web-dev-qa-db-fra.com

ValueError: les dimensions doivent être égales, mais sont 1 et 3 pour 'Conv2D' (op: 'Conv2D') avec des formes d'entrée: [1,400,400,1], [1,3,3,1]

j'essaie de créer une simple convolution d'une couche pour une entrée 2D l'idée est juste d'avoir une image d'entrée, un noyau et une sortie le code est:

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")

et je reçois cette erreur:

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].

mon entrée est 400x400x1 et le noyau est 3x3

pythonmachine-learningtensorflowconvolution
6
MORagab

Basé sur doc conv2d :

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

La dernière dimension de l'entrée et la troisième dimension du filtre représentent le nombre de canaux d'entrée. Dans votre cas, ils ne sont pas égaux.

You can change the shape of filter to [3, 3, 1, 1].
20
user1454804