ValueError：尺寸必须相等，但对于'Conv2D'（op：'Conv2D'），其输入形状为1和3：[1,400,400,1]，[1,3,3,1]

Question

我正在尝试创建一个简单的一层卷积二维输入的想法只是有一个输入图像，内核和输出的代码是：

import tensorflow as tf 
import numpy as np 
from PIL import Image 
import matplotlib.pyplot as plt 

filename_queue = tf.train.string_input_producer(['/home/ubuntu/test.png']) 

reader = tf.WholeFileReader() 
key, value = reader.read(filename_queue) 

my_img = tf.image.decode_png(value) 

init_op = tf.initialize_all_variables() 
sess = tf.InteractiveSession() 
with sess.as_default(): 
    sess.run(init_op) 

coord = tf.train.Coordinator() 
threads = tf.train.start_queue_runners(coord=coord) 

for i in range(1): 
    image = my_img.eval() 
image = tf.cast(image, tf.float64) 
image = tf.expand_dims(image, 0) 

K=np.array([[0,1,0],[1,1,1],[0,1,0]]).astype(float) 
K = tf.expand_dims(K, 2) 
K = tf.expand_dims(K, 0) 


conv = tf.nn.conv2d(
     image, 
     K, 
     strides=[3, 3, 3, 3], 
     padding="SAME") 

，我收到此错误：

Traceback (most recent call last): 
    File "test4.py", line 35, in <module> 
    padding="SAME") 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_nn_ops.py", line 396, in conv2d 
    data_format=data_format, name=name) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 759, in apply_op 
    op_def=op_def) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2242, in create_op 
    set_shapes_for_outputs(ret) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1617, in set_shapes_for_outputs 
    shapes = shape_func(op) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1568, in call_with_requiring 
    return call_cpp_shape_fn(op, require_shape_fn=True) 
    File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/common_shapes.py", line 610, in call_cpp_shape_fn 
    debug_python_shape_fn, require_shape_fn) 
    File "/usr/local/lib/python2.7/dist-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 1 and 3 for 'Conv2D' (op: 'Conv2D') with input shapes: [1,400,400,1], [1,3,3,1]. 

我输入是400x400x1，内核是3x3

Answer 1

根据conv2d doc：

shape of input = [batch, in_height, in_width, in_channels] 
shape of filter = [filter_height, filter_width, in_channels, out_channels] 

输入和过滤器的第三尺寸的最后维度表示输入信道的数目。在你的情况下，他们是不平等的。

You can change the shape of filter to [3, 3, 1, 1].