 10\u001b[0m batch_size\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m64\u001b[39m,\n\u001b[0;32m 11\u001b[0m target_size\u001b[38;5;241m=\u001b[39m(\u001b[38;5;241m48\u001b[39m,\u001b[38;5;241m48\u001b[39m),\n\u001b[0;32m 12\u001b[0m shuffle\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m,\n\u001b[0;32m 13\u001b[0m color_mode\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mgrayscale\u001b[39m\u001b[38;5;124m'\u001b[39m,\n\u001b[0;32m 14\u001b[0m class_mode\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mcategorical\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m 16\u001b[0m validation_datagen \u001b[38;5;241m=\u001b[39m ImageDataGenerator(rescale\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m1.\u001b[39m\u001b[38;5;241m/\u001b[39m\u001b[38;5;241m255\u001b[39m)\n\u001b[0;32m 17\u001b[0m validation_set \u001b[38;5;241m=\u001b[39m validation_datagen\u001b[38;5;241m.\u001b[39mflow_from_directory(test_dir,\n\u001b[0;32m 18\u001b[0m batch_size\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m64\u001b[39m,\n\u001b[0;32m 19\u001b[0m target_size\u001b[38;5;241m=\u001b[39m(\u001b[38;5;241m48\u001b[39m,\u001b[38;5;241m48\u001b[39m),\n\u001b[0;32m 20\u001b[0m shuffle\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m,\n\u001b[0;32m 21\u001b[0m color_mode\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mgrayscale\u001b[39m\u001b[38;5;124m'\u001b[39m,\n\u001b[0;32m 22\u001b[0m class_mode\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mcategorical\u001b[39m\u001b[38;5;124m'\u001b[39m)\n", "File \u001b[1;32m~\\AppData\\Roaming\\Python\\Python312\\site-packages\\keras\\src\\legacy\\preprocessing\\image.py:1138\u001b[0m, in \u001b[0;36mImageDataGenerator.flow_from_directory\u001b[1;34m(self, directory, target_size, color_mode, classes, class_mode, batch_size, shuffle, seed, save_to_dir, save_prefix, save_format, follow_links, subset, interpolation, keep_aspect_ratio)\u001b[0m\n\u001b[0;32m 1120\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mflow_from_directory\u001b[39m(\n\u001b[0;32m 1121\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[0;32m 1122\u001b[0m directory,\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 1136\u001b[0m keep_aspect_ratio\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[0;32m 1137\u001b[0m ):\n\u001b[1;32m-> 1138\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m DirectoryIterator(\n\u001b[0;32m 1139\u001b[0m directory,\n\u001b[0;32m 1140\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[0;32m 1141\u001b[0m target_size\u001b[38;5;241m=\u001b[39mtarget_size,\n\u001b[0;32m 1142\u001b[0m color_mode\u001b[38;5;241m=\u001b[39mcolor_mode,\n\u001b[0;32m 1143\u001b[0m keep_aspect_ratio\u001b[38;5;241m=\u001b[39mkeep_aspect_ratio,\n\u001b[0;32m 1144\u001b[0m classes\u001b[38;5;241m=\u001b[39mclasses,\n\u001b[0;32m 1145\u001b[0m class_mode\u001b[38;5;241m=\u001b[39mclass_mode,\n\u001b[0;32m 1146\u001b[0m data_format\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdata_format,\n\u001b[0;32m 1147\u001b[0m batch_size\u001b[38;5;241m=\u001b[39mbatch_size,\n\u001b[0;32m 1148\u001b[0m shuffle\u001b[38;5;241m=\u001b[39mshuffle,\n\u001b[0;32m 1149\u001b[0m seed\u001b[38;5;241m=\u001b[39mseed,\n\u001b[0;32m 1150\u001b[0m save_to_dir\u001b[38;5;241m=\u001b[39msave_to_dir,\n\u001b[0;32m 1151\u001b[0m save_prefix\u001b[38;5;241m=\u001b[39msave_prefix,\n\u001b[0;32m 1152\u001b[0m save_format\u001b[38;5;241m=\u001b[39msave_format,\n\u001b[0;32m 1153\u001b[0m follow_links\u001b[38;5;241m=\u001b[39mfollow_links,\n\u001b[0;32m 1154\u001b[0m subset\u001b[38;5;241m=\u001b[39msubset,\n\u001b[0;32m 1155\u001b[0m interpolation\u001b[38;5;241m=\u001b[39minterpolation,\n\u001b[0;32m 1156\u001b[0m dtype\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdtype,\n\u001b[0;32m 1157\u001b[0m )\n", "File \u001b[1;32m~\\AppData\\Roaming\\Python\\Python312\\site-packages\\keras\\src\\legacy\\preprocessing\\image.py:453\u001b[0m, in \u001b[0;36mDirectoryIterator.__init__\u001b[1;34m(self, directory, image_data_generator, target_size, color_mode, classes, class_mode, batch_size, shuffle, seed, data_format, save_to_dir, save_prefix, save_format, follow_links, subset, interpolation, keep_aspect_ratio, dtype)\u001b[0m\n\u001b[0;32m 451\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m classes:\n\u001b[0;32m 452\u001b[0m classes \u001b[38;5;241m=\u001b[39m []\n\u001b[1;32m--> 453\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m subdir \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28msorted\u001b[39m(os\u001b[38;5;241m.\u001b[39mlistdir(directory)):\n\u001b[0;32m 454\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39misdir(os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mjoin(directory, subdir)):\n\u001b[0;32m 455\u001b[0m classes\u001b[38;5;241m.\u001b[39mappend(subdir)\n", "\u001b[1;31mFileNotFoundError\u001b[0m: [WinError 3] The system cannot find the path specified: './dataset/train'" ] } ], "source": [ "train_dir = \"./dataset/train\" \n", "test_dir = \"./dataset/test\" \n", "\n", "from tensorflow.keras.preprocessing.image import ImageDataGenerator, load_img\n", "train_datagen = ImageDataGenerator(rescale=1./255,\n", " zoom_range=0.3,\n", " horizontal_flip=True)\n", "\n", "training_set = train_datagen.flow_from_directory(train_dir,\n", " batch_size=64,\n", " target_size=(48,48),\n", " shuffle=True,\n", " color_mode='grayscale',\n", " class_mode='categorical')\n", "\n", "validation_datagen = ImageDataGenerator(rescale=1./255)\n", "validation_set = validation_datagen.flow_from_directory(test_dir,\n", " batch_size=64,\n", " target_size=(48,48),\n", " shuffle=True,\n", " color_mode='grayscale',\n", " class_mode='categorical')" ] }, { "cell_type": "code", "execution_count": null, "id": "90f718a2", "metadata": {}, "outputs": [], "source": [ "model = Sequential([\n", " Conv2D(32, (3, 3), activation='tanh', input_shape=(48, 48,1)),\n", " MaxPooling2D(pool_size=(2, 2)),\n", " Flatten(),\n", " Dense(7, activation='softmax')\n", "])\n", "\n", "model.summary()" ] }, { "cell_type": "code", "execution_count": null, "id": "29ad3559", "metadata": {}, "outputs": [], "source": [ "model.compile(optimizer=Adam(learning_rate=0.0001), \n", " loss='categorical_crossentropy', \n", " metrics=['accuracy'])\n", " \n", "#model.compile(optimizer=keras.optimizers.SGD(lr=0.001),\n", "# loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),\n", "# metrics=['accuracy'])\n", "\n", "#model.compile(loss='sparse_categorical_crossentropy',optimizer='sgd',metrics=[\"accuracy\"])" ] }, { "cell_type": "code", "execution_count": null, "id": "de9144a8", "metadata": {}, "outputs": [], "source": [ "root_logdir = os.path.join(os.curdir,\"my_newlogs2\")\n", "def get_run_logdir():\n", " import time\n", " run_id=time.strftime(\"run_%Y_%m_%d_%H_%M_%S\")\n", " return os.path.join(root_logdir,run_id)\n", "logdir=get_run_logdir()\n", "logdir" ] }, { "cell_type": "code", "execution_count": null, "id": "f8cafcab", "metadata": {}, "outputs": [], "source": [ "#create a tensorboard callback function that makes use of folder logger\n", "tensorboard_cb=keras.callbacks.TensorBoard(logdir)\n", "\n", "#create checkpoint callback that saves every epoch\n", "checkpoint_cb = keras.callbacks.ModelCheckpoint(\"MLP_model.h5\",\n", " save_best_only=True, verbose=1,mode='min', moniter='val_loss')\n", "\n", "#create early stopping callback\n", "\n", "early_stopping_cb = keras.callbacks.EarlyStopping(monitor='val_loss', \n", " min_delta=0, \n", " patience=3, \n", " verbose=1,\n", " restore_best_weights=True)\n", "\n", "steps_per_epoch = training_set.n // training_set.batch_size\n", "validation_steps = validation_set.n // validation_set.batch_size\n", "\n", "history = model.fit(x=training_set,\n", " validation_data=validation_set,\n", " epochs= 60,\n", " callbacks=[tensorboard_cb,\n", " checkpoint_cb, early_stopping_cb],\n", " steps_per_epoch=steps_per_epoch,\n", " validation_steps=validation_steps)" ] }, { "cell_type": "code", "execution_count": null, "id": "6b52c7cc", "metadata": {}, "outputs": [], "source": [ "def plot_history(history):\n", " acc = history.history[\"accuracy\"]\n", " loss = history.history[\"loss\"]\n", " val_loss = history.history[\"val_loss\"]\n", " val_accuracy = history.history[\"val_accuracy\"]\n", " \n", " x = range(1, len(acc) + 1)\n", " \n", " plt.figure(figsize=(12,5))\n", " plt.subplot(1, 2, 1)\n", " plt.plot(x, acc, \"b\", label=\"traning_acc\")\n", " plt.plot(x, val_accuracy, \"r\", label=\"traning_acc\")\n", " plt.title(\"Accuracy\")\n", " \n", " plt.subplot(1, 2, 2)\n", " plt.plot(x, loss, \"b\", label=\"traning_acc\")\n", " plt.plot(x, val_loss, \"r\", label=\"traning_acc\")\n", " plt.title(\"Loss\")\n", " \n", "plot_history(history)" ] }, { "cell_type": "code", "execution_count": null, "id": "aec6b30a", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.12.7" } }, "nbformat": 4, "nbformat_minor": 5 }