Question

我已经使用以下代码设置了张量流神经网络，并且它的工作非常好：

from master2 import create_feature_sets_and_labels
import tensorflow as tf
import numpy as np
from datetime import datetime as timer

start=timer.now()
train_x,train_y,test_x,test_y = create_feature_sets_and_labels('temp1c.txt','temp2c.txt')

print('Starting neural network')
n_nodes_hl1 = 3

n_classes = 2 #Set to label size
batch_size = 50

x = tf.placeholder('float', [None, len(train_x[0])])
y = tf.placeholder('float')

def neural_network_model(data):
    hidden_1_layer = {'weights':tf.Variable(tf.random_normal([len(train_x[0]), n_nodes_hl1])),
                  'biases':tf.Variable(tf.random_normal([n_nodes_hl1]))}

    output_layer = {'weights':tf.Variable(tf.random_normal([n_nodes_hl1, n_classes])),
                'biases':tf.Variable(tf.random_normal([n_classes])),}

    l1 = tf.add(tf.matmul(data,hidden_1_layer['weights']), hidden_1_layer['biases'])
    l1 = tf.nn.relu(l1)
    output = tf.matmul(l1,output_layer['weights']) + output_layer['biases']
    return output

def train_neural_network(x):
    prediction = neural_network_model(x)
    cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits_v2(logits=prediction, labels=y) )
    optimizer = tf.train.AdamOptimizer().minimize(cost)

    hm_epochs = 50
    with tf.Session() as sess:
        writer = tf.summary.FileWriter("output", sess.graph)
        saver = tf.train.Saver()
        sess.run(tf.global_variables_initializer())
        for epoch in range(hm_epochs):
            epoch_loss = 0
            i=0
            while i < len(train_x):
                start = i
                end = i+batch_size
                batch_x = np.array(train_x[start:end])
                batch_y = np.array(train_y[start:end])
                _, c = sess.run([optimizer, cost], feed_dict={x: batch_x, y: batch_y})
                epoch_loss += c
                i+=batch_size
            print('Epoch', epoch+1, 'completed out of',hm_epochs,'loss:',epoch_loss)
        #print(timer.now()-start)
        correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
        accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
        print('Accuracy:',accuracy.eval({x:test_x, y:test_y}))
        writer.close()
        save_path = saver.save(sess, "model.ckpt")
        print("Model saved in path: %s" % save_path)

train_neural_network(x)
print(timer.now()-start)
print('Done.')

我遇到的问题是在恢复中，我看似无法让模型读回内存。单独文件中的代码是：

import tensorflow as tf
import pandas as pd
import datetime
#lexicon was length 2912 for x[0] above
x = tf.Variable('float', [None, 2912])
y = tf.Variable('float')

saver = tf.train.Saver()
with tf.Session() as sess:
    # Restore variables from disk.
    saver.restore(sess, "model.ckpt")
    print("Model restored.")

有谁知道为什么我无法恢复体重和偏见？错误如下：

DataLossError: Invalid size in bundle entry: key Variable; stored size 11648; expected size 93184
 [[Node: save/RestoreV2 = RestoreV2[dtypes=[DT_STRING], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2/tensor_names, save/RestoreV2/shape_and_slices)]]

Answer 1

解决。这是一个dtype问题。我在原始文件中使用了占位符，并且在Variable类型未对齐时出现问题。

Tensorflow恢复错误

1 个答案: