diff --git "a/data/model/cnn.ipynb" "b/data/model/cnn.ipynb"
new file mode 100644--- /dev/null
+++ "b/data/model/cnn.ipynb"
@@ -0,0 +1,576 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "id": "ab9cb1f2-9fa8-4f78-b35a-bca831d983eb",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import os\n",
+ "import matplotlib.pyplot as plt\n",
+ "\n",
+ "from tensorflow.keras.optimizers import Adam\n",
+ "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
+ "\n",
+ "from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout\n",
+ "from tensorflow.keras.models import Sequential\n",
+ "\n",
+ "from tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "id": "cbcf8842-1b02-4d24-921a-a371832bfc8e",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Found 1274 images belonging to 5 classes.\n"
+ ]
+ }
+ ],
+ "source": [
+ "img_width=256; img_height=256\n",
+ "batch_size=16\n",
+ "TRAINING_DIR = '../../weather_pred/Data/training/'\n",
+ "train_datagen = ImageDataGenerator(rescale = 1/255.0,\n",
+ " rotation_range=30,\n",
+ " zoom_range=0.4,\n",
+ " horizontal_flip=True\n",
+ "\t\t\t\t\t\t\t\t )\n",
+ "train_generator = train_datagen.flow_from_directory(TRAINING_DIR,\n",
+ " batch_size=batch_size,\n",
+ " class_mode='categorical',\n",
+ " target_size=(img_height, img_width))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "id": "d0b74405-fd6d-4170-b755-c3ce870de51b",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Found 226 images belonging to 5 classes.\n"
+ ]
+ }
+ ],
+ "source": [
+ "VALIDATION_DIR = '../../weather_pred/Data/validation/'\n",
+ "validation_datagen = ImageDataGenerator(rescale = 1/255.0)\n",
+ "validation_generator = validation_datagen.flow_from_directory(VALIDATION_DIR,\n",
+ " batch_size=batch_size,\n",
+ " class_mode='categorical',\n",
+ " target_size=(img_height, img_width)\n",
+ " )"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "id": "d3e97d78-ee4f-46ce-97c0-4e8e06824f7f",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "callbacks = EarlyStopping(monitor='val_loss', patience=5, verbose=1, mode='auto')\n",
+ "# autosave best Model\n",
+ "best_model_file = '../CNN_aug_drop25_best_weights_256.keras'\n",
+ "best_model = ModelCheckpoint(best_model_file, monitor='val_acc', verbose = 1, save_best_only = True)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "id": "5e742430-27df-4c58-97a2-d535138ed358",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "C:\\Users\\akhyar\\AppData\\Roaming\\Python\\Python311\\site-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"
+ ]
+ }
+ ],
+ "source": [
+ "model = Sequential([\n",
+ " Conv2D(16, (3, 3), activation='relu', input_shape=(img_height, img_width, 3)),\n",
+ " MaxPooling2D(2, 2),\n",
+ " \n",
+ " Conv2D(32, (3, 3), activation='relu'),\n",
+ " MaxPooling2D(2, 2),\n",
+ " \n",
+ " Conv2D(64, (3, 3), activation='relu'),\n",
+ " Conv2D(64, (3, 3), activation='relu'),\n",
+ " MaxPooling2D(2, 2),\n",
+ "\t\n",
+ " Conv2D(128, (3, 3), activation='relu'),\n",
+ " Conv2D(128, (3, 3), activation='relu'),\n",
+ " MaxPooling2D(2, 2),\n",
+ " \n",
+ " Conv2D(256, (3, 3), activation='relu'),\n",
+ " Conv2D(256, (3, 3), activation='relu'),\n",
+ " Conv2D(256, (3, 3), activation='relu'),\n",
+ " MaxPooling2D(2, 2),\n",
+ " \n",
+ " Flatten(),\n",
+ " Dense(512, activation='relu'),\n",
+ " Dense(512, activation='relu'),\n",
+ " Dense(5, activation='softmax')\n",
+ "])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "id": "30951498-99fd-468a-b766-98bcb8512371",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "Model: \"sequential\"\n",
+ "
\n"
+ ],
+ "text/plain": [
+ "\u001b[1mModel: \"sequential\"\u001b[0m\n"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
+ "┃ Layer (type) ┃ Output Shape ┃ Param # ┃\n",
+ "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
+ "│ conv2d (Conv2D) │ (None, 254, 254, 16) │ 448 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ max_pooling2d (MaxPooling2D) │ (None, 127, 127, 16) │ 0 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ conv2d_1 (Conv2D) │ (None, 125, 125, 32) │ 4,640 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ max_pooling2d_1 (MaxPooling2D) │ (None, 62, 62, 32) │ 0 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ conv2d_2 (Conv2D) │ (None, 60, 60, 64) │ 18,496 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ conv2d_3 (Conv2D) │ (None, 58, 58, 64) │ 36,928 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ max_pooling2d_2 (MaxPooling2D) │ (None, 29, 29, 64) │ 0 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ conv2d_4 (Conv2D) │ (None, 27, 27, 128) │ 73,856 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ conv2d_5 (Conv2D) │ (None, 25, 25, 128) │ 147,584 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ max_pooling2d_3 (MaxPooling2D) │ (None, 12, 12, 128) │ 0 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ conv2d_6 (Conv2D) │ (None, 10, 10, 256) │ 295,168 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ conv2d_7 (Conv2D) │ (None, 8, 8, 256) │ 590,080 │\n",
+ "├─────────────────────────────────┼────────────────────────┼──────────────��┤\n",
+ "│ conv2d_8 (Conv2D) │ (None, 6, 6, 256) │ 590,080 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ max_pooling2d_4 (MaxPooling2D) │ (None, 3, 3, 256) │ 0 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ flatten (Flatten) │ (None, 2304) │ 0 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ dense (Dense) │ (None, 512) │ 1,180,160 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ dense_1 (Dense) │ (None, 512) │ 262,656 │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ dense_2 (Dense) │ (None, 5) │ 2,565 │\n",
+ "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
+ "
\n"
+ ],
+ "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;34m254\u001b[0m, \u001b[38;5;34m254\u001b[0m, \u001b[38;5;34m16\u001b[0m) │ \u001b[38;5;34m448\u001b[0m │\n",
+ "├────────────────────���────────────┼────────────────────────┼───────────────┤\n",
+ "│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m127\u001b[0m, \u001b[38;5;34m127\u001b[0m, \u001b[38;5;34m16\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;34m125\u001b[0m, \u001b[38;5;34m125\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m4,640\u001b[0m │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ max_pooling2d_1 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m62\u001b[0m, \u001b[38;5;34m62\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;34m60\u001b[0m, \u001b[38;5;34m60\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m18,496\u001b[0m │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ conv2d_3 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m58\u001b[0m, \u001b[38;5;34m58\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m36,928\u001b[0m │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ max_pooling2d_2 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m29\u001b[0m, \u001b[38;5;34m29\u001b[0m, \u001b[38;5;34m64\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;34m27\u001b[0m, \u001b[38;5;34m27\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m73,856\u001b[0m │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ conv2d_5 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m25\u001b[0m, \u001b[38;5;34m25\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;34m12\u001b[0m, \u001b[38;5;34m12\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ conv2d_6 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m, \u001b[38;5;34m10\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m295,168\u001b[0m │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ conv2d_7 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m590,080\u001b[0m │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ conv2d_8 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m6\u001b[0m, \u001b[38;5;34m6\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m590,080\u001b[0m │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ max_pooling2d_4 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m3\u001b[0m, \u001b[38;5;34m3\u001b[0m, \u001b[38;5;34m256\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;34m2304\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;34m1,180,160\u001b[0m │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ dense_1 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m) │ \u001b[38;5;34m262,656\u001b[0m │\n",
+ "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+ "│ dense_2 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m5\u001b[0m) │ \u001b[38;5;34m2,565\u001b[0m │\n",
+ "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " Total params: 3,202,661 (12.22 MB)\n",
+ "
\n"
+ ],
+ "text/plain": [
+ "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m3,202,661\u001b[0m (12.22 MB)\n"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " Trainable params: 3,202,661 (12.22 MB)\n",
+ "
\n"
+ ],
+ "text/plain": [
+ "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m3,202,661\u001b[0m (12.22 MB)\n"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " Non-trainable params: 0 (0.00 B)\n",
+ "
\n"
+ ],
+ "text/plain": [
+ "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "model.summary()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "id": "3699a6b9-f2e0-4a12-9fec-c9381cbe740a",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "You must install pydot (`pip install pydot`) for `plot_model` to work.\n"
+ ]
+ }
+ ],
+ "source": [
+ "from tensorflow.keras.utils import plot_model\n",
+ "\n",
+ "plot_model(model, show_shapes=False, show_layer_names=True)\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "id": "2c32391e-5dcb-4018-af54-97949792e49b",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "C:\\Users\\akhyar\\AppData\\Roaming\\Python\\Python311\\site-packages\\keras\\src\\trainers\\data_adapters\\py_dataset_adapter.py:121: UserWarning: Your `PyDataset` class should call `super().__init__(**kwargs)` in its constructor. `**kwargs` can include `workers`, `use_multiprocessing`, `max_queue_size`. Do not pass these arguments to `fit()`, as they will be ignored.\n",
+ " self._warn_if_super_not_called()\n"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Epoch 1/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 462ms/step - accuracy: 0.2253 - loss: 1.6205"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "C:\\Users\\akhyar\\AppData\\Roaming\\Python\\Python311\\site-packages\\keras\\src\\trainers\\data_adapters\\py_dataset_adapter.py:121: UserWarning: Your `PyDataset` class should call `super().__init__(**kwargs)` in its constructor. `**kwargs` can include `workers`, `use_multiprocessing`, `max_queue_size`. Do not pass these arguments to `fit()`, as they will be ignored.\n",
+ " self._warn_if_super_not_called()\n"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m44s\u001b[0m 494ms/step - accuracy: 0.2255 - loss: 1.6202 - val_accuracy: 0.1770 - val_loss: 1.6205\n",
+ "Epoch 2/30\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "C:\\Users\\akhyar\\AppData\\Roaming\\Python\\Python311\\site-packages\\keras\\src\\callbacks\\model_checkpoint.py:206: UserWarning: Can save best model only with val_acc available, skipping.\n",
+ " self._save_model(epoch=epoch, batch=None, logs=logs)\n"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m37s\u001b[0m 455ms/step - accuracy: 0.2272 - loss: 1.6536 - val_accuracy: 0.3451 - val_loss: 1.5663\n",
+ "Epoch 3/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m39s\u001b[0m 485ms/step - accuracy: 0.2838 - loss: 1.5130 - val_accuracy: 0.5265 - val_loss: 1.1628\n",
+ "Epoch 4/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m39s\u001b[0m 492ms/step - accuracy: 0.3746 - loss: 1.6910 - val_accuracy: 0.3628 - val_loss: 1.4366\n",
+ "Epoch 5/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m39s\u001b[0m 491ms/step - accuracy: 0.3204 - loss: 1.7489 - val_accuracy: 0.3097 - val_loss: 1.5500\n",
+ "Epoch 6/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m39s\u001b[0m 483ms/step - accuracy: 0.2589 - loss: 1.5465 - val_accuracy: 0.3142 - val_loss: 1.4905\n",
+ "Epoch 7/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m38s\u001b[0m 476ms/step - accuracy: 0.3658 - loss: 1.4573 - val_accuracy: 0.3407 - val_loss: 1.4126\n",
+ "Epoch 8/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m40s\u001b[0m 495ms/step - accuracy: 0.4545 - loss: 1.2681 - val_accuracy: 0.5044 - val_loss: 1.1992\n",
+ "Epoch 9/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m40s\u001b[0m 502ms/step - accuracy: 0.4519 - loss: 1.2501 - val_accuracy: 0.5398 - val_loss: 1.2358\n",
+ "Epoch 10/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m39s\u001b[0m 484ms/step - accuracy: 0.5046 - loss: 1.2335 - val_accuracy: 0.5796 - val_loss: 0.9872\n",
+ "Epoch 11/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m39s\u001b[0m 478ms/step - accuracy: 0.5403 - loss: 1.0928 - val_accuracy: 0.6106 - val_loss: 0.9754\n",
+ "Epoch 12/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m38s\u001b[0m 469ms/step - accuracy: 0.5447 - loss: 1.0311 - val_accuracy: 0.6372 - val_loss: 0.8882\n",
+ "Epoch 13/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m36s\u001b[0m 453ms/step - accuracy: 0.5755 - loss: 1.0518 - val_accuracy: 0.5841 - val_loss: 1.1186\n",
+ "Epoch 14/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m37s\u001b[0m 459ms/step - accuracy: 0.5573 - loss: 1.0779 - val_accuracy: 0.6062 - val_loss: 0.9210\n",
+ "Epoch 15/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m37s\u001b[0m 455ms/step - accuracy: 0.5636 - loss: 0.9718 - val_accuracy: 0.6504 - val_loss: 0.8533\n",
+ "Epoch 16/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m38s\u001b[0m 468ms/step - accuracy: 0.6075 - loss: 0.9389 - val_accuracy: 0.6106 - val_loss: 0.9144\n",
+ "Epoch 17/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m37s\u001b[0m 465ms/step - accuracy: 0.5833 - loss: 1.0026 - val_accuracy: 0.6195 - val_loss: 1.0384\n",
+ "Epoch 18/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m37s\u001b[0m 459ms/step - accuracy: 0.6111 - loss: 1.0040 - val_accuracy: 0.6549 - val_loss: 0.8821\n",
+ "Epoch 19/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m43s\u001b[0m 537ms/step - accuracy: 0.5845 - loss: 1.0040 - val_accuracy: 0.6372 - val_loss: 0.8731\n",
+ "Epoch 20/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m42s\u001b[0m 526ms/step - accuracy: 0.6456 - loss: 0.8255 - val_accuracy: 0.5796 - val_loss: 1.0377\n",
+ "Epoch 21/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m42s\u001b[0m 528ms/step - accuracy: 0.6021 - loss: 0.9292 - val_accuracy: 0.6460 - val_loss: 0.8081\n",
+ "Epoch 22/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m40s\u001b[0m 498ms/step - accuracy: 0.6295 - loss: 0.8661 - val_accuracy: 0.6637 - val_loss: 0.8325\n",
+ "Epoch 23/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m39s\u001b[0m 489ms/step - accuracy: 0.6079 - loss: 0.8695 - val_accuracy: 0.5973 - val_loss: 0.8605\n",
+ "Epoch 24/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m38s\u001b[0m 470ms/step - accuracy: 0.6077 - loss: 0.9255 - val_accuracy: 0.6460 - val_loss: 0.8265\n",
+ "Epoch 25/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m38s\u001b[0m 477ms/step - accuracy: 0.6108 - loss: 0.9091 - val_accuracy: 0.6504 - val_loss: 0.7982\n",
+ "Epoch 26/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m38s\u001b[0m 473ms/step - accuracy: 0.6259 - loss: 0.8461 - val_accuracy: 0.6327 - val_loss: 0.8301\n",
+ "Epoch 27/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m38s\u001b[0m 471ms/step - accuracy: 0.6639 - loss: 0.7962 - val_accuracy: 0.6239 - val_loss: 0.9369\n",
+ "Epoch 28/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m38s\u001b[0m 473ms/step - accuracy: 0.6029 - loss: 0.8907 - val_accuracy: 0.6681 - val_loss: 0.7992\n",
+ "Epoch 29/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m39s\u001b[0m 486ms/step - accuracy: 0.6502 - loss: 0.8188 - val_accuracy: 0.6770 - val_loss: 0.8378\n",
+ "Epoch 30/30\n",
+ "\u001b[1m80/80\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m38s\u001b[0m 470ms/step - accuracy: 0.6411 - loss: 0.8481 - val_accuracy: 0.6593 - val_loss: 0.7786\n"
+ ]
+ }
+ ],
+ "source": [
+ "model.compile(optimizer='Adam', loss='categorical_crossentropy', metrics =['accuracy'])\n",
+ "history = model.fit(train_generator,\n",
+ " epochs=30,\n",
+ " verbose=1,\n",
+ " validation_data=validation_generator,\n",
+ " callbacks = [best_model]\n",
+ " )"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "id": "bfe1fe88",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'cloudy': 0, 'foggy': 1, 'rainy': 2, 'shine': 3, 'sunrise': 4}\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(train_generator.class_indices)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "id": "4de69113-a158-4cda-9313-b0ac433193f0",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
+ ]
+ }
+ ],
+ "source": [
+ "model.save('../weather_model.h5')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 17,
+ "id": "bbb78806-08dc-4e67-97a8-0ad728429e57",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "model.save(\"../cnnModel.keras\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 18,
+ "id": "4f6eabb2-0c80-4331-9102-0709a37a9406",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "acc=history.history['accuracy']\n",
+ "val_acc=history.history['val_accuracy']\n",
+ "loss=history.history['loss']\n",
+ "val_loss=history.history['val_loss']\n",
+ "\n",
+ "epochs=range(len(acc))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 21,
+ "id": "ea88072b-f951-4418-8629-7948bbe4395f",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "\n",
+ "\n",
+ "# In[14]:\n",
+ "\n",
+ "fig = plt.figure(figsize=(20,10))\n",
+ "plt.plot(epochs, acc, 'r', label=\"Training Accuracy\")\n",
+ "plt.plot(epochs, val_acc, 'b', label=\"Validation Accuracy\")\n",
+ "plt.xlabel('Epoch')\n",
+ "plt.ylabel('Accuracy')\n",
+ "plt.title('Training and validation accuracy')\n",
+ "plt.legend(loc='lower right')\n",
+ "plt.show()\n",
+ "fig.savefig('../Accuracy_curve_CNN_aug_256.jpg')\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 22,
+ "id": "1db97deb-81a6-42d3-a29f-d5af1a4ddca2",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "image/png": "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",
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "# In[15]:\n",
+ "\n",
+ "fig2 = plt.figure(figsize=(20,10))\n",
+ "plt.plot(epochs, loss, 'r', label=\"Training Loss\")\n",
+ "plt.plot(epochs, val_loss, 'b', label=\"Validation Loss\")\n",
+ "plt.legend(loc='upper right')\n",
+ "plt.xlabel('Epoch')\n",
+ "plt.ylabel('Loss')\n",
+ "plt.title('Training and validation loss')\n",
+ "fig2.savefig('../Loss_curve_CNN_aug_256.jpg')\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n"
+ ]
+ }
+ ],
+ "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": "3.11.9"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}