Skip to content

Instantly share code, notes, and snippets.

@agrhn

agrhn/vggnet_transfer_learning_tensorflow.ipynb

Created January 20, 2021 10:31
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save agrhn/b998029a7c602973b1a31369d4ea0b81 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save agrhn/b998029a7c602973b1a31369d4ea0b81 to your computer and use it in GitHub Desktop.
Download ZIP
VGGNet_Transfer_Learning_Tensorflow.ipynb
Display the source blob
Display the rendered blob
Raw
vggnet_transfer_learning_tensorflow.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "VGGNet_Transfer_Learning_Tensorflow.ipynb",
"provenance": [],
"collapsed_sections": [],
"authorship_tag": "ABX9TyOagkyjbImYIprEN2JqONie",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"accelerator": "GPU"
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/mrgrhn/b998029a7c602973b1a31369d4ea0b81/vggnet_transfer_learning_tensorflow.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "code",
"metadata": {
"id": "vk5qZTNi7CnP"
},
"source": [
"import tensorflow as tf\r\n",
"import matplotlib.pyplot as plt\r\n",
"from tensorflow.keras import datasets, layers, models, losses, Model"
],
"execution_count": 1,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "Wfojd2Md7TF9"
},
"source": [
"(x_train, y_train), (x_test, y_test)=tf.keras.datasets.mnist.load_data()\r\n",
"x_train = tf.pad(x_train, [[0, 0], [2,2], [2,2]])/255\r\n",
"x_test = tf.pad(x_test, [[0, 0], [2,2], [2,2]])/255\r\n",
"x_train = tf.expand_dims(x_train, axis=3, name=None)\r\n",
"x_test = tf.expand_dims(x_test, axis=3, name=None)\r\n",
"x_train = tf.repeat(x_train, 3, axis=3)\r\n",
"x_test = tf.repeat(x_test, 3, axis=3)\r\n",
"x_val = x_train[-2000:,:,:]\r\n",
"y_val = y_train[-2000:]\r\n",
"x_train = x_train[:-2000,:,:]\r\n",
"y_train = y_train[:-2000]"
],
"execution_count": 2,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "aO3hOirPYric"
},
"source": [
"base_model = tf.keras.applications.VGG16(weights = 'imagenet', include_top = False, input_shape = (32,32,3))\r\n",
"for layer in base_model.layers:\r\n",
" layer.trainable = False"
],
"execution_count": 3,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "VmL5rReIY9T6",
"outputId": "1779c7ba-c77d-4731-d92d-cdba8441cbe9"
},
"source": [
"base_model.summary()"
],
"execution_count": 4,
"outputs": [
{
"output_type": "stream",
"text": [
"Model: \"vgg16\"\n",
"_________________________________________________________________\n",
"Layer (type) Output Shape Param # \n",
"=================================================================\n",
"input_1 (InputLayer) [(None, 32, 32, 3)] 0 \n",
"_________________________________________________________________\n",
"block1_conv1 (Conv2D) (None, 32, 32, 64) 1792 \n",
"_________________________________________________________________\n",
"block1_conv2 (Conv2D) (None, 32, 32, 64) 36928 \n",
"_________________________________________________________________\n",
"block1_pool (MaxPooling2D) (None, 16, 16, 64) 0 \n",
"_________________________________________________________________\n",
"block2_conv1 (Conv2D) (None, 16, 16, 128) 73856 \n",
"_________________________________________________________________\n",
"block2_conv2 (Conv2D) (None, 16, 16, 128) 147584 \n",
"_________________________________________________________________\n",
"block2_pool (MaxPooling2D) (None, 8, 8, 128) 0 \n",
"_________________________________________________________________\n",
"block3_conv1 (Conv2D) (None, 8, 8, 256) 295168 \n",
