我使用张量流 0.9。
我想保存我的模型然后恢复它。
我只需添加tf.train.Saver()以保存和恢复我的训练变量。
这是我的代码：
import tensorflow as tf
import input_data
import os
checkpoint_dir='./ckpt_dir/'
mnist = input_data.read_data_sets("MNIST_data", one_hot = True)
x = tf.placeholder(tf.float32, shape = [None , 784])
y_ = tf.placeholder(tf.float32, [None, 10])
sess = tf.InteractiveSession()
def load_model(sess, saver, checkpoint_dir ):
ckpt = tf.train.get_checkpoint_state(checkpoint_dir)
if ckpt and ckpt.model_checkpoint_path:
print(ckpt.model_checkpoint_path)
saver.restore(sess, ckpt.model_checkpoint_path)
else:
if not os.path.exists(checkpoint_dir):
os.makedirs(checkpoint_dir)
sess.run(init)
return
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):
return tf.nn.conv2d(x, W, strides = [1, 1, 1, 1], padding = "SAME")
def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize = [1, 2, 2, 1], strides = [1, 2, 2, 1],
padding = "SAME")
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
x_image = tf.reshape(x, [-1, 28, 28, 1])
#
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1))
h_pool1 = max_pool_2x2(h_conv1)
#
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2))
h_pool2 = max_pool_2x2(h_conv2)
W_fc1 = weight_variable([7764, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, 7764])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
#
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
#
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop,W_fc2) +b_fc2)
#
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y_conv), reduction_indices = [1]))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
init = tf.initialize_all_variables()
saver = tf.train.Saver()
load_model(sess, saver, checkpoint_dir)
for i in range(1):
batch = mnist.train.next_batch(50)
if i%10 == 0:
train_accuracy = accuracy.eval(feed_dict = {x : batch[0] , y_ : batch[1], keep_prob : 1.0})
print("step %d, training accuracy %g"%(i, train_accuracy))
train_step.run(feed_dict = {x : batch[0], y_ : batch[1], keep_prob : 0.5})
print("test accuracy %g"%accuracy.eval(feed_dict={
x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))
tf.scalar_summary("accuracy", accuracy)
saver.save(sess,checkpoint_dir+'model.ckpt')
当我恢复检查点时：
saver.restore(sess, ckpt.model_checkpoint_path)
TensorFlow 抛出此错误：
Traceback (most recent call last):
.
.
.
NotFoundError: Tensor name "global_step_7" not found in checkpoint files ./ckpt_dir/model.ckpt-0
[[Node: save_18/restore_slice_438 = RestoreSlicedt=DT_INT32, preferred_shard=-1, _device="/job:localhost/replica:0/task:0/cpu:0"]]
Caused by op 'save_18/restore_slice_438', defined at:
File "/home/m/anaconda3/lib/python3.5/site-packages/spyderlib/widgets/externalshell/start_ipython_kernel.py", line 205, in
ipythonkernel.start()
.
.
.
File "/home/m/anaconda3/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 1224, in __init
raise TypeError("Control input must be an Operation, "
编辑：
我用蟒蛇。我第一次使用“run filename.py”在 spyder 或 ipython 中运行此代码时，它会将模型保存在检查点中，但是当我再次运行此代码时，它会引发错误。
但是当我关闭 spyder 或 ipython 时，再次打开它并运行它可以正确恢复检查点的代码。
此外，当我在终端“python filename.py”中运行时，它总是运行并且不会抛出任何错误。