python - tensorflow cnn 错误 : InvalidArgumentError (see above for traceback): logits and labels must be same size

Question

这段代码是我根据tensorflow官方教程修改的。我有一个网络如下:

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')

import tensorflow as tf
import numpy as np

train_feature = np.array(model.dataset[0])
train_label = np.array(model.labelset[0])
print(train_feature.shape)
print(train_label.shape)

x_placeholder = tf.placeholder(tf.float32, shape=[None, train_feature.shape[1]])
y_placeholder = tf.placeholder(tf.float32, shape=[None, 8])
# network structure
w_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
x_image = tf.reshape(x_placeholder, [-1, 160, 120, 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([320, 1024])
b_fc1 = bias_variable([1024])

h_pool2_flat = tf.reshape(h_pool2, [-1, 320])
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, 8])
b_fc2 = bias_variable([8])

y_conv = tf.matmul(h_fc1_drop, w_fc2) + b_fc2

cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(y_conv, y_placeholder))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
sess = tf.InteractiveSession()
sess.run(tf.global_variables_initializer())
batch = (train_feature, np.eye(8)[train_label])
train_step.run(feed_dict={x_placeholder: batch[0], y_placeholder: batch[1], keep_prob: 0.5})

错误如下:

cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(y_conv, y_placeholder))
File "/Users/lintseju/anaconda/lib/python3.5/site-packages/tensorflow/python/ops/nn_ops.py", line 1449, in softmax_cross_entropy_with_logits
precise_logits, labels, name=name)
File "/Users/lintseju/anaconda/lib/python3.5/site-packages/tensorflow/python/ops/gen_nn_ops.py", line 2265, in _softmax_cross_entropy_with_logits
features=features, labels=labels, name=name)
File "/Users/lintseju/anaconda/lib/python3.5/site-packages/tensorflow/python/framework/op_def_library.py", line 759, in apply_op
op_def=op_def)
File "/Users/lintseju/anaconda/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 2240, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/Users/lintseju/anaconda/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 1128, in __init__
self._traceback = _extract_stack()

InvalidArgumentError (see above for traceback): logits and labels must be same size: logits_size=[2400,8] labels_size=[10,8]
 [[Node: SoftmaxCrossEntropyWithLogits = SoftmaxCrossEntropyWithLogits[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](Reshape_2, Reshape_3)]]

train_feature是(10, 19200) numpy数组，train label是(10,) numpy数组。有人知道为什么 logits_size=[2400,8] 吗？

Answer 1

在将图像(无论是网络的输入还是卷积 (CONV) 层的某些中间输出)传递到全连接 (FC) 层之前，您必须确保 (1) 您正确地 reshape 了图像进入一维向量以及(2)设置网络权重的维度以与一维向量一致。在您的情况下，切换到 FC 层发生在第二层的池化之后。虽然您确保 h_pool2_flat 具有与第一个 FC 层的权重 w_fc1 兼容的尺寸，但您没有正确设置平面尺寸。在这种情况下，硬编码值 320 不是正确的维度。并且尝试硬编码这可能不是一般的最佳实践，并且每当您对输入的大小或网络的卷积堆栈进行修改时，代码可能会不断中断(例如，通过添加/删除池化层或调整步幅一些层)。

相反，您应该添加一些代码来自动计算平面尺寸，并使用计算值来设置尺寸，如下例所示:

# Here happens conversion from 2/3D images to 1D vectors.
h_pool2_shape = h_pool2.get_shape()
# Don't hard-code the 1D vector dim. Rather, (1) multiply image's height,
# width and depth to get it.
h_pool2_dim = h_pool2_shape[1] * h_pool2_shape[2] * h_pool2_shape[3]
# (2) Use the computed 1D dimension to set the FC1 weight matrix dimensions.
w_fc1 = weight_variable(tf.stack([h_pool2_dim, 1024]))
b_fc1 = bias_variable([1024])
# (3) Use the same 1D dimension to correctly reshape the batch matrix.
h_pool2_flat = tf.reshape(h_pool2, tf.stack([-1, h_pool2_dim]))
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, w_fc1) + b_fc1)