"_________________________________________________________________\n",
"block3_conv2 (Conv2D) (None, 8, 8, 256) 590080 \n",
"_________________________________________________________________\n",
"block3_conv3 (Conv2D) (None, 8, 8, 256) 590080 \n",
"_________________________________________________________________\n",
"block3_pool (MaxPooling2D) (None, 4, 4, 256) 0 \n",
"_________________________________________________________________\n",
"block4_conv1 (Conv2D) (None, 4, 4, 512) 1180160 \n",
"_________________________________________________________________\n",
"block4_conv2 (Conv2D) (None, 4, 4, 512) 2359808 \n",
"_________________________________________________________________\n",
"block4_conv3 (Conv2D) (None, 4, 4, 512) 2359808 \n",
"_________________________________________________________________\n",
"block4_pool (MaxPooling2D) (None, 2, 2, 512) 0 \n",
"_________________________________________________________________\n",
"block5_conv1 (Conv2D) (None, 2, 2, 512) 2359808 \n",
"_________________________________________________________________\n",
"block5_conv2 (Conv2D) (None, 2, 2, 512) 2359808 \n",
"_________________________________________________________________\n",
"block5_conv3 (Conv2D) (None, 2, 2, 512) 2359808 \n",
"_________________________________________________________________\n",
"block5_pool (MaxPooling2D) (None, 1, 1, 512) 0 \n",
"=================================================================\n",
"Total params: 14,714,688\n",
"Trainable params: 0\n",
"Non-trainable params: 14,714,688\n",
"_________________________________________________________________\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "oQS-ROZaZCbo"
},
"source": [
"x = layers.Flatten()(base_model.output)\r\n",
"x = layers.Dense(4096, activation='relu')(x)\r\n",
"x = layers.Dropout(0.5)(x)\r\n",
"x = layers.Dense(4096, activation='relu')(x)\r\n",
"x = layers.Dropout(0.5)(x)\r\n",
"predictions = layers.Dense(10, activation = 'softmax')(x)"
],
"execution_count": 11,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "5Mwvpskmbz9O"
},
"source": [
"head_model = Model(inputs = base_model.input, outputs = predictions)\r\n",
"head_model.compile(optimizer='adam', loss=losses.sparse_categorical_crossentropy, metrics=['accuracy'])"
],
"execution_count": 12,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "Q23qe_dUcPrf",
"outputId": "0f7550a8-dec9-42fe-ee57-cdbb7ff2f072"
},
"source": [
"head_model.summary()"
],
"execution_count": 13,
"outputs": [
{
"output_type": "stream",
"text": [
"Model: \"model_1\"\n",
"_________________________________________________________________\n",
"Layer (type) Output Shape Param # \n",
"=================================================================\n",
"input_1 (InputLayer) [(None, 32, 32, 3)] 0 \n",
"_________________________________________________________________\n",
"block1_conv1 (Conv2D) (None, 32, 32, 64) 1792 \n",
"_________________________________________________________________\n",
"block1_conv2 (Conv2D) (None, 32, 32, 64) 36928 \n",
"_________________________________________________________________\n",
"block1_pool (MaxPooling2D) (None, 16, 16, 64) 0 \n",
"_________________________________________________________________\n",
"block2_conv1 (Conv2D) (None, 16, 16, 128) 73856 \n",
"_________________________________________________________________\n",
"block2_conv2 (Conv2D) (None, 16, 16, 128) 147584 \n",
"_________________________________________________________________\n",
"block2_pool (MaxPooling2D) (None, 8, 8, 128) 0 \n",
"_________________________________________________________________\n",
"block3_conv1 (Conv2D) (None, 8, 8, 256) 295168 \n",
"_________________________________________________________________\n",
"block3_conv2 (Conv2D) (None, 8, 8, 256) 590080 \n",
"_________________________________________________________________\n",
"block3_conv3 (Conv2D) (None, 8, 8, 256) 590080 \n",
"_________________________________________________________________\n",
"block3_pool (MaxPooling2D) (None, 4, 4, 256) 0 \n",
"_________________________________________________________________\n",
"block4_conv1 (Conv2D) (None, 4, 4, 512) 1180160 \n",
"_________________________________________________________________\n",
"block4_conv2 (Conv2D) (None, 4, 4, 512) 2359808 \n",
"_________________________________________________________________\n",
"block4_conv3 (Conv2D) (None, 4, 4, 512) 2359808 \n",
"_________________________________________________________________\n",
"block4_pool (MaxPooling2D) (None, 2, 2, 512) 0 \n",
"_________________________________________________________________\n",
"block5_conv1 (Conv2D) (None, 2, 2, 512) 2359808 \n",
"_________________________________________________________________\n",
"block5_conv2 (Conv2D) (None, 2, 2, 512) 2359808 \n",
"_________________________________________________________________\n",
"block5_conv3 (Conv2D) (None, 2, 2, 512) 2359808 \n",
"_________________________________________________________________\n",
"block5_pool (MaxPooling2D) (None, 1, 1, 512) 0 \n",
"_________________________________________________________________\n",
"flatten_1 (Flatten) (None, 512) 0 \n",
"_________________________________________________________________\n",
"dense_3 (Dense) (None, 4096) 2101248 \n",
"_________________________________________________________________\n",
"dropout_2 (Dropout) (None, 4096) 0 \n",
"_________________________________________________________________\n",
"dense_4 (Dense) (None, 4096) 16781312 \n",
"_________________________________________________________________\n",
"dropout_3 (Dropout) (None, 4096) 0 \n",
"_________________________________________________________________\n",
"dense_5 (Dense) (None, 10) 40970 \n",
"=================================================================\n",
"Total params: 33,638,218\n",
"Trainable params: 18,923,530\n",
"Non-trainable params: 14,714,688\n",
"_________________________________________________________________\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "YuL7NjAhcUyH",
"outputId": "a8bef6c7-13b7-437b-9cb7-a818961b9c27"
},
"source": [
"history = head_model.fit(x_train, y_train, batch_size=64, epochs=40, validation_data=(x_val, y_val))"
],
"execution_count": 8,
"outputs": [
{
"output_type": "stream",
"text": [
"Epoch 1/40\n",
"907/907 [==============================] - 18s 16ms/step - loss: 0.7102 - accuracy: 0.8044 - val_loss: 0.4429 - val_accuracy: 0.8335\n",
"Epoch 2/40\n",
"907/907 [==============================] - 14s 15ms/step - loss: 0.4784 - accuracy: 0.8454 - val_loss: 0.1808 - val_accuracy: 0.9425\n",
"Epoch 3/40\n",
"907/907 [==============================] - 14s 15ms/step - loss: 0.4286 - accuracy: 0.8658 - val_loss: 0.1467 - val_accuracy: 0.9520\n",
"Epoch 4/40\n",
"907/907 [==============================] - 14s 15ms/step - loss: 0.3487 - accuracy: 0.8904 - val_loss: 0.1191 - val_accuracy: 0.9610\n",
"Epoch 5/40\n",
"907/907 [==============================] - 14s 16ms/step - loss: 0.3357 - accuracy: 0.8932 - val_loss: 0.1072 - val_accuracy: 0.9655\n",
"Epoch 6/40\n",
"907/907 [==============================] - 14s 16ms/step - loss: 0.3307 - accuracy: 0.8948 - val_loss: 0.1158 - val_accuracy: 0.9645\n",
"Epoch 7/40\n",
"907/907 [==============================] - 14s 16ms/step - loss: 0.3294 - accuracy: 0.8968 - val_loss: 0.1158 - val_accuracy: 0.9665\n",
"Epoch 8/40\n",
"907/907 [==============================] - 14s 16ms/step - loss: 0.3189 - accuracy: 0.9002 - val_loss: 0.0934 - val_accuracy: 0.9720\n",
"Epoch 9/40\n",
"907/907 [==============================] - 14s 16ms/step - loss: 0.2941 - accuracy: 0.9091 - val_loss: 0.2546 - val_accuracy: 0.9470\n",
"Epoch 10/40\n",
"907/907 [==============================] - 14s 16ms/step - loss: 0.3437 - accuracy: 0.8950 - val_loss: 0.0951 - val_accuracy: 0.9720\n",
"Epoch 11/40\n",
"907/907 [==============================] - 15s 16ms/step - loss: 0.3289 - accuracy: 0.8987 - val_loss: 0.1061 - val_accuracy: 0.9675\n",
"Epoch 12/40\n",
"907/907 [==============================] - 15s 16ms/step - loss: 0.3184 - accuracy: 0.8987 - val_loss: 0.1366 - val_accuracy: 0.9590\n",
"Epoch 13/40\n",
"907/907 [==============================] - 14s 16ms/step - loss: 0.3047 - accuracy: 0.9050 - val_loss: 0.0940 - val_accuracy: 0.9695\n",
"Epoch 14/40\n",
"907/907 [==============================] - 14s 16ms/step - loss: 0.2907 - accuracy: 0.9086 - val_loss: 0.1182 - val_accuracy: 0.9640\n",
"Epoch 15/40\n",
"907/907 [==============================] - 14s 16ms/step - loss: 0.3064 - accuracy: 0.9053 - val_loss: 0.1031 - val_accuracy: 0.9735\n",
"Epoch 16/40\n",
"907/907 [==============================] - 15s 16ms/step - loss: 0.3090 - accuracy: 0.9044 - val_loss: 0.0854 - val_accuracy: 0.9785\n",
"Epoch 17/40\n",
"907/907 [==============================] - 15s 16ms/step - loss: 0.3272 - accuracy: 0.8971 - val_loss: 0.0923 - val_accuracy: 0.9765\n",
"Epoch 18/40\n",
"907/907 [==============================] - 15s 16ms/step - loss: 0.3005 - accuracy: 0.9083 - val_loss: 0.1163 - val_accuracy: 0.9690\n",
"Epoch 19/40\n",
"907/907 [==============================] - 15s 16ms/step - loss: 0.3080 - accuracy: 0.9027 - val_loss: 0.0857 - val_accuracy: 0.9765\n",
"Epoch 20/40\n",
"907/907 [==============================] - 15s 16ms/step - loss: 0.2964 - accuracy: 0.9059 - val_loss: 0.1024 - val_accuracy: 0.9740\n",
"Epoch 21/40\n",
"907/907 [==============================] - 15s 16ms/step - loss: 0.2978 - accuracy: 0.9061 - val_loss: 0.1049 - val_accuracy: 0.9735\n",
"Epoch 22/40\n",
"907/907 [==============================] - 15s 16ms/step - loss: 0.2812 - accuracy: 0.9123 - val_loss: 0.1198 - val_accuracy: 0.9665\n",
"Epoch 23/40\n",
"907/907 [==============================] - 15s 16ms/step - loss: 0.2782 - accuracy: 0.9127 - val_loss: 0.0903 - val_accuracy: 0.9765\n",
"Epoch 24/40\n",
"907/907 [==============================] - 15s 16ms/step - loss: 0.2823 - accuracy: 0.9116 - val_loss: 0.1149 - val_accuracy: 0.9675\n",
"Epoch 25/40\n",
"907/907 [==============================] - 15s 16ms/step - loss: 0.2916 - accuracy: 0.9100 - val_loss: 0.0905 - val_accuracy: 0.9780\n",
"Epoch 26/40\n",
"907/907 [==============================] - 15s 16ms/step - loss: 0.2974 - accuracy: 0.9076 - val_loss: 0.1140 - val_accuracy: 0.9700\n",
"Epoch 27/40\n",
"907/907 [==============================] - 15s 16ms/step - loss: 0.2820 - accuracy: 0.9108 - val_loss: 0.0907 - val_accuracy: 0.9770\n",
"Epoch 28/40\n",
"907/907 [==============================] - 15s 16ms/step - loss: 0.2922 - accuracy: 0.9079 - val_loss: 0.1081 - val_accuracy: 0.9735\n",
"Epoch 29/40\n",
"907/907 [==============================] - 15s 16ms/step - loss: 0.2740 - accuracy: 0.9125 - val_loss: 0.1167 - val_accuracy: 0.9705\n",
"Epoch 30/40\n",
"907/907 [==============================] - 15s 16ms/step - loss: 0.2833 - accuracy: 0.9105 - val_loss: 0.1350 - val_accuracy: 0.9680\n",
"Epoch 31/40\n",
"907/907 [==============================] - 15s 16ms/step - loss: 0.2809 - accuracy: 0.9123 - val_loss: 0.1522 - val_accuracy: 0.9625\n",
"Epoch 32/40\n",
"907/907 [==============================] - 15s 17ms/step - loss: 0.2756 - accuracy: 0.9139 - val_loss: 0.1338 - val_accuracy: 0.9725\n",
"Epoch 33/40\n",
"907/907 [==============================] - 15s 16ms/step - loss: 0.2986 - accuracy: 0.9059 - val_loss: 0.1006 - val_accuracy: 0.9740\n",
"Epoch 34/40\n",
"907/907 [==============================] - 15s 16ms/step - loss: 0.2953 - accuracy: 0.9065 - val_loss: 0.1540 - val_accuracy: 0.9500\n",
"Epoch 35/40\n",
"907/907 [==============================] - 15s 16ms/step - loss: 0.2864 - accuracy: 0.9121 - val_loss: 0.1199 - val_accuracy: 0.9710\n",
"Epoch 36/40\n",
"907/907 [==============================] - 15s 16ms/step - loss: 0.2794 - accuracy: 0.9127 - val_loss: 0.1140 - val_accuracy: 0.9690\n",
"Epoch 37/40\n",
"907/907 [==============================] - 15s 16ms/step - loss: 0.2711 - accuracy: 0.9133 - val_loss: 0.1501 - val_accuracy: 0.9670\n",
"Epoch 38/40\n",
"907/907 [==============================] - 15s 16ms/step - loss: 0.2810 - accuracy: 0.9117 - val_loss: 0.1356 - val_accuracy: 0.9680\n",
"Epoch 39/40\n",
"907/907 [==============================] - 15s 16ms/step - loss: 0.2698 - accuracy: 0.9151 - val_loss: 0.1454 - val_accuracy: 0.9700\n",
"Epoch 40/40\n",
"907/907 [==============================] - 15s 16ms/step - loss: 0.2771 - accuracy: 0.9127 - val_loss: 0.1397 - val_accuracy: 0.9650\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 910
},
"id": "ii-nX7TwEbOL",
"outputId": "aabb2369-a4eb-4ca9-9eeb-7889ee67a3cc"
},
"source": [
"fig, axs = plt.subplots(2, 1, figsize=(15,15))\r\n",
"\r\n",
"axs[0].plot(history.history['loss'])\r\n",
"axs[0].plot(history.history['val_loss'])\r\n",
"axs[0].title.set_text('Training Loss vs Validation Loss')\r\n",
"axs[0].set_xlabel('Epochs')\r\n",
"axs[0].set_ylabel('Loss')\r\n",
"axs[0].legend(['Train','Val'])\r\n",
"\r\n",
"axs[1].plot(history.history['accuracy'])\r\n",
"axs[1].plot(history.history['val_accuracy'])\r\n",
"axs[1].title.set_text('Training Accuracy vs Validation Accuracy')\r\n",
"axs[1].set_xlabel('Epochs')\r\n",
"axs[1].set_ylabel('Accuracy')\r\n",
"axs[1].legend(['Train', 'Val'])"
],
"execution_count": 9,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.legend.Legend at 0x7f2a6f596240>"
]
},
"metadata": {
"tags": []
},
"execution_count": 9
},
{
"output_type": "display_data",
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 1080x1080 with 2 Axes>"
]
},
"metadata": {
"tags": [],
"needs_background": "light"
}
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "JQ7WooM5E1IA",
"outputId": "adc3bcad-a4be-4969-a760-ae721e03a50b"
},
"source": [
"head_model.evaluate(x_test, y_test)"
],
"execution_count": 10,
"outputs": [
{
"output_type": "stream",
"text": [
"313/313 [==============================] - 3s 9ms/step - loss: 0.1821 - accuracy: 0.9505\n"
],
"name": "stdout"
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"[0.18214020133018494, 0.9505000114440918]"
]
},
"metadata": {
"tags": []
},
"execution_count": 10
}
]
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment