这些是我认为在使用TF构建U-net模型时引起问题的关键信息。
我不知道tensorlayer.layers定义的Conv2d层怎么会出错。
我很确定占位符的dtype是uint8 这是我的声明方式：
X_placeholder = tf.placeholder(uint8 , (num_of_input_image, 284, 284, 3))
然后我将X-placeholer用作自定义模型的输入。
Con2d用于我的自定义模型中，但是似乎不起作用。 如果需要更多信息，请告诉我。
（我确实看到了类似的问题，例如this）
Traceback (most recent call last):
File "model.py", line 104, in <module>
main()
File "model.py", line 32, in main
net = u_net(X_placeholder ,is_train = True , n_out=1)
File "model.py", line 68, in u_net
conv1 = Conv2d(inputs, 64, (3, 3), act=tf.nn.relu, name='conv1_1')
...
...
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/init_ops.py", line 336, in __call__
shape, self.mean, self.stddev, dtype, seed=self.seed)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/random_ops.py", line 170, in truncated_normal
mean_tensor = ops.convert_to_tensor(mean, dtype=dtype, name="mean")
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1011, in convert_to_tensor
as_ref=False)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1107, in internal_convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/constant_op.py", line 217, in _constant_tensor_conversion_function
return constant(v, dtype=dtype, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/constant_op.py", line 196, in constant
value, dtype=dtype, shape=shape, verify_shape=verify_shape))
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/tensor_util.py", line 436, in make_tensor_proto
_AssertCompatible(values, dtype)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/tensor_util.py", line 347, in _AssertCompatible
(dtype.name, repr(mismatch), type(mismatch).__name__))
TypeError: Expected uint8, got 0.0 of type 'float' instead.