python3.5下载+tensorflow安装教程 python安装tensorflow的方法

一.python3.5下载（跳过)

下载地址： [https://www.python.org/downloads/release/python-350/] 安装方法： [https://jingyan.baidu.com/article/29697b9158e688ab21de3c75.html]

二.下载anaconda（自带python 3.5）

(相关资料图)

最好下载3-4.2.0 下载地址 安装方法

三.下载安装tensorflow

在anaconda prompt 里敲命令安装tensorflow(一定要用管理员打开anaconda prompt不然可能报cmd 不是内部指令 若无法解决自行百度) 安装方法 https://www.cnblogs.com/ming-4/p/11516728.html 如果出现错误 解决办法 如果该解决方法里的命令不对，看他的评论然后又遇到了 查看python版本和pip版本

实在不行，考虑换镜像。

pip install https://mirrors.tuna.tsinghua.edu.cn/tensorflow/windows/cpu/tensorflow-1.1.0-cp35-cp35m-win_amd64.whl

作者链接

很明显我是小白，走到弯路不比你们少。 （到这的步骤已经搞了一上午） 用Spyder 测试Tensorflow安装成功(感谢凡哥提供,转载于 悲恋花丶无心之人) 如果进入Spyder import tensorflow 没找到 tensorflow 点击参照方法二

四.python 手写体识别

import tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_dataimport osos.environ["TF_CPP_MIN_LOG_LEVEL"] = "2"# 定义一个全局对象来获取参数的值，在程序中使用(eg：FLAGS.iteration)来引用参数FLAGS = tf.app.flags.FLAGS# 设置训练相关参数tf.app.flags.DEFINE_integer("iteration", 10001, "Iterations to train [1e4]")tf.app.flags.DEFINE_integer("disp_freq", 200, "Display the current results every display_freq iterations [1e2]")tf.app.flags.DEFINE_integer("train_batch_size", 100, "The size of batch images [128]")tf.app.flags.DEFINE_float("learning_rate", 0.1, "Learning rate of for adam [0.01]")tf.app.flags.DEFINE_string("log_dir", "logs", "Directory of logs.")def main(argv=None):    # 0、准备训练/验证/测试数据集    mnist = input_data.read_data_sets("MNIST_data", one_hot=True)    # 1、数据输入设计：使用 placeholder 将数据送入网络，None 表示张量的第一个维度可以是任意长度的    with tf.name_scope("Input"):        X = tf.placeholder(dtype=tf.float32, shape=[None, 784], name="X_placeholder")        Y = tf.placeholder(dtype=tf.int32, shape=[None, 10], name="Y_placeholder")    # 2、前向网络设计    with tf.name_scope("Inference"):        W = tf.Variable(initial_value=tf.random_normal(shape=[784, 10], stddev=0.01), name="Weights")        b = tf.Variable(initial_value=tf.zeros(shape=[10]), name="bias")        logits = tf.matmul(X, W) + b        Y_pred = tf.nn.softmax(logits=logits)    # 3、损失函数设计    with tf.name_scope("Loss"):        # 求交叉熵损失        cross_entropy = tf.nn.softmax_cross_entropy_with_logits(labels=Y, logits=logits, name="cross_entropy")        # 求平均        loss = tf.reduce_mean(cross_entropy, name="loss")    # 4、参数学习算法设计    with tf.name_scope("Optimization"):        optimizer = tf.train.GradientDescentOptimizer(FLAGS.learning_rate).minimize(loss)    # 5、评估节点设计    with tf.name_scope("Evaluate"):        # 返回验证集/测试集预测正确或错误的布尔值        correct_prediction = tf.equal(tf.argmax(Y_pred, 1), tf.argmax(Y, 1))        # 将布尔值转换为浮点数后，求平均准确率        accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))    print("~~~~~~~~~~~开始执行计算图~~~~~~~~~~~~~~")    with tf.Session() as sess:        summary_writer = tf.summary.FileWriter(logdir=FLAGS.log_dir, graph=sess.graph)        # 初始化所有变量        sess.run(tf.global_variables_initializer())        total_loss = 0        for i in range(0, FLAGS.iteration):            X_batch, Y_batch = mnist.train.next_batch(FLAGS.train_batch_size)            _, loss_batch = sess.run([optimizer, loss], feed_dict={X: X_batch, Y: Y_batch})            total_loss += loss_batch            if i % FLAGS.disp_freq == 0:                val_acc = sess.run(accuracy, feed_dict={X: mnist.validation.images, Y: mnist.validation.labels})                if i == 0:                    print("step: {}, train_loss: {}, val_acc: {}".format(i, total_loss, val_acc))                else:                    print("step: {}, train_loss: {}, val_acc: {}".format(i, total_loss / FLAGS.disp_freq, val_acc))                total_loss = 0        test_acc = sess.run(accuracy, feed_dict={X: mnist.test.images, Y: mnist.test.labels})        print("test accuracy: {}".format(test_acc))        summary_writer.close()# 执行main函数if __name__ == "__main__":    tf.app.run()

# -*- coding: utf-8 -*-"""Created on Mon Feb 24 16:18:26 2020TREEGER@author: Administrator"""import tensorflow as tfimport sslssl._create_default_https_context = ssl._create_unverified_contextfrom tensorflow.examples.tutorials.mnist import input_datamnist = input_data.read_data_sets("./mnist_data/", one_hot=True)learning_rate = 0.005training_epochs = 20batch_size = 100batch_count = int(mnist.train.num_examples / batch_size)n_hidden_1 = 256n_hidden_2 = 256n_input = 784n_classes = 10  # (0-9 数字)X = tf.placeholder("float", [None, n_input])Y = tf.placeholder("float", [None, n_classes])weights = {"weight1": tf.Variable(tf.random_normal([n_input, n_hidden_1])),    "weight2": tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2])),    "out": tf.Variable(tf.random_normal([n_hidden_2, n_classes]))}biases = {"bias1": tf.Variable(tf.random_normal([n_hidden_1])),    "bias2": tf.Variable(tf.random_normal([n_hidden_2])),    "out": tf.Variable(tf.random_normal([n_classes]))}def multilayer_perceptron_model(x):    layer_1 = tf.add(tf.matmul(x, weights["weight1"]), biases["bias1"])    layer_2 = tf.add(tf.matmul(layer_1, weights["weight2"]), biases["bias2"])    out_layer = tf.matmul(layer_2, weights["out"]) + biases["out"]    return out_layerlogits = multilayer_perceptron_model(X)loss_op = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=Y))optimizer = tf.train.GradientDescentOptimizer(learning_rate)# optimizer = tf.train.MomentumOptimizer(learning_rate,0.2)# optimizer = tf.train.AdagradOptimizer(learning_rate)# optimizer = tf.train.AdamOptimizer(learning_rate)train_op = optimizer.minimize(loss_op)init = tf.global_variables_initializer()  # 参数初始化with tf.Session() as sess:    sess.run(init)    for epoch in range(training_epochs):  # range(150):training_epochs        avg_cost = 0.        for i in range(batch_count):            train_x, train_y = mnist.train.next_batch(batch_size)            _, c = sess.run([train_op, loss_op], feed_dict={X: train_x, Y: train_y})            avg_cost += c / batch_count        print("Epoch:", "%02d" % (epoch + 1), "avg cost={:.6f}".format(avg_cost))        pred = tf.nn.softmax(logits)  # Apply softmax to logits        correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(Y, 1))        accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))        print("Accuracy:", accuracy.eval({X: mnist.test.images, Y: mnist.test.labels}))