Question

如果我有张量流神经网络，我在这样的测试数据上运行：

   result = sess.run(y_conv, feed_dict={x: test_inputs})

然而，这会有内存问题，所以我试图像这样分解计算：

result = []
for i in range(0, len(test_inputs), 100):
   end = min(i+100 - 1, len(test_inputs)  - 1)
   r = sess.run(y_conv, feed_dict={x: test_inputs.loc[i:end, :]})
   result.append(r)

但是，现在我收到了这个错误：

InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor 'Placeholder_2' with dtype float
     [[Node: Placeholder_2 = Placeholder[dtype=DT_FLOAT, shape=<unknown>, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]

那么这个问题的原因是什么？我原以为网络可以在较小批量的例子上运行良好。

如果这与任何相关性无关，神经网络的创建方式如下：

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) + b_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) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])

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)

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.matmul(h_fc1_drop, W_fc2) + b_fc2

Answer 1

您已将x作为输入，但未提供keep_prob。您的网络与Deep MNIST for Experts类似。一个示例代码段：

train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})

对于推理，您应该将keep_prob更改为1.0。

尝试拆分神经网络测试时出错

1 个答案: