tensorflow学习笔记(六):cnn过程可视化
来源:互联网 发布:美国传播学专业知乎 编辑:程序博客网 时间:2024/05/01 23:34
import tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_dataimport osimport matplotlib.pyplot as pltos.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'mnist = input_data.read_data_sets('MNIST_data',one_hot=True)# print mnist.train.images.shape,mnist.train.labels.shape# (55000, 784) (55000, 10)# 784 = 28*28# print mnist.test.images.shape,mnist.test.labels.shape\# (10000, 784) (10000, 10)# print mnist.validation.images.shape,mnist.validation.labels.shape# (5000, 784) (5000, 10)def Weight_value(shape): init = tf.random_normal(shape, stddev=0.1) return tf.Variable(init, name="weight")def bias_value(shape): init = tf.constant(0.1, shape=shape) return tf.Variable(init)def conv2d(x, W): return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding="SAME")def pool_2x2(x): return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding="SAME")xs = tf.placeholder(tf.float32, [None, 784])ys = tf.placeholder(tf.float32, [None, 10])x_image = tf.reshape(xs, [-1, 28, 28, 1])# layer1 conv1 [-1, 28, 28, 32]W_conv1 = Weight_value([5, 5, 1, 32])b_conv1 = bias_value([32])h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1)+b_conv1)# layer2 pool1 [-1, 14, 14, 32]h_pool1 = pool_2x2(h_conv1)# layer3 conv2 [-1, 14, 14, 64]W_conv2 = Weight_value([5, 5, 32, 64])b_conv2 = bias_value([64])h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2)+b_conv2)# layer4 pool2 [-1,7,7,64]h_pool2 = pool_2x2(h_conv2)# layer5 fc1 [-1,1024]h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])W_fc1 = Weight_value([7*7*64, 1024])b_fc1 = bias_value([1024])h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1)+b_fc1)#layer6 dropoutkeep_prob = tf.placeholder(tf.float32)h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)# layer7 fc2 [-1,10]W_fc2 = Weight_value([1024, 10])b_fc2 = bias_value([10])y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2)+b_fc2)# cross_entropycross_entropy = tf.reduce_mean(-tf.reduce_sum(ys*tf.log(y_conv), reduction_indices=[1]))# optimizertrain_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)# accuracycorrect_prediction = tf.equal(tf.argmax(ys, 1), tf.argmax(y_conv, 1))accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))# initinit = tf.global_variables_initializer()# sesswith tf.Session() as sess: sess.run(init) img1 = mnist.train.images[1] img1.shape = [1, 784] result = sess.run(h_conv1, feed_dict={xs : img1}) for i in range(32): show_img = result[:, :, :, i] # print type(show_img) show_img.shape = [28, 28] plt.subplot(4, 8, i + 1) plt.imshow(show_img, cmap='gray') plt.axis('off') plt.show() # for i in range(1001): # x_batch, y_batch = mnist.train.next_batch(50) # sess.run(train_step, feed_dict={xs:x_batch, ys:y_batch, keep_prob:0.5}) # if i%100 == 0: # x_test, y_test = mnist.test.next_batch(50) # print i, ' step train ', sess.run(accuracy, feed_dict={xs: x_batch, ys: y_batch, keep_prob: 1}) # print i, ' step test', sess.run(accuracy, feed_dict={xs:x_test, ys:y_test, keep_prob: 1})
可以看出32个卷积核对图片特征的提取
阅读全文
0 0
- tensorflow学习笔记(六):cnn过程可视化
- TensorFlow学习笔记(四):Tensorflow网络构建和TensorBoard进行训练过程可视化
- tensorflow学习笔记(五):cnn
- TensorFlow学习笔记(六)
- TensorFlow学习笔记(六)
- tensorflow学习笔记(七):tensorboard可视化
- tensorflow 学习笔记6 TensorBoard可视化神经网络过程
- Python学习笔记(六):数据可视化
- tensorflow学习笔记(二十一):tensorflow可视化
- Tensorflow深度学习笔记(九)--卷积神经网络(CNN)
- TensorFlow学习笔记(3)----CNN识别MNIST手写数字
- tensorflow学习笔记五:mnist实例--卷积神经网络(CNN)
- TensorFlow学习笔记8:CNN搭建(layer,estimator等)
- TensorFlow学习笔记(六)Variable变量
- python tensorflow学习笔记(六)最小二乘法
- Tensorflow cnn网络 vgg可视化
- TensorFlow学习笔记2:构建CNN模型
- TensorFlow学习笔记--CNN精要及实现
- LA -- 3695 Distant Galaxy 【思维】
- DB和DBMS
- 频道管理(第二步)
- 简单的js实现放大镜效果
- HDU 6161 Big binary tree(树形DP)
- tensorflow学习笔记(六):cnn过程可视化
- iOS关于模块化开发解决方案(纯干货)
- 常考排序算法
- android ril 深度学习
- UVa 11148 Hyper Prefix Sets (Trie)
- 毕业以后上百万大学生去哪了
- 计算机学习网站汇总
- 如何批量修改Word文档中的表格样式和题注格式?
- 富文本编辑器react-quill的使用