可重复使用的Tensorflow卷积网络

Question

我想重用Tensorflow"MNIST for Pros"CNN示例中的代码.我的图像是388px X 191px,只有2个输出类.原始代码可以在这里找到.我试图通过仅更改输入和输出层来重用此代码,如下所示:

输入层

x = tf.placeholder("float", shape=[None, 74108])

y_ = tf.placeholder("float", shape=[None, 2])

x_image = tf.reshape(x, [-1,388,191,1])

输出层

W_fc2 = weight_variable([1024, 2])

b_fc2 = bias_variable([2])

运行修改后的代码会产生模糊的堆栈跟踪:

W tensorflow/core/common_runtime/executor.cc:1027] 0x2136510 Compute status: Invalid argument: Input has 14005248 values, which isn't divisible by 3136
     [[Node: Reshape_4 = Reshape[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](MaxPool_5, Reshape_4/shape)]]
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1267, in run
    _run_using_default_session(self, feed_dict, self.graph, session)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2763, in _run_using_default_session
    session.run(operation, feed_dict)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 345, in run
    results = self._do_run(target_list, unique_fetch_targets, feed_dict_string)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 419, in _do_run
    e.code)
tensorflow.python.framework.errors.InvalidArgumentError: Input has 14005248 values, which isn't divisible by 3136
     [[Node: Reshape_4 = Reshape[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](MaxPool_5, Reshape_4/shape)]]
Caused by op u'Reshape_4', defined at:
  File "<stdin>", line 1, in <module>
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_array_ops.py", line 554, in reshape
    name=name)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/op_def_library.py", line 633, in apply_op
    op_def=op_def)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1710, in create_op
    original_op=self._default_original_op, op_def=op_def)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 988, in __init__
    self._traceback = _extract_stack()

Answer 1

tensorflow.python.framework.errors.InvalidArgumentError: Input has 14005248 values, which isn't divisible by 3136
 [[Node: Reshape_4 = Reshape[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](MaxPool_5, Reshape_4/shape)]]

但是你执行它的方式会阻止你看到导致问题的实际行.将它保存到文件和python中<file>.

  File "<stdin>", line 1, in <module>

但答案是你没有改变你的卷积和汇集层的大小,所以当你以前运行28x28图像时,它们最终会缩小到7x7x(convolutional_depth)层.现在你正在运行巨大的图像,所以在第一个卷积层和2x2 maxpool之后,你有一个非常大的东西,你想要输入,但你正在重塑:

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])

对于较大的图像,h_pool2的输出要大得多.你需要将它们缩小得更多 - 可能有更多的卷积和最大化层.您还可以尝试增加W_fc1的大小以匹配到达那里的输入大小.它通过两个2x2 maxpools - 每个在x和y维度上缩小2.28x28x1 - > 14x14x32 - > 7x7x64.所以你的图像是从388 x 191 - > 194 x 95 - > 97 x 47

作为警告,具有97*47 = 4559输入的完全连接层将变得非常缓慢.