我在OSX上使用tensorflow 1.0.0，但版本1.0.1也出现了同样的问题。
您可以运行此脚本以产生错误
import tensorflow as tf
import numpy as np
def conv3d(inputs,weights, biases,layer_name,act=tf.nn.relu,padding='VALID'):
preactivate = tf.nn.conv3d(inputs,weights,strides=[1,1,1,1,1],padding=padding) + biases
activation = act(preactivate)
return activation
def maxpool(inputs,padding='VALID'):
return tf.nn.max_pool3d(inputs,ksize=[1,2,2,2,1],strides=[1,2,2,2,1],padding=padding)
def weight_variable(shape,dtype=np.float32,partition_info=None):
shape[shape==None] = 1
n = np.prod(shape)
w = (np.random.randn(n) * np.sqrt(2./n)).astype(np.float32)
return tf.Variable(w.reshape(shape),trainable=True)
## initializes biases
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial,trainable=True)
def mean_square_error(a,b):
shape = a.get_shape().as_list()
shape[shape==None] = 1
N = np.prod(shape)
return tf.reduce_sum(tf.squared_difference(a,b)) / N
### low level api ################################
def ll_model(inputs):
input_layer = tf.reshape(inputs,[-1,65,65,65,2])
W_conv1 = weight_variable([3,3,3,2,16])
b_conv1 = bias_variable([16])
conv1 = conv3d(input_layer,W_conv1,b_conv1,'conv1')
print(conv1.get_shape().as_list())
pad = tf.pad(conv1,[[0,0],[1,0],[1,0],[1,0],[0,0]],mode='CONSTANT')
print(pad.get_shape().as_list())
maxpool1 = maxpool(pad)
print(maxpool1.get_shape().as_list())
W_conv2 = weight_variable([3,3,3,16,24])
b_conv2 = bias_variable([24])
conv2 = conv3d(maxpool1,W_conv2, b_conv2,'conv2',padding="SAME")
print(conv2.get_shape().as_list())
W_conv3 = weight_variable([3,3,3,24,28])
b_conv3 = bias_variable([28])
conv3 = conv3d(conv2,W_conv3,b_conv3,'conv3',padding="SAME")
print(conv3.get_shape().as_list())
W_conv4 = weight_variable([4,4,4,28,34])
b_conv4 = bias_variable([34])
conv4 = conv3d(conv3,W_conv4,b_conv4,'conv4')
print(conv4.get_shape().as_list())
W_conv5 = weight_variable([5,5,5,34,42])
b_conv5 = bias_variable([42])
conv5 = conv3d(conv4,W_conv5,b_conv5,'conv5')
print(conv5.get_shape().as_list())
W_conv6 = weight_variable([5,5,5,42,50])
b_conv6 = bias_variable([50])
conv6 = conv3d(conv5,W_conv6,b_conv6,'conv6')
print(conv6.get_shape().as_list())
W_conv7 = weight_variable([5,5,5,50,50])
b_conv7 = bias_variable([50])
conv7 = conv3d(conv6,W_conv7,b_conv7,'conv7')
print(conv7.get_shape().as_list())
W_conv8 = weight_variable([1,1,1,50,2])
b_conv8 = bias_variable([2])
conv8 = conv3d(conv7,W_conv8, b_conv8,'output')
return conv8
sess = tf.Session()
## placeholders
x = tf.placeholder(tf.float32,shape=[None,65,65,65,2],name='features')
y = tf.placeholder(tf.float32,shape=[None,17,17,17,2],name='targets')
loss = mean_square_error(y,ll_model(x))
编译模型时发生错误。 conv8应该具有[None，17,17,17,2]的形状。
python task.py
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 ins
tructions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 ins
tructions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instru
ctions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instr
uctions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instru
ctions, but these are available on your machine and could speed up CPU computations.
[None, 65, 63, 63, 16]
[None, 66, 64, 64, 16]
[None, 33, 32, 32, 16]
[None, 33, 32, 32, 24]
[None, 33, 32, 32, 28]
[None, 33, 29, 29, 34]
[None, 33, 25, 25, 42]
[None, 33, 21, 21, 50]
[None, 33, 17, 17, 50]
Traceback (most recent call last):
File "/Users/vhasfclanga/anaconda/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/
common_shapes.py", line 670, in _call_cpp_shape_fn_impl
status)
File "/Users/vhasfclanga/anaconda/envs/tensorflow/lib/python3.5/contextlib.py", line 66, in __exit__
next(self.gen)
File "/Users/vhasfclanga/anaconda/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/
errors_impl.py", line 469, in raise_exception_on_not_ok_status
pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Dimensions must be equal, but are 17 and 33 fo
r 'SquaredDifference' (op: 'SquaredDifference') with input shapes: [?,17,17,17,2], [?,33,17,17,2].
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "task.py", line 33, in <module>
loss = mean_square_error(y,ll_model(x))
File "/Users/vhasfclanga/tflow_trainer/trainer/functions.py", line 80, in mean_square_error
return tf.reduce_sum(tf.squared_difference(a,b)) / N
File "/Users/vhasfclanga/anaconda/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/ops/gen_ma
th_ops.py", line 2754, in squared_difference
result = _op_def_lib.apply_op("SquaredDifference", x=x, y=y, name=name)
File "/Users/vhasfclanga/anaconda/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/
op_def_library.py", line 763, in apply_op
op_def=op_def)
File "/Users/vhasfclanga/anaconda/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/
ops.py", line 2397, in create_op
set_shapes_for_outputs(ret)
File "/Users/vhasfclanga/anaconda/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/
ops.py", line 1757, in set_shapes_for_outputs
shapes = shape_func(op)
File "/Users/vhasfclanga/anaconda/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/
ops.py", line 1707, in call_with_requiring
return call_cpp_shape_fn(op, require_shape_fn=True)
File "/Users/vhasfclanga/anaconda/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/
common_shapes.py", line 610, in call_cpp_shape_fn
debug_python_shape_fn, require_shape_fn)
File "/Users/vhasfclanga/anaconda/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/
common_shapes.py", line 675, in _call_cpp_shape_fn_impl
raise ValueError(err.message)
ValueError: Dimensions must be equal, but are 17 and 33 for 'SquaredDifference' (op: 'SquaredDifference') wi
th input shapes: [?,17,17,17,2], [?,33,17,17,2].
如您所见，这些是每个卷积层产生的张量的形状。
[无，65,63,63,16]
[无，66,64,64,16]
[无，33,32,32,16]
[无，33,32,32,24]
[无，33,32,32,28]
[无，33,29,29,34]
[无，33,25,25,42]
[无，33,21,21,50]
[无，33,17,17,50]
请注意，第一个空间维度仅受池和填充层的影响，并且卷积层完全忽略。这对我来说很奇怪，因为一切都应该在空间维度上对称。
我尝试过使用tf.nn.convolution，结果相同。我尝试过填充填充，但也没有用。我尝试使用tf.layers中的更高级函数来构建模型，这也没有用。这些方法都不起作用的事实使我认为这对我来说一定是编程错误，但错误来自于张量形状的简单传播，从占位符开始
with tf.name_scope('inputs'):
x = tf.placeholder(tf.float32,shape=[None,65,65,65,2],name='features')
tf.summary.histogram('feature-hist', x)
with tf.name_scope('ground_truth'):
y = tf.placeholder(tf.float32,shape=[None,17,17,17,2],name='targets')
tf.summary.histogram('target-hist', y)
所以我不确定我可能在哪里出错。
此外，当与Estimator + ModelFnOps API一起使用时，这种精确的模型结构会产生正确的输出形状。
有人知道这是我的错误或编程错误吗？
提前致谢， 亚历
答案 0 :(得分：0)
我回头回答我的问题，低着头。我自己玩了。
问题在于这一行
shape[shape==None] = 1
weight_variable中的。
由于这种情况下的形状只是一个普通的python列表，shape==None不是按元素计算的，只是评估为False，然后由于某种原因shape[False]返回{{1} }}。这就是所有内核的第一个维度为1的原因。
将shape[0]功能修改为此
weight_variable工作正常。