tensorflow - 为什么这个简单的 CNN 突然失败了?
问题描述
我从本教程视频https://www.youtube.com/watch?v=hSDrJM6fJFM中查看了一些简单的 CNN,并修改了代码,使其使用 MomentumOptimizer 而不是 AdamOptimizer,并使其训练无限期运行仅到 1000。在 i 的 9500 值附近,准确度始终达到 0.085 并永久卡在那里,此后永远不会改变。我对可能导致这种情况的原因感到非常困惑。随着它进展顺利,逐渐提高准确性,然后突然下降到比随机猜测更差并永远停留在那里。
from __future__ import print_function
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
# number 1 to 10 data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
def compute_accuracy(v_xs, v_ys):
global prediction
y_pre = sess.run(prediction, feed_dict={xs: v_xs, keep_prob: 1})
correct_prediction = tf.equal(tf.argmax(y_pre,1), tf.argmax(v_ys,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
result = sess.run(accuracy, feed_dict={xs: v_xs, ys: v_ys, keep_prob: 1})
return result
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
def conv2d(x, W):
# stride [1, x_movement, y_movement, 1]
# Must have strides[0] = strides[3] = 1
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(x):
# stride [1, x_movement, y_movement, 1]
return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')
# define placeholder for inputs to network
xs = tf.placeholder(tf.float32, [None, 784])/255. # 28x28
ys = tf.placeholder(tf.float32, [None, 10])
keep_prob = tf.placeholder(tf.float32)
x_image = tf.reshape(xs, [-1, 28, 28, 1])
# print(x_image.shape) # [n_samples, 28,28,1]
## conv1 layer ##
W_conv1 = weight_variable([5,5, 1,32]) # patch 5x5, in size 1, out size 32
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) # output size 28x28x32
h_pool1 = max_pool_2x2(h_conv1) # output size 14x14x32
## conv2 layer ##
W_conv2 = weight_variable([5,5, 32, 64]) # patch 5x5, in size 32, out size 64
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2) # output size 14x14x64
h_pool2 = max_pool_2x2(h_conv2) # output size 7x7x64
## fc1 layer ##
W_fc1 = weight_variable([7*7*64, 1024])
b_fc1 = bias_variable([1024])
# [n_samples, 7, 7, 64] ->> [n_samples, 7*7*64]
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
## fc2 layer ##
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
prediction = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
# the error between prediction and real data
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),reduction_indices=[1])) # loss
train_step = tf.train.MomentumOptimizer(1e-4, 0.999).minimize(cross_entropy)
sess = tf.Session()
init = tf.global_variables_initializer()
sess.run(init)
for i in range(100000):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_step, feed_dict={xs: batch_xs, ys: batch_ys, keep_prob: 0.5})
if i % 50 == 0:
print(i, compute_accuracy(mnist.test.images[:1000], mnist.test.labels[:1000]))
这是我运行的代码,我非常感谢任何帮助解决这个谜的帮助,谢谢。
解决方案
推荐阅读
- java - 如何实时远程调试更改
- prolog - Prolog 中的“循环”,用 `fail` 替换目标
- javascript - 如何从 JSON 数组中获取值
- bash - 从一个文件中删除另一个文件中没有密钥的行
- python - Python pandas - 基于其他列的新列(字符串)
- azure - 并行更新管理 - Azure
- python - 在 CSV 列 python 中查找差异
- system-verilog - 是否可以使用带有 DPI 的打包结构
- amazon-web-services - CloudFormation中多个ECS服务定义之间如何使用同一套环境变量
- templates - 在 VS Code 中创建新的 Flutter Web 项目时的 Dart 模板请求