mnist2.ipynb · sdau20171754/deeplearning

Create your Gitee Account

Explore and code with more than 12 million developers，Free private repositories ！：）

This repository doesn't specify license. Please pay attention to the specific project description and its upstream code dependency when using it.

Clone or Download

mnist2.ipynb 6.23 KB

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import tensorflow as tf\n",
    "from tensorflow.keras.optimizers import SGD\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(60000, 28, 28)\n",
      "(60000,)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([[0., 0., 0., ..., 0., 0., 0.],\n",
       "       [1., 0., 0., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 0., 0.],\n",
       "       ...,\n",
       "       [0., 0., 0., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 1., 0.]], dtype=float32)"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mnist=tf.keras.datasets.mnist\n",
    "(x_train,y_train),(x_test,y_test)=mnist.load_data()\n",
    "x_train,x_test=x_train/255.0,x_test/255.0\n",
    "print(x_train.shape)\n",
    "print(y_train.shape)\n",
    "y_train=tf.keras.utils.to_categorical(y_train,num_classes=10)\n",
    "y_test=tf.keras.utils.to_categorical(y_test,num_classes=10)\n",
    "y_train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "mnist_train=tf.data.Dataset.from_tensor_slices((x_train,y_train))\n",
    "mnist_train=mnist_train.repeat(1)\n",
    "mnist_train=mnist_train.batch(32)#每次取32个数据\n",
    "mnist_test=tf.data.Dataset.from_tensor_slices((x_test,y_test))\n",
    "mnist_test=mnist_test.repeat(1)\n",
    "mnist_test=mnist_test.batch(32)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "model=tf.keras.models.Sequential([\n",
    "    tf.keras.layers.Flatten(input_shape=(28,28)),\n",
    "    tf.keras.layers.Dense(10,activation='softmax')\n",
    "])\n",
    "optimizer=tf.keras.optimizers.SGD(0.1)\n",
    "train_loss=tf.keras.metrics.Mean(name='train_loss')\n",
    "train_accuracy=tf.keras.metrics.CategoricalAccuracy(name='train_accuracy')\n",
    "test_loss=tf.keras.metrics.Mean(name='test_loss')\n",
    "test_accuracy=tf.keras.metrics.CategoricalAccuracy(name='test_accuracy')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "@tf.function\n",
    "def train_step(data,label):\n",
    "    with tf.GradientTape() as tape:\n",
    "        predictions=model(data)\n",
    "        loss=tf.keras.losses.MSE(label,predictions)\n",
    "        gradients=tape.gradient(loss,model.trainable_variables)\n",
    "        optimizer.apply_gradients(zip(gradients,model.trainable_variables))\n",
    "        train_loss(loss)\n",
    "        train_accuracy(label,predictions)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "@tf.function\n",
    "def test_step(data,label):\n",
    "    predictions=model(data)\n",
    "    t_loss=tf.keras.losses.MSE(label,predictions)\n",
    "    test_loss(t_loss)\n",
    "    test_accuracy(label,predictions)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:Layer flatten is casting an input tensor from dtype float64 to the layer's dtype of float32, which is new behavior in TensorFlow 2.  The layer has dtype float32 because it's dtype defaults to floatx.\n",
      "\n",
      "If you intended to run this layer in float32, you can safely ignore this warning. If in doubt, this warning is likely only an issue if you are porting a TensorFlow 1.X model to TensorFlow 2.\n",
      "\n",
      "To change all layers to have dtype float64 by default, call `tf.keras.backend.set_floatx('float64')`. To change just this layer, pass dtype='float64' to the layer constructor. If you are the author of this layer, you can disable autocasting by passing autocast=False to the base Layer constructor.\n",
      "\n",
      "epoch 1,loss 0.017,Accuracy 0.893,Test loss:0.0139,test accuracy0.909\n",
      "epoch 2,loss 0.0149,Accuracy 0.905,Test loss:0.0134,test accuracy0.911\n",
      "epoch 3,loss 0.014,Accuracy 0.91,Test loss:0.0131,test accuracy0.913\n",
      "epoch 4,loss 0.0134,Accuracy 0.914,Test loss:0.0129,test accuracy0.914\n",
      "epoch 5,loss 0.013,Accuracy 0.917,Test loss:0.0127,test accuracy0.916\n"
     ]
    }
   ],
   "source": [
    "epochs=5\n",
    "#5个周期\n",
    "for epoch in range(epochs):\n",
    "    for image,label in mnist_train:\n",
    "        train_step(image,label)\n",
    "    for test_image,test_label in mnist_test:\n",
    "        test_step(test_image,test_label)\n",
    "    template='epoch {},loss {:.3},Accuracy {:.3},Test loss:{:.3},test accuracy{:.3}'\n",
    "    print(template.format(epoch+1,\n",
    "                          train_loss.result(),\n",
    "                          train_accuracy.result(),\n",
    "                          test_loss.result(),\n",
    "                          test_accuracy.result()\n",
    "                         ))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:tensorflow]",
   "language": "python",
   "name": "conda-env-tensorflow-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.6"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}

Copy Edit Raw Blame History

authored 2020-02-14 16:11 . tensorflow基础

https://gitee.com/sdau20171754/deeplearning.git

git@gitee.com:sdau20171754/deeplearning.git

sdau20171754

deeplearning

master

sdau20171754 / deeplearning

About

Releases

Contributors

Activities