Skip to content

Instantly share code, notes, and snippets.

@kiransair

kiransair/tf_forum_10130.ipynb Secret

Created August 9, 2022 05:30
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save kiransair/dd07ba560b5907c23349b869ea20fb52 to your computer and use it in GitHub Desktop.
Save kiransair/dd07ba560b5907c23349b869ea20fb52 to your computer and use it in GitHub Desktop.
Download ZIP
TF_Forum_10130.ipynb
Display the source blob
Display the rendered blob
Raw
tf_forum_10130.ipynb
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/kiransair/dd07ba560b5907c23349b869ea20fb52/tf_forum_10130.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"id": "Da9J0GgbIy85"
},
"outputs": [],
"source": [
"import tensorflow as tf\n",
"from tensorflow import keras\n",
"import numpy as np\n",
"import os"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "kvwi47x3I891",
"outputId": "970abb7d-265f-42c0-e059-89aeca9348e6"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz\n",
"11493376/11490434 [==============================] - 0s 0us/step\n",
"11501568/11490434 [==============================] - 0s 0us/step\n"
]
}
],
"source": [
"mnist=keras.datasets.mnist.load_data()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"id": "2u_jnfKII-xM"
},
"outputs": [],
"source": [
"(x_train,y_train),(x_test,y_test)=mnist"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"id": "bbMrsrdAJAqr"
},
"outputs": [],
"source": [
"x_train=x_train.astype('float32')/255\n",
"x_test=x_test.astype('float32')/255"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"id": "FZLaP3LfJCsC"
},
"outputs": [],
"source": [
"y_train=keras.utils.to_categorical(y_train,10)\n",
"y_test=keras.utils.to_categorical(y_test,10)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"id": "mIys4cNkJE2i"
},
"outputs": [],
"source": [
"model=keras.Sequential([\n",
" keras.Input(shape=(28,28,1)),\n",
" keras.layers.Conv2D(32,kernel_size=(3,3),activation='relu'),\n",
" keras.layers.MaxPooling2D(pool_size=(2,2)),\n",
" keras.layers.Conv2D(64,kernel_size=(3,3),activation='relu'),\n",
" keras.layers.MaxPooling2D(pool_size=(2,2)),\n",
" keras.layers.Flatten(),\n",
" keras.layers.Dropout(0.5),\n",
" keras.layers.Dense(10,activation='softmax')\n",
"])"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"id": "fO3ihOooJGr7"
},
"outputs": [],
"source": [
"model.compile(loss=\"categorical_crossentropy\", optimizer='adam',metrics=['accuracy'])"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"id": "GeETDC_jInTy"
},
"outputs": [],
"source": [
"checkpoint_path = \"training_1/cp.ckpt\"\n",
"checkpoint_dir = os.path.dirname(checkpoint_path)\n",
"\n",
"# Create a callback that saves the model's weights\n",
"cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_path,\n",
" save_weights_only=True,\n",
" verbose=1)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "EdQrdnD9LZus",
"outputId": "db6b2c08-221e-4ed6-a520-0569e76d1093"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/3\n",
"1874/1875 [============================>.] - ETA: 0s - loss: 0.2130 - accuracy: 0.9354\n",
"Epoch 1: saving model to training_1/cp.ckpt\n",
"1875/1875 [==============================] - 64s 33ms/step - loss: 0.2130 - accuracy: 0.9354\n",
"Epoch 2/3\n",
"1875/1875 [==============================] - ETA: 0s - loss: 0.0802 - accuracy: 0.9754\n",
"Epoch 2: saving model to training_1/cp.ckpt\n",
"1875/1875 [==============================] - 60s 32ms/step - loss: 0.0802 - accuracy: 0.9754\n",
"Epoch 3/3\n",
"1874/1875 [============================>.] - ETA: 0s - loss: 0.0615 - accuracy: 0.9807\n",
"Epoch 3: saving model to training_1/cp.ckpt\n",
"1875/1875 [==============================] - 60s 32ms/step - loss: 0.0615 - accuracy: 0.9807\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.callbacks.History at 0x7ff417df0dd0>"
]
},
"metadata": {},
"execution_count": 9
}
],
"source": [
"model.fit(x_train,y_train,epochs=3,callbacks=[cp_callback])"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"id": "X23_FrwiJMx0"
},
"outputs": [],
"source": [
"model1=keras.Sequential([\n",
" keras.Input(shape=(28,28,1)),\n",
" keras.layers.Conv2D(32,kernel_size=(3,3),activation='relu'),\n",
" keras.layers.MaxPooling2D(pool_size=(2,2)),\n",
" keras.layers.Conv2D(64,kernel_size=(3,3),activation='relu'),\n",
" keras.layers.MaxPooling2D(pool_size=(2,2)),\n",
" keras.layers.Flatten(),\n",
" keras.layers.Dropout(0.5),\n",
" keras.layers.Dense(10,activation='softmax')\n",
"])"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"id": "g_VjwvccJQfe",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "3ce85db3-24e8-4bb2-fbdf-0e2bf6499073"
},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<tensorflow.python.training.tracking.util.CheckpointLoadStatus at 0x7ff416356310>"
]
},
"metadata": {},
"execution_count": 11
}
],
"source": [
"model1.load_weights(checkpoint_path)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"id": "ro-AlXgyJSdN"
},
"outputs": [],
"source": [
"model1.compile(loss=\"categorical_crossentropy\", optimizer='adam',metrics=['accuracy'])"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "M73f0xxdJU0N",
"outputId": "5e2e7b26-62e8-4225-c4af-f22b3f5afb7a"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/3\n",
"1875/1875 [==============================] - 60s 32ms/step - loss: 0.0547 - accuracy: 0.9829\n",
"Epoch 2/3\n",
"1875/1875 [==============================] - 61s 33ms/step - loss: 0.0464 - accuracy: 0.9855\n",
"Epoch 3/3\n",
"1875/1875 [==============================] - 58s 31ms/step - loss: 0.0435 - accuracy: 0.9867\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.callbacks.History at 0x7ff4145f0e90>"
]
},
"metadata": {},
"execution_count": 13
}
],
"source": [
"model1.fit(x_train,y_train,epochs=3)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"id": "98LpOPeDJW30"
},
"outputs": [],
"source": [
""
]
}
],
"metadata": {
"colab": {
"name": "TF_Forum_10130.ipynb",
"provenance": [],
"collapsed_sections": [],
"authorship_tag": "ABX9TyO0DwnktPlrjy2/n9tPuvp7",
"include_colab_link": true
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment