https://tensorflow.google.cn/tutorials/keras/classification

解决方案

#!usr/bin/env python
# -*- coding:utf-8 _*-
"""
@version: 0.0.1
author: ShenTuZhiGang
@time: 2021/01/25 16:33
@file: 12.py
@function:
@modify:
"""from tensorflow import keras
import tensorflow as tf
import mnist_reader
import numpy as np
import matplotlib.pyplot as plt
from tensorflow import summary
import datetimecurrent_time = str(datetime.datetime.now().timestamp())
train_log_dir = '/content/drive/My Drive/colab notebooks/output/tsboardx/train/' + current_time
test_log_dir = '/content/drive/My Drive/colab notebooks/output/tsboardx/test/' + current_time
val_log_dir = '/content/drive/My Drive/colab notebooks/output/tsboardx/val/' + current_time
train_summary_writer = summary.create_file_writer(train_log_dir)
val_summary_writer = summary.create_file_writer(val_log_dir)
test_summary_writer = summary.create_file_writer(test_log_dir)
(train_images, train_labels), (test_images, test_labels) = mnist_reader.load_data('../data/fashion')
class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat','Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']
train_images = train_images / 255.0test_images = test_images / 255.0plt.figure(figsize=(10,10))
for i in range(25):plt.subplot(5,5,i+1)plt.xticks([])plt.yticks([])plt.grid(False)plt.imshow(train_images[i], cmap=plt.cm.binary)plt.xlabel(class_names[train_labels[i]])
plt.show()class FashionMnistModel(keras.Model):def __init__(self, **kwargs):super().__init__(**kwargs)self.input_ = keras.layers.Flatten(input_shape=[28, 28])self.hidden1 = keras.layers.Dense(128, activation="relu")self.main_output = keras.layers.Dense(10)def call(self, inputs, **kwargs):input_a = self.input_(inputs)hidden1 = self.hidden1(input_a)output = self.main_output(hidden1)return outputmodel = FashionMnistModel()
model.build(input_shape=(0, 28, 28))
model.summary()
model.compile(optimizer='adam',loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),metrics=['accuracy'])
history = model.fit(train_images, train_labels, epochs=10)
test_loss, test_acc = model.evaluate(test_images,  test_labels, verbose=2)
with test_summary_writer.as_default():summary.scalar('loss', test_loss, 10)summary.scalar('accuracy', test_acc, 10)
print('\nTest accuracy:', test_acc)
probability_model = tf.keras.Sequential([model,tf.keras.layers.Softmax()])
predictions = probability_model.predict(test_images)
print(predictions[0])
print(np.argmax(predictions[0]))
print(test_labels[0])def plot_image(i, predictions_array, true_label, img):predictions_array, true_label, img = predictions_array, true_label[i], img[i]plt.grid(False)plt.xticks([])plt.yticks([])plt.imshow(img, cmap=plt.cm.binary)predicted_label = np.argmax(predictions_array)if predicted_label == true_label:color = 'blue'else:color = 'red'plt.xlabel("{} {:2.0f}% ({})".format(class_names[predicted_label],100*np.max(predictions_array),class_names[true_label]),color=color)def plot_value_array(i, predictions_array, true_label):predictions_array, true_label = predictions_array, true_label[i]plt.grid(False)plt.xticks(range(10))plt.yticks([])thisplot = plt.bar(range(10), predictions_array, color="#777777")plt.ylim([0, 1])predicted_label = np.argmax(predictions_array)thisplot[predicted_label].set_color('red')thisplot[true_label].set_color('blue')i = 0
plt.figure(figsize=(6, 3))
plt.subplot(1, 2, 1)
plot_image(i, predictions[i], test_labels, test_images)
plt.subplot(1, 2, 2)
plot_value_array(i, predictions[i], test_labels)
plt.show()i = 12
plt.figure(figsize=(6,3))
plt.subplot(1,2,1)
plot_image(i, predictions[i], test_labels, test_images)
plt.subplot(1,2,2)
plot_value_array(i, predictions[i],  test_labels)
plt.show()# Plot the first X test images, their predicted labels, and the true labels.
# Color correct predictions in blue and incorrect predictions in red.
num_rows = 5
num_cols = 3
num_images = num_rows*num_cols
plt.figure(figsize=(2*2*num_cols, 2*num_rows))
for i in range(num_images):plt.subplot(num_rows, 2*num_cols, 2*i+1)plot_image(i, predictions[i], test_labels, test_images)plt.subplot(num_rows, 2*num_cols, 2*i+2)plot_value_array(i, predictions[i], test_labels)
plt.tight_layout()
plt.show()# Grab an image from the test dataset.
img = test_images[1]print(img.shape)# Add the image to a batch where it's the only member.
img = (np.expand_dims(img,0))print(img.shape)predictions_single = probability_model.predict(img)print(predictions_single)plot_value_array(1, predictions_single[0], test_labels)
_ = plt.xticks(range(10), class_names, rotation=45)print(np.argmax(predictions_single[0]))

参考文章

TensorFlow——本地加载fashion-mnist数据集

TensorFlow 教程——基本分类：对服装图像进行分类

TensorFlow——基于Keras子类API的fashion-mnist数据集图像分类相关推荐

TensorFlow(Keras) 一步步实现Fashion MNIST衣服鞋子图片分类 (2) Coursera深度学习教程分享
@[TOC](Coursera TensorFlow(Keras) 一步步手写体Fashion Mnist识别分类(2) Tensorflow和ML, DL 机器学习/深度学习Coursera教程分享 ...
fashionmnist数据集_Keras实现Fashion MNIST数据集分类
本篇用keras构建人工神经网路(ANN)和卷积神经网络(CNN)实现Fashion MNIST 数据集单个物品分类,并从模型预测的准确性方面对ANN和CNN进行简单比较. Fashion MNIST ...
python cnn程序_python cnn训练（针对Fashion MNIST数据集）
本文将和大家一起一步步尝试对Fashion MNIST数据集进行调参,看看每一步对模型精度的影响.(调参过程中,基础模型架构大致保持不变) 废话不多说,先上任务: 模型的主体框架如下(此为拿到的原始代 ...
DL之DCGNN：基于TF利用DCGAN实现在MNIST数据集上训练生成新样本
DL之DCGNN:基于TF利用DCGAN实现在MNIST数据集上训练生成新样本目录输出结果设计思路实现部分代码说明:所有图片文件丢失输出结果更新-- 设计思路更新-- 实现部分代码更 ...
基于jupyter notebook的python编程-----MNIST数据集的的定义及相关处理学习
基于jupyter notebook的python编程-----MNIST数据集的相关处理一.MNIST定义 1.什么是MNIST数据集 2.python如何导入MNIST数据集并操作 3.接下来, ...
Fashion MNIST数据集的处理——“...-idx3-ubyte”文件解析
Fashion MNIST MNIST数据集可能是计算机视觉所接触的第一个图片数据集.而 Fashion MNIST 是在遵循 MNIST 的格式和大小的基础上,提升了一定的难度,在比较算法的性能时可 ...
Tensorflow 笔记 XIII——“百无聊赖”：深挖 mnist 数据集与 fashion-mnist 数据集的读取原理，经典数据的读取你真的懂了吗？
文章目录数据集简介 Mnist 出门右转 Fashion-Mnist 数据集制作需求来源写给专业的机器学习研究者获取数据类别标注读取原理原理获取 TRAINING SET LABEL FI ...
深度学习之利用TensorFlow实现简单的卷积神经网络（MNIST数据集）
卷积神经网络(Convolutional Neural Networks, CNN)是一类包含卷积计算且具有深度结构的前馈神经网络(Feedforward Neural Networks),是深度学习 ...
基于Python实现的神经网络分类MNIST数据集
神经网络分类MNIST数据集目录神经网络分类MNIST数据集 1 一 .问题背景 1 1.1 神经网络简介 1 前馈神经网络模型: 1 1.2 MINST 数据说明 4 1.3 TensorFlo ...

TensorFlow——基于Keras子类API的fashion-mnist数据集图像分类

解决方案

参考文章

TensorFlow——基于Keras子类API的fashion-mnist数据集图像分类相关推荐

最新文章

热门文章