2021-12-19 23:09:15 +01:00
|
|
|
{
|
|
|
|
|
"cells": [
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2021-12-20 06:53:12 +01:00
|
|
|
"execution_count": 1,
|
2021-12-19 23:09:15 +01:00
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"import os\n",
|
|
|
|
|
"import numpy as np\n",
|
|
|
|
|
"import tensorflow as tf\n",
|
|
|
|
|
"from tensorflow.keras.models import Sequential\n",
|
|
|
|
|
"from tensorflow.keras.layers import Dense, Dropout, Flatten, Activation, Conv2D, MaxPooling2D\n",
|
2021-12-20 04:59:37 +01:00
|
|
|
"from keras.preprocessing.image import ImageDataGenerator\n",
|
|
|
|
|
"from tensorflow.keras.optimizers import RMSprop\n",
|
2021-12-20 06:53:12 +01:00
|
|
|
"from tensorflow.keras.utils import plot_model\n",
|
|
|
|
|
"import matplotlib.pyplot as plt\n",
|
|
|
|
|
"import matplotlib.image as mpimg\n",
|
|
|
|
|
"import keras_tuner as kt\n",
|
|
|
|
|
"import keras"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"## Konfiguracja"
|
2021-12-19 23:09:15 +01:00
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2021-12-20 06:53:12 +01:00
|
|
|
"execution_count": 2,
|
2021-12-19 23:09:15 +01:00
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
2021-12-20 06:53:12 +01:00
|
|
|
"train_data_dir=\"./Trees\"\n",
|
|
|
|
|
"validation_data_dir=\"./Trees\"\n",
|
|
|
|
|
"batch_size=16\n",
|
2021-12-20 04:59:37 +01:00
|
|
|
"img_height, img_width = 60,80"
|
2021-12-19 23:09:15 +01:00
|
|
|
]
|
|
|
|
|
},
|
2021-12-20 06:53:12 +01:00
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"## Generowanie zdjęć"
|
|
|
|
|
]
|
|
|
|
|
},
|
2021-12-19 23:09:15 +01:00
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2021-12-20 06:53:12 +01:00
|
|
|
"execution_count": 3,
|
2021-12-19 23:09:15 +01:00
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"name": "stdout",
|
|
|
|
|
"output_type": "stream",
|
|
|
|
|
"text": [
|
2021-12-20 06:53:12 +01:00
|
|
|
"Found 759 images belonging to 3 classes.\n",
|
|
|
|
|
"Found 187 images belonging to 3 classes.\n"
|
2021-12-19 23:09:15 +01:00
|
|
|
]
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
2021-12-20 06:53:12 +01:00
|
|
|
"train_datagen = ImageDataGenerator(\n",
|
|
|
|
|
" rescale=1./255, \n",
|
|
|
|
|
" shear_range=0.2, # view images from various angles\n",
|
2021-12-20 04:59:37 +01:00
|
|
|
" zoom_range=0.2,\n",
|
2021-12-20 06:53:12 +01:00
|
|
|
" horizontal_flip=True, # randomly flip img horizontally\n",
|
|
|
|
|
" vertical_flip=True, # randomly flip img vertically\n",
|
2021-12-20 04:59:37 +01:00
|
|
|
" validation_split=0.2) # set validation split\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"train_generator = train_datagen.flow_from_directory(\n",
|
|
|
|
|
" train_data_dir,\n",
|
|
|
|
|
" target_size=(img_height, img_width),\n",
|
|
|
|
|
" batch_size=batch_size,\n",
|
|
|
|
|
" class_mode='categorical',\n",
|
|
|
|
|
" subset='training') # set as training data\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"validation_generator = train_datagen.flow_from_directory(\n",
|
|
|
|
|
" validation_data_dir, # same directory as training data\n",
|
|
|
|
|
" target_size=(img_height, img_width),\n",
|
|
|
|
|
" batch_size=batch_size,\n",
|
|
|
|
|
" class_mode='categorical',\n",
|
|
|
|
|
" subset='validation')"
|
2021-12-19 23:09:15 +01:00
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2021-12-20 06:53:12 +01:00
|
|
|
"execution_count": 4,
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"image/png": "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
|
|
|
|
|
"text/plain": [
|
|
|
|
|
"<Figure size 720x360 with 3 Axes>"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
"metadata": {
|
|
|
|
|
"needs_background": "light"
|
|
|
|
|
},
|
|
|
|
|
"output_type": "display_data"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"image/png": "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
|
|
|
|
|
"text/plain": [
|
|
|
|
|
"<Figure size 720x360 with 3 Axes>"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
"metadata": {
|
|
|
|
|
"needs_background": "light"
|
|
|
|
|
},
|
|
|
|
|
"output_type": "display_data"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"image/png": "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
|
|
|
|
|
"text/plain": [
|
|
|
|
|
"<Figure size 720x360 with 3 Axes>"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
"metadata": {
|
|
|
|
|
"needs_background": "light"
|
|
|
|
|
},
|
|
|
|
|
"output_type": "display_data"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
|
|
|
|
"def plot_image(fname, label, col):\n",
|
|
|
|
|
" img = mpimg.imread(train_data_dir + '/' + fname)\n",
|
|
|
|
|
" plt.subplot(1,3,col)\n",
|
|
|
|
|
" plt.title(label)\n",
|
|
|
|
|
" plt.imshow(img)\n",
|
|
|
|
|
" \n",
|
|
|
|
|
"plt.figure(figsize=(10,5))\n",
|
|
|
|
|
"cat1_files = ['AS12_7/18.png','AS12_7/103.png','AS12_7/225.png']\n",
|
|
|
|
|
"for idx, f in enumerate(cat1_files):\n",
|
|
|
|
|
" plot_image(f, f'Category 1: {idx+1}', idx + 1)\n",
|
|
|
|
|
"plt.show()\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"plt.figure(figsize=(10,5))\n",
|
|
|
|
|
"cat2_files = ['EA01a/15.png','EA01a/5.png','EA01a/12.png']\n",
|
|
|
|
|
"for idx, f in enumerate(cat2_files):\n",
|
|
|
|
|
" plot_image(f, f'Category 2: {idx+1}', idx + 1)\n",
|
|
|
|
|
"plt.show()\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"plt.figure(figsize=(10,5))\n",
|
|
|
|
|
"cat3_files = ['EU43_6/135.png','EU43_6/195.png','EU43_6/16.png']\n",
|
|
|
|
|
"for idx, f in enumerate(cat3_files):\n",
|
|
|
|
|
" plot_image(f, f'Category 2: {idx+1}', idx + 1)\n",
|
|
|
|
|
"plt.show()"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
2021-12-19 23:09:15 +01:00
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
2021-12-20 06:53:12 +01:00
|
|
|
"## CNN"
|
2021-12-20 04:58:55 +01:00
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2021-12-20 06:53:12 +01:00
|
|
|
"execution_count": 5,
|
2021-12-19 23:09:15 +01:00
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
2021-12-20 06:53:12 +01:00
|
|
|
"model = Sequential()\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"model.add(Conv2D(32, (3,3), activation='relu', input_shape=(img_height, img_width, 3)))\n",
|
2021-12-20 04:59:37 +01:00
|
|
|
"model.add(MaxPooling2D((2,2)))\n",
|
2021-12-20 06:53:12 +01:00
|
|
|
"\n",
|
2021-12-20 04:59:37 +01:00
|
|
|
"model.add(Conv2D(64, (3,3), activation='relu'))\n",
|
|
|
|
|
"model.add(MaxPooling2D((2,2)))\n",
|
2021-12-20 06:53:12 +01:00
|
|
|
"\n",
|
2021-12-20 04:59:37 +01:00
|
|
|
"model.add(Conv2D(64, (3,3), activation='relu'))\n",
|
|
|
|
|
"model.add(MaxPooling2D((2,2)))\n",
|
2021-12-20 06:53:12 +01:00
|
|
|
"\n",
|
2021-12-20 04:59:37 +01:00
|
|
|
"model.add(Flatten())\n",
|
2021-12-20 06:53:12 +01:00
|
|
|
"\n",
|
2021-12-20 04:59:37 +01:00
|
|
|
"model.add(Dense(512, activation='relu'))\n",
|
|
|
|
|
"model.add(Dense(512, activation='relu'))\n",
|
2021-12-19 23:09:15 +01:00
|
|
|
"\n",
|
2021-12-20 04:59:37 +01:00
|
|
|
"model.add(Dense(3, activation='softmax'))"
|
2021-12-19 23:09:15 +01:00
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2021-12-20 06:53:12 +01:00
|
|
|
"execution_count": 6,
|
2021-12-19 23:09:15 +01:00
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
2021-12-20 06:53:12 +01:00
|
|
|
"data": {
|
|
|
|
|
"image/png": "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
|
|
|
|
|
"text/plain": [
|
|
|
|
|
"<IPython.core.display.Image object>"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
"execution_count": 6,
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "execute_result"
|
2021-12-19 23:09:15 +01:00
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
2021-12-20 04:59:37 +01:00
|
|
|
"plot_model(model, to_file='model1_plot.png', show_shapes=True,show_dtype=True, show_layer_names=True, expand_nested=True,)"
|
2021-12-19 23:09:15 +01:00
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2021-12-20 06:53:12 +01:00
|
|
|
"execution_count": 7,
|
2021-12-19 23:09:15 +01:00
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"name": "stdout",
|
|
|
|
|
"output_type": "stream",
|
|
|
|
|
"text": [
|
2021-12-20 06:53:12 +01:00
|
|
|
"Model: \"sequential\"\n",
|
2021-12-19 23:09:15 +01:00
|
|
|
"_________________________________________________________________\n",
|
|
|
|
|
"Layer (type) Output Shape Param # \n",
|
|
|
|
|
"=================================================================\n",
|
2021-12-20 06:53:12 +01:00
|
|
|
"conv2d (Conv2D) (None, 58, 78, 32) 896 \n",
|
2021-12-19 23:09:15 +01:00
|
|
|
"_________________________________________________________________\n",
|
2021-12-20 06:53:12 +01:00
|
|
|
"max_pooling2d (MaxPooling2D) (None, 29, 39, 32) 0 \n",
|
2021-12-19 23:09:15 +01:00
|
|
|
"_________________________________________________________________\n",
|
2021-12-20 06:53:12 +01:00
|
|
|
"conv2d_1 (Conv2D) (None, 27, 37, 64) 18496 \n",
|
2021-12-19 23:09:15 +01:00
|
|
|
"_________________________________________________________________\n",
|
2021-12-20 06:53:12 +01:00
|
|
|
"max_pooling2d_1 (MaxPooling2 (None, 13, 18, 64) 0 \n",
|
2021-12-19 23:09:15 +01:00
|
|
|
"_________________________________________________________________\n",
|
2021-12-20 06:53:12 +01:00
|
|
|
"conv2d_2 (Conv2D) (None, 11, 16, 64) 36928 \n",
|
2021-12-19 23:09:15 +01:00
|
|
|
"_________________________________________________________________\n",
|
2021-12-20 06:53:12 +01:00
|
|
|
"max_pooling2d_2 (MaxPooling2 (None, 5, 8, 64) 0 \n",
|
2021-12-19 23:09:15 +01:00
|
|
|
"_________________________________________________________________\n",
|
2021-12-20 06:53:12 +01:00
|
|
|
"flatten (Flatten) (None, 2560) 0 \n",
|
2021-12-19 23:09:15 +01:00
|
|
|
"_________________________________________________________________\n",
|
2021-12-20 06:53:12 +01:00
|
|
|
"dense (Dense) (None, 512) 1311232 \n",
|
2021-12-19 23:09:15 +01:00
|
|
|
"_________________________________________________________________\n",
|
2021-12-20 06:53:12 +01:00
|
|
|
"dense_1 (Dense) (None, 512) 262656 \n",
|
2021-12-20 04:59:37 +01:00
|
|
|
"_________________________________________________________________\n",
|
2021-12-20 06:53:12 +01:00
|
|
|
"dense_2 (Dense) (None, 3) 1539 \n",
|
2021-12-19 23:09:15 +01:00
|
|
|
"=================================================================\n",
|
2021-12-20 04:59:37 +01:00
|
|
|
"Total params: 1,631,747\n",
|
|
|
|
|
"Trainable params: 1,631,747\n",
|
2021-12-19 23:09:15 +01:00
|
|
|
"Non-trainable params: 0\n",
|
|
|
|
|
"_________________________________________________________________\n",
|
|
|
|
|
"None\n"
|
|
|
|
|
]
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
|
|
|
|
"print(model.summary())"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2021-12-20 06:53:12 +01:00
|
|
|
"execution_count": 8,
|
2021-12-19 23:09:15 +01:00
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
2021-12-20 04:59:37 +01:00
|
|
|
"model.compile(optimizer=RMSprop(learning_rate=0.0001),\n",
|
|
|
|
|
" loss=tf.keras.losses.CategoricalCrossentropy(),\n",
|
2021-12-19 23:09:15 +01:00
|
|
|
" metrics=['accuracy'])"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2021-12-20 06:53:12 +01:00
|
|
|
"execution_count": 9,
|
2021-12-19 23:09:15 +01:00
|
|
|
"metadata": {
|
|
|
|
|
"scrolled": false
|
|
|
|
|
},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"name": "stdout",
|
|
|
|
|
"output_type": "stream",
|
|
|
|
|
"text": [
|
2021-12-20 06:53:12 +01:00
|
|
|
"Epoch 1/16\n",
|
|
|
|
|
"48/48 [==============================] - 21s 419ms/step - loss: 0.8317 - accuracy: 0.6440 - val_loss: 0.7841 - val_accuracy: 0.8125\n",
|
|
|
|
|
"Epoch 2/16\n",
|
|
|
|
|
"48/48 [==============================] - 18s 376ms/step - loss: 0.6134 - accuracy: 0.7810 - val_loss: 0.3542 - val_accuracy: 0.8438\n",
|
|
|
|
|
"Epoch 3/16\n",
|
|
|
|
|
"48/48 [==============================] - 18s 377ms/step - loss: 0.4492 - accuracy: 0.8211 - val_loss: 0.2147 - val_accuracy: 0.9531\n",
|
|
|
|
|
"Epoch 4/16\n",
|
|
|
|
|
"48/48 [==============================] - 18s 367ms/step - loss: 0.2990 - accuracy: 0.9016 - val_loss: 0.4539 - val_accuracy: 0.8125\n",
|
|
|
|
|
"Epoch 5/16\n",
|
|
|
|
|
"48/48 [==============================] - 18s 379ms/step - loss: 0.2767 - accuracy: 0.8925 - val_loss: 0.0954 - val_accuracy: 0.9531\n",
|
|
|
|
|
"Epoch 6/16\n",
|
|
|
|
|
"48/48 [==============================] - 17s 364ms/step - loss: 0.2011 - accuracy: 0.9363 - val_loss: 0.1089 - val_accuracy: 0.9688\n",
|
|
|
|
|
"Epoch 7/16\n",
|
|
|
|
|
"48/48 [==============================] - 17s 362ms/step - loss: 0.2036 - accuracy: 0.9311 - val_loss: 0.0708 - val_accuracy: 1.0000\n",
|
|
|
|
|
"Epoch 8/16\n",
|
|
|
|
|
"48/48 [==============================] - 17s 361ms/step - loss: 0.1124 - accuracy: 0.9751 - val_loss: 0.5785 - val_accuracy: 0.7500\n",
|
|
|
|
|
"Epoch 9/16\n",
|
|
|
|
|
"48/48 [==============================] - 17s 360ms/step - loss: 0.1146 - accuracy: 0.9699 - val_loss: 0.0354 - val_accuracy: 1.0000\n",
|
|
|
|
|
"Epoch 10/16\n",
|
|
|
|
|
"48/48 [==============================] - 16s 341ms/step - loss: 0.1671 - accuracy: 0.9596 - val_loss: 0.0151 - val_accuracy: 1.0000\n",
|
|
|
|
|
"Epoch 11/16\n",
|
|
|
|
|
"48/48 [==============================] - 16s 327ms/step - loss: 0.0743 - accuracy: 0.9792 - val_loss: 0.0216 - val_accuracy: 1.0000\n",
|
|
|
|
|
"Epoch 12/16\n",
|
|
|
|
|
"48/48 [==============================] - 16s 332ms/step - loss: 0.0752 - accuracy: 0.9779 - val_loss: 0.0099 - val_accuracy: 1.0000\n",
|
|
|
|
|
"Epoch 13/16\n",
|
|
|
|
|
"48/48 [==============================] - 16s 328ms/step - loss: 0.1131 - accuracy: 0.9679 - val_loss: 0.0610 - val_accuracy: 0.9844\n",
|
|
|
|
|
"Epoch 14/16\n",
|
|
|
|
|
"48/48 [==============================] - 15s 318ms/step - loss: 0.1129 - accuracy: 0.9591 - val_loss: 0.0253 - val_accuracy: 1.0000\n",
|
|
|
|
|
"Epoch 15/16\n",
|
|
|
|
|
"48/48 [==============================] - 16s 329ms/step - loss: 0.0445 - accuracy: 0.9877 - val_loss: 0.0213 - val_accuracy: 1.0000\n",
|
|
|
|
|
"Epoch 16/16\n",
|
|
|
|
|
"48/48 [==============================] - 17s 346ms/step - loss: 0.0665 - accuracy: 0.9746 - val_loss: 0.0353 - val_accuracy: 0.9844\n"
|
|
|
|
|
]
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
|
|
|
|
"history = model.fit(train_generator, epochs=16, verbose=1,\n",
|
|
|
|
|
" validation_data = validation_generator, validation_steps = 4)"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
"execution_count": 10,
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"text/plain": [
|
|
|
|
|
"<matplotlib.legend.Legend at 0x17d175c4e20>"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
"execution_count": 10,
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "execute_result"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"image/png": "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
|
|
|
|
|
"text/plain": [
|
|
|
|
|
"<Figure size 432x288 with 1 Axes>"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
"metadata": {
|
|
|
|
|
"needs_background": "light"
|
|
|
|
|
},
|
|
|
|
|
"output_type": "display_data"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
|
|
|
|
"plt.plot(history.history['accuracy'], label='accuracy')\n",
|
|
|
|
|
"plt.plot(history.history['val_accuracy'], label = 'val_accuracy')\n",
|
|
|
|
|
"plt.xlabel('Epoch')\n",
|
|
|
|
|
"plt.ylabel('Accuracy')\n",
|
|
|
|
|
"plt.ylim([0.5, 1])\n",
|
|
|
|
|
"plt.legend(loc='lower right')"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"## CNN + hyperparameter tuning"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
"execution_count": 15,
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"def build_model(hp):\n",
|
|
|
|
|
" inputs = keras.Input(shape=(img_height, img_width, 3))\n",
|
|
|
|
|
" x = inputs\n",
|
|
|
|
|
" for i in range(hp.Int(\"cnn_layers\", 1, 3)):\n",
|
|
|
|
|
" x = Conv2D(\n",
|
|
|
|
|
" hp.Int(f\"filters_{i}\", 32, 128, step=32),\n",
|
|
|
|
|
" kernel_size=(3, 3),\n",
|
|
|
|
|
" activation=\"relu\",\n",
|
|
|
|
|
" )(x)\n",
|
|
|
|
|
" x = MaxPooling2D(pool_size=(2, 2))(x)\n",
|
|
|
|
|
" x = Flatten()(x)\n",
|
|
|
|
|
"\n",
|
|
|
|
|
" # A hyperparamter for whether to use dropout layer.\n",
|
|
|
|
|
" if hp.Boolean(\"dropout\"):\n",
|
|
|
|
|
" x = Dropout(0.5)(x)\n",
|
|
|
|
|
"\n",
|
|
|
|
|
" outputs = Dense(units=3, activation=\"softmax\")(x)\n",
|
|
|
|
|
" model = keras.Model(inputs=inputs, outputs=outputs)\n",
|
|
|
|
|
"\n",
|
|
|
|
|
" # Compile the model.\n",
|
|
|
|
|
" model.compile(\n",
|
|
|
|
|
" optimizer=RMSprop(learning_rate=0.0001),\n",
|
|
|
|
|
" loss=tf.keras.losses.CategoricalCrossentropy(),\n",
|
|
|
|
|
" metrics=['accuracy'],\n",
|
|
|
|
|
" )\n",
|
|
|
|
|
" return model\n"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
"execution_count": 17,
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"hp = kt.HyperParameters()\n",
|
|
|
|
|
"model = build_model(hp)"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
"execution_count": 18,
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"image/png": "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
|
|
|
|
|
"text/plain": [
|
|
|
|
|
"<IPython.core.display.Image object>"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
"execution_count": 18,
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "execute_result"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
|
|
|
|
"plot_model(model, to_file='model2_plot.png', show_shapes=True,show_dtype=True, show_layer_names=True, expand_nested=True,)"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
"execution_count": 19,
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"name": "stdout",
|
|
|
|
|
"output_type": "stream",
|
|
|
|
|
"text": [
|
|
|
|
|
"Epoch 1/16\n",
|
|
|
|
|
"48/48 [==============================] - 17s 342ms/step - loss: 0.7536 - accuracy: 0.6303 - val_loss: 0.5446 - val_accuracy: 0.9375\n",
|
|
|
|
|
"Epoch 2/16\n",
|
|
|
|
|
"48/48 [==============================] - 18s 369ms/step - loss: 0.4898 - accuracy: 0.8538 - val_loss: 0.3223 - val_accuracy: 0.9531\n",
|
|
|
|
|
"Epoch 3/16\n",
|
|
|
|
|
"48/48 [==============================] - 17s 362ms/step - loss: 0.3330 - accuracy: 0.8921 - val_loss: 0.1827 - val_accuracy: 0.9844\n",
|
|
|
|
|
"Epoch 4/16\n",
|
|
|
|
|
"48/48 [==============================] - 18s 380ms/step - loss: 0.2685 - accuracy: 0.9094 - val_loss: 0.2703 - val_accuracy: 0.9844\n",
|
|
|
|
|
"Epoch 5/16\n",
|
|
|
|
|
"48/48 [==============================] - 19s 403ms/step - loss: 0.2051 - accuracy: 0.9460 - val_loss: 0.2149 - val_accuracy: 0.9844\n",
|
|
|
|
|
"Epoch 6/16\n",
|
|
|
|
|
"48/48 [==============================] - 19s 403ms/step - loss: 0.1838 - accuracy: 0.9561 - val_loss: 0.1424 - val_accuracy: 0.9531\n",
|
|
|
|
|
"Epoch 7/16\n",
|
|
|
|
|
"48/48 [==============================] - 19s 394ms/step - loss: 0.1609 - accuracy: 0.9720 - val_loss: 0.1484 - val_accuracy: 0.9688\n",
|
|
|
|
|
"Epoch 8/16\n",
|
|
|
|
|
"48/48 [==============================] - 19s 404ms/step - loss: 0.1325 - accuracy: 0.9680 - val_loss: 0.0957 - val_accuracy: 0.9844\n",
|
|
|
|
|
"Epoch 9/16\n",
|
|
|
|
|
"48/48 [==============================] - 19s 406ms/step - loss: 0.1129 - accuracy: 0.9808 - val_loss: 0.1412 - val_accuracy: 0.9844\n",
|
|
|
|
|
"Epoch 10/16\n",
|
|
|
|
|
"48/48 [==============================] - 19s 401ms/step - loss: 0.1178 - accuracy: 0.9695 - val_loss: 0.0513 - val_accuracy: 1.0000\n",
|
|
|
|
|
"Epoch 11/16\n",
|
|
|
|
|
"48/48 [==============================] - 20s 408ms/step - loss: 0.0963 - accuracy: 0.9795 - val_loss: 0.0421 - val_accuracy: 1.0000\n",
|
|
|
|
|
"Epoch 12/16\n",
|
|
|
|
|
"48/48 [==============================] - 18s 387ms/step - loss: 0.0932 - accuracy: 0.9893 - val_loss: 0.0515 - val_accuracy: 1.0000\n",
|
|
|
|
|
"Epoch 13/16\n",
|
|
|
|
|
"48/48 [==============================] - 20s 416ms/step - loss: 0.0915 - accuracy: 0.9801 - val_loss: 0.1114 - val_accuracy: 0.9844\n",
|
|
|
|
|
"Epoch 14/16\n",
|
|
|
|
|
"48/48 [==============================] - 17s 356ms/step - loss: 0.0663 - accuracy: 0.9935 - val_loss: 0.0428 - val_accuracy: 1.0000\n",
|
|
|
|
|
"Epoch 15/16\n",
|
|
|
|
|
"48/48 [==============================] - 17s 360ms/step - loss: 0.0889 - accuracy: 0.9767 - val_loss: 0.0825 - val_accuracy: 0.9844\n",
|
|
|
|
|
"Epoch 16/16\n",
|
|
|
|
|
"48/48 [==============================] - 17s 347ms/step - loss: 0.0807 - accuracy: 0.9835 - val_loss: 0.0292 - val_accuracy: 1.0000\n"
|
2021-12-19 23:09:15 +01:00
|
|
|
]
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
2021-12-20 06:53:12 +01:00
|
|
|
"history = model.fit(train_generator, verbose=1, epochs=16,\n",
|
2021-12-20 04:59:37 +01:00
|
|
|
" validation_data = validation_generator, validation_steps = 4)"
|
2021-12-19 23:09:15 +01:00
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2021-12-20 06:53:12 +01:00
|
|
|
"execution_count": 20,
|
2021-12-19 23:09:15 +01:00
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
2021-12-20 04:59:37 +01:00
|
|
|
"data": {
|
|
|
|
|
"text/plain": [
|
2021-12-20 06:53:12 +01:00
|
|
|
"<matplotlib.legend.Legend at 0x17d1769efd0>"
|
2021-12-20 04:59:37 +01:00
|
|
|
]
|
|
|
|
|
},
|
2021-12-20 06:53:12 +01:00
|
|
|
"execution_count": 20,
|
2021-12-20 04:59:37 +01:00
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "execute_result"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
2021-12-20 06:53:12 +01:00
|
|
|
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEKCAYAAAAfGVI8AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8vihELAAAACXBIWXMAAAsTAAALEwEAmpwYAAAtKElEQVR4nO3deXxV9bnv8c+TARICJAwBmUFkFlGI4FAFpSIqiraOx9pKqx691WP1tNrqseppT29vh9trj9PBU7W2DqfFWVGcoa3WMkqYQcZAgBDISEKm5/6xdsImJLAD2dlJ9vf9euWVvdZea+0nCfy+a/3WWr9l7o6IiMSvhFgXICIisaUgEBGJcwoCEZE4pyAQEYlzCgIRkTinIBARiXNRCwIze9rMdpvZikbeNzP7rZltMLPlZjY+WrWIiEjjonlE8Cww/QjvXwQMC33dAjwRxVpERKQRUQsCd18A7D3CIjOB5zzwdyDDzPpEqx4REWlYUgw/ux+wLWw6JzQvt/6CZnYLwVEDaWlpE0aOHNkiBYq0WgdKoHwflBVCTWWsq4lccidIzYCUDEjqGNtaKvdDWQGUF0DVgWCeJUBKelBfStdgOla8BsqLgr9zeVEwnZYJ6f2PaXOLFy/e4+6ZDb0XyyCwBuY1ON6Fu88GZgNkZWX5okWLolmXSOtTUw1bP4OVr8Gq16F0NySlwvBrYMwV0G9CbButo6ncD+vmwcpXYfsioAj6nApjLofRl0P3IdGvwR12Lg9qWPka7NsOlggnTg/qSB8Aq9+E1W9AaR4kl8LwC4Pf70kXQIdO0a+xohTWvxfUt24eVJVB594walZQx8AzICHxmDZtZlsafS+aYw2Z2WDgLXc/uYH3/gv4xN1fDE2vBaa4+2FHBOEUBBI3ampg29+DhmvV61CyK9T4TwsahWHToENarKtsuoKtwc+z8lXYvjiY1/e0IBDGXA7dBjffZ7nDzmxY9VrweXs3hhr/ycHnjZwBaT0OXae6Crb8LVhn1Ruwfw8kp8GI6cE6wy6A5NTmq7FiP2x4P6hv3bwgNNMyYfTMUON/5jE3/uHMbLG7ZzX4XgyD4BLgduBiYBLwW3efeLRtKgikXaupgW2fhzX+OyEpJWj0axv/jp1jXWXz2bflYCjsWBLM6zs++FlHz4Rug5q+TXfYtSLYq175Kuz9Mmj8h5wTbHfkpYc3/o2proItfw22s/pN2J8PHTrD8NBRxElfPbZQqCyD9eGNfyl06hlq/C+HQWc3S+MfLiZBYGYvAlOAnsAu4EEgGcDdnzQzAx4luLJoPzDL3Y/awisIpN2pqYGcfxxs/Itzg8b/pK8GDdfw6W2m8Xd38koOsCV/P5v2lLIlv5TN+fvZvq+Mnp07MrhHJwb1TGNwj04M7pFG34xUEhNCvcT7Noe6vl6DHUuDef0mHAyFjIFH+mDYvSrU7fMq5G8IusoGhxr/UZdCWs8GVy05UEVuQRllldWc0DWFnp07kpDQQM91dRVs/svBUCjbG4TCiIuCzxg6FZJTGq+xsgw2fBCsv/bdg43/qEuD9QedDYlBb33B/go25+8Pfn97Qt/zS5l5aj++ddbgo/0ZGhSzI4JoUBBIu1BTAzkLQ10Wr0HxDkjsGHQ7jLki6Jvu2CXWVTaopsbZXXyAzflBQ7+prqEKvu+vqK5bNjHBGNAtlb4ZqeSXVLBlbynllTV17ycnGgO6B6EwqMfB7ycl7aHP9ndJXP0a5H4RLNwvKywUBoQa/9Vhjf/6UOP/lbo9//KO3dlRUEZuYXnd99zCMnYUlLOzsJwdhWUUl1cd8vMlJxq9u6bQNz2VPhkp9ElPpW/oe5/0FPqkp9A9xbDwI4WyfdChS1gonB+EQmX5wcZ/3btQUQKp3fFRl1E0dAYbOp3Kln0H2Jy/n81hwVlYdvACADPom57KoB6d+Nr4/lw54dhOFisI2oKaGlj2/ME+09YqsQNkfRt6xcGVW7WH75v/AtXNeGVOdQVs/ASKtge/z5PCGv+Urs33OcehpsbJLSpny56DDXywh78/osZ8cGivv29GKsmJCYdsNzxEahvAhkIkKcHo3y2V07sWMo3POK3kE3oWrwm20+90OFBIwp51uCWwp0cWq7pN5bMOZ7Fhfyo7CoIGf9/+w/9uPdI6HGzg01PokxE08KnJiewsKq9bN7egnNyiMnYWllNZfWg72TEpIRQKqfRLT2ISKzmt+GMG7f6I5IpCvENnGDAR3/YPEipKOJCcwZpuk5mffA4flA1jU/4Big8cDKAEg37dUusFYvA7HNC9EynJbfgcQTS0yyDYtxlevz1ocFK7Q0IsL+Y6igPF4NVw3n1w5h11h7LtRkN7cB06B5c9Nhezg10ew6e3isZ/d1E5i7fsC7627mPljiIqqg429h2SEhjUvVNd49Ro985xCO9WCsKh9JDukZIDVQyynVyS8DnTExdS6im8XTOJedWnk0cGAOmpyXV77X0yQg19aM++b3oqJ6SnNLlRralx9pQeCIIhdDSRW1jGjsJyckNHGbuKyqlxSKKKsxNWcnHC52QlrmNh9XDerjmDz2pG4wnJDOiWevB32CONwT2D7/27pdIxqXnPCdSnIGitampg8dPw3o+DQ9oL/wPGfzNoKFqrkjx4++7gErt+E+DyJyBzRKyrOj6V5fDlh6G+23fqDt/r+m4Hn9MsgVdT4+SXVrCrqJz01ORma0Cbqqq6hjU7i+sa/iVb95GzrwwIGvxx/dMZ1z+DEzM71zX6fbqmNNxv3kLcnb2l4f3mpSQk2CHdN33SU0jrGJsdk6rqGnYXHzgkKPJLK+q6dAb3SKNft0OPjlqagqA1KtgaHAVsmg8nToHLHg36PdsCd1jxMsz9fnDp2/n3w5m3N/tVDlFVWQ5ffhTW+BeHGv8ZYY1/csSbc3cK9leyo7ZLIWyPcUeoX3pX4QEqqhvvUhnS82B3QL+MVJKaqdHYV1rB0m2hRn9LAcu2FVBWGXTB9O7akaxB3TltYAYTBnVjTN90OiS14vsR5JgpCFoTd1j8LLz3b8H0tJ/ChBtb91FAY4p3BUcHa96C/hPh8seh57BYV9W4qgOHNv4HioI7SGv3/Iec22jjX1xeeegJx7AGPrcgOOkY3m8OQR93764ph51oPCE9hYL9lWH940Hfe23jXLtu/3rdCEFQdKJ/t06NNtY1Nc6XeSV1e/qLt+zjy7xSIDhxO7pPVyYM6sb4Qd2YMKgbfdNTsLb4b0+aTEHQWhRsgzfugI0fw5DJcNl/Htt10q2JO2TPCY4Oqsrh/AfgjNta9OigusbJ3l7I/LV5zF+3u67hA0j2Ss5kOdP4lCkspAtlFJLGR0zkPc7iH5xMlR25O6GquobSsJOYEOR2ry4dD7uipG/Gwe89O3eMuOvH3ckrDl09Unsidc/+upAoOcqJxbKKahZv3ceSLfsoCl0Fk9EpmQkDg0Z//MBujBuQTqcO7eycjkRMQRBr7rDkOZh3fzBeyLSfBFfetKc9seKd8NZdsHYuDDgDZj4GPU+K2sflFR/gL+vzmL8ujwXr8ti3vxIzOKV/Bqf16cSw0oWM2fcxIwsXkFJdQlliF9ZknMvKjKls6jKB6oTIu30SzOjdtePBk48ZqfTq0rHF+nvdg3ML4deUbwq7kqf28sfhvTszfuDBvf0Te6Zpb1/qKAhiqXB7cBTw5YdBv/PMR5v3FvrWxB2W/wne+UHQDTP1QZh0KyQcf4NZVV3D0m0Fob3+PLK3FwLQs3MHzh2WyZRh6ZyXvIouX74ddFWVF0LH9IN9/kMmQ1KH466jtXF39u2vJDHBSE+NPNwk/igIYsE9uC/g3R9BTRVc8O+Q9Z1maRRbvaJceOt7weWXA88Kwq/H0CZvJrewjAXrgob/L+v3UFxeRWKCMX5gBlNG9GLySRmMLltKwqrXYM2bBxv/kRfDmK8FJ+HbYeMvciwUBC2taAe8eWcwiuCgs4OGsPuJsa6qZbnDFy/COz8MbqC64GE4/eYjBuGBqmoWb97H/FDjv2ZnMQAndE1hyohMJg/P5Kwh6aTv/DR0R+dbwRDCHbvCyEuCAcGGnhf74Y1FWiE
|
2021-12-20 04:59:37 +01:00
|
|
|
"text/plain": [
|
|
|
|
|
"<Figure size 432x288 with 1 Axes>"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
"metadata": {
|
|
|
|
|
"needs_background": "light"
|
|
|
|
|
},
|
|
|
|
|
"output_type": "display_data"
|
2021-12-19 23:09:15 +01:00
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
2021-12-20 04:59:37 +01:00
|
|
|
"plt.plot(history.history['accuracy'], label='accuracy')\n",
|
|
|
|
|
"plt.plot(history.history['val_accuracy'], label = 'val_accuracy')\n",
|
|
|
|
|
"plt.xlabel('Epoch')\n",
|
|
|
|
|
"plt.ylabel('Accuracy')\n",
|
|
|
|
|
"plt.ylim([0.5, 1])\n",
|
|
|
|
|
"plt.legend(loc='lower right')"
|
2021-12-19 23:09:15 +01:00
|
|
|
]
|
|
|
|
|
},
|
2021-12-20 06:53:12 +01:00
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"# MLP"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
"execution_count": 21,
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"model = Sequential()\n",
|
|
|
|
|
"model.add(Flatten(input_shape=(img_height, img_width, 3), name=\"Input_layer\"))\n",
|
|
|
|
|
"model.add(Dense(350, activation='relu'))\n",
|
|
|
|
|
"model.add(Dense(50, activation='relu'))\n",
|
|
|
|
|
"model.add(Dense(3, activation='softmax'))"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
"execution_count": 22,
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"image/png": "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
|
|
|
|
|
"text/plain": [
|
|
|
|
|
"<IPython.core.display.Image object>"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
"execution_count": 22,
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "execute_result"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
|
|
|
|
"plot_model(model, to_file='model3_plot.png', show_shapes=True,show_dtype=True, show_layer_names=True, expand_nested=True,)"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
"execution_count": 23,
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"model.compile(\n",
|
|
|
|
|
" optimizer=RMSprop(learning_rate=0.0001),\n",
|
|
|
|
|
" loss=tf.keras.losses.CategoricalCrossentropy(),\n",
|
|
|
|
|
" metrics=['accuracy'],\n",
|
|
|
|
|
" )"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2021-12-20 06:53:58 +01:00
|
|
|
"execution_count": 24,
|
2021-12-20 06:53:12 +01:00
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"name": "stdout",
|
|
|
|
|
"output_type": "stream",
|
|
|
|
|
"text": [
|
|
|
|
|
"Epoch 1/16\n",
|
|
|
|
|
"48/48 [==============================] - 19s 388ms/step - loss: 1.2904 - accuracy: 0.5216 - val_loss: 0.6917 - val_accuracy: 0.6562\n",
|
|
|
|
|
"Epoch 2/16\n",
|
|
|
|
|
"48/48 [==============================] - 19s 404ms/step - loss: 0.6465 - accuracy: 0.7112 - val_loss: 0.7890 - val_accuracy: 0.6719\n",
|
|
|
|
|
"Epoch 3/16\n",
|
|
|
|
|
"48/48 [==============================] - 18s 383ms/step - loss: 0.5448 - accuracy: 0.7737 - val_loss: 0.4680 - val_accuracy: 0.8594\n",
|
|
|
|
|
"Epoch 4/16\n",
|
|
|
|
|
"48/48 [==============================] - 18s 368ms/step - loss: 0.4313 - accuracy: 0.8452 - val_loss: 0.5577 - val_accuracy: 0.7500\n",
|
|
|
|
|
"Epoch 5/16\n",
|
|
|
|
|
"48/48 [==============================] - 24s 501ms/step - loss: 0.4464 - accuracy: 0.8121 - val_loss: 0.2900 - val_accuracy: 0.7969\n",
|
|
|
|
|
"Epoch 6/16\n",
|
|
|
|
|
"48/48 [==============================] - 21s 438ms/step - loss: 0.3362 - accuracy: 0.8622 - val_loss: 0.2690 - val_accuracy: 0.7969\n",
|
|
|
|
|
"Epoch 7/16\n",
|
|
|
|
|
"48/48 [==============================] - 20s 426ms/step - loss: 0.3143 - accuracy: 0.8954 - val_loss: 0.3525 - val_accuracy: 0.8438\n",
|
|
|
|
|
"Epoch 8/16\n",
|
|
|
|
|
"48/48 [==============================] - 20s 426ms/step - loss: 0.2822 - accuracy: 0.9002 - val_loss: 0.2506 - val_accuracy: 0.9688\n",
|
|
|
|
|
"Epoch 9/16\n",
|
|
|
|
|
"48/48 [==============================] - 19s 398ms/step - loss: 0.2282 - accuracy: 0.9134 - val_loss: 0.3262 - val_accuracy: 0.9219\n",
|
|
|
|
|
"Epoch 10/16\n",
|
|
|
|
|
"48/48 [==============================] - 20s 409ms/step - loss: 0.1698 - accuracy: 0.9452 - val_loss: 0.3116 - val_accuracy: 0.9375\n",
|
|
|
|
|
"Epoch 11/16\n",
|
|
|
|
|
"48/48 [==============================] - 20s 409ms/step - loss: 0.2168 - accuracy: 0.9184 - val_loss: 0.2565 - val_accuracy: 0.9062\n",
|
|
|
|
|
"Epoch 12/16\n",
|
|
|
|
|
"48/48 [==============================] - 20s 409ms/step - loss: 0.2145 - accuracy: 0.9224 - val_loss: 0.1434 - val_accuracy: 1.0000\n",
|
|
|
|
|
"Epoch 13/16\n",
|
|
|
|
|
"48/48 [==============================] - 20s 425ms/step - loss: 0.2573 - accuracy: 0.9295 - val_loss: 0.1047 - val_accuracy: 0.9688\n",
|
|
|
|
|
"Epoch 14/16\n",
|
|
|
|
|
"48/48 [==============================] - 19s 405ms/step - loss: 0.1623 - accuracy: 0.9460 - val_loss: 0.1506 - val_accuracy: 0.9844\n",
|
|
|
|
|
"Epoch 15/16\n",
|
2021-12-20 06:53:58 +01:00
|
|
|
"48/48 [==============================] - 19s 395ms/step - loss: 0.1781 - accuracy: 0.9512 - val_loss: 0.0769 - val_accuracy: 0.9844\n",
|
|
|
|
|
"Epoch 16/16\n",
|
|
|
|
|
"48/48 [==============================] - 18s 383ms/step - loss: 0.2260 - accuracy: 0.9164 - val_loss: 0.2339 - val_accuracy: 0.9844\n"
|
2021-12-20 06:53:12 +01:00
|
|
|
]
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
|
|
|
|
"history = model.fit(train_generator, verbose=1, epochs=16,\n",
|
|
|
|
|
" validation_data = validation_generator, validation_steps = 4)"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2021-12-20 06:53:58 +01:00
|
|
|
"execution_count": 25,
|
2021-12-20 06:53:12 +01:00
|
|
|
"metadata": {},
|
2021-12-20 06:53:58 +01:00
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"text/plain": [
|
|
|
|
|
"<matplotlib.legend.Legend at 0x17d195eb6d0>"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
"execution_count": 25,
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "execute_result"
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"image/png": "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
|
|
|
|
|
"text/plain": [
|
|
|
|
|
"<Figure size 432x288 with 1 Axes>"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
"metadata": {
|
|
|
|
|
"needs_background": "light"
|
|
|
|
|
},
|
|
|
|
|
"output_type": "display_data"
|
|
|
|
|
}
|
|
|
|
|
],
|
2021-12-20 06:53:12 +01:00
|
|
|
"source": [
|
|
|
|
|
"plt.plot(history.history['accuracy'], label='accuracy')\n",
|
|
|
|
|
"plt.plot(history.history['val_accuracy'], label = 'val_accuracy')\n",
|
|
|
|
|
"plt.xlabel('Epoch')\n",
|
|
|
|
|
"plt.ylabel('Accuracy')\n",
|
|
|
|
|
"plt.ylim([0.5, 1])\n",
|
|
|
|
|
"plt.legend(loc='lower right')"
|
|
|
|
|
]
|
|
|
|
|
},
|
2021-12-19 23:09:15 +01:00
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
"execution_count": null,
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": []
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"metadata": {
|
|
|
|
|
"kernelspec": {
|
|
|
|
|
"display_name": "Python 3",
|
|
|
|
|
"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",
|
2021-12-20 06:53:12 +01:00
|
|
|
"version": "3.8.5"
|
2021-12-19 23:09:15 +01:00
|
|
|
}
|
|
|
|
|
},
|
|
|
|
|
"nbformat": 4,
|
|
|
|
|
"nbformat_minor": 5
|
|
|
|
|
}
|
