'Conv2D' 从 1 中减去 3 导致的负尺寸大小

Question

我使用Keras与Tensorflow作为后端，这里是我的代码：

import numpy as np
np.random.seed(1373) 
import tensorflow as tf
tf.python.control_flow_ops = tf

import os
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation, Flatten
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.utils import np_utils

batch_size = 128
nb_classes = 10
nb_epoch = 12


img_rows, img_cols = 28, 28

nb_filters = 32

nb_pool = 2

nb_conv = 3


(X_train, y_train), (X_test, y_test) = mnist.load_data()

print(X_train.shape[0])

X_train = X_train.reshape(X_train.shape[0], 1, img_rows, img_cols)
X_test = X_test.reshape(X_test.shape[0], 1, img_rows, img_cols)


X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
X_train /= 255
X_test /= 255


print('X_train shape:', X_train.shape)
print(X_train.shape[0], 'train samples')
print(X_test.shape[0], 'test samples')


Y_train = np_utils.to_categorical(y_train, nb_classes)
Y_test = np_utils.to_categorical(y_test, nb_classes)

model = Sequential()

model.add(Convolution2D(nb_filters, nb_conv, nb_conv,
border_mode='valid',
input_shape=(1, img_rows, img_cols)))
model.add(Activation('relu'))
model.add(Convolution2D(nb_filters, nb_conv, nb_conv))
model.add(Activation('relu'))

model.add(MaxPooling2D(pool_size=(nb_pool, nb_pool)))
model.add(Dropout(0.25))

model.add(Flatten())
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(nb_classes)) 
model.add(Activation('softmax')) 

model.compile(loss='categorical_crossentropy', optimizer='adadelta', metrics=["accuracy"])


model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch,
verbose=1, validation_data=(X_test, Y_test))

score = model.evaluate(X_test, Y_test, verbose=0)

print('Test score:', score[0])
print('Test accuracy:', score[1])

和引用错误：

Using TensorFlow backend.
60000
('X_train shape:', (60000, 1, 28, 28))
(60000, 'train samples')
(10000, 'test samples')
Traceback (most recent call last):
  File "mnist.py", line 154, in <module>
    input_shape=(1, img_rows, img_cols)))
  File "/usr/local/lib/python2.7/dist-packages/keras/models.py", line 276, in add
    layer.create_input_layer(batch_input_shape, input_dtype)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 370, in create_input_layer
    self(x)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 514, in __call__
    self.add_inbound_node(inbound_layers, node_indices, tensor_indices)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 572, in add_inbound_node
    Node.create_node(self, inbound_layers, node_indices, tensor_indices)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 149, in create_node
    output_tensors = to_list(outbound_layer.call(input_tensors[0], mask=input_masks[0]))
  File "/usr/local/lib/python2.7/dist-packages/keras/layers/convolutional.py", line 466, in call
    filter_shape=self.W_shape)
  File "/usr/local/lib/python2.7/dist-packages/keras/backend/tensorflow_backend.py", line 1579, in conv2d
    x = tf.nn.conv2d(x, kernel, strides, padding=padding)
  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: Negative dimension size caused by subtracting 3 from 1 for 'Conv2D' (op: 'Conv2D') with input shapes: [?,1,28,28], [3,3,28,32].

首先，我看到一些答案是Tensorflow版本有问题，所以我将Tensorflow升级到0.12.0 ，但仍然存在，是网络问题还是我遗漏了什么， input_shape应该是什么样子？

更新这里是./keras/keras.json ：

{
    "image_dim_ordering": "tf", 
    "epsilon": 1e-07, 
    "floatx": "float32", 
    "backend": "tensorflow"
}

Answer 1

您的问题来自image_ordering_dim中的keras.json 。

来自Keras 图像处理文档：

dim_ordering：{"th", "tf"} 之一。 “tf”模式意味着图像应该具有形状（样本、高度、宽度、通道），“th”模式意味着图像应该具有形状（样本、通道、高度、宽度）。 它默认为在 ~/.keras/keras.json 的 Keras 配置文件中找到的 image_dim_ordering 值。 如果您从未设置它，那么它将是“tf”。

Keras 将卷积操作映射到选定的后端（theano 或 tensorflow）。 但是，两个后端对维度的排序做出了不同的选择。 如果您的图像批次是 N 个 HxW 大小的图像和 C 通道，theano 使用 NCHW 排序，而 tensorflow 使用 NHWC 排序。

Keras 允许您选择您喜欢的顺序，并将进行转换以映射到后面的后端。 但是如果你选择image_ordering_dim="th"它需要 Theano 风格的排序（NCHW，你的代码中的image_ordering_dim="tf" ），如果image_ordering_dim="tf"它需要张量流风格的排序 (NHWC)。

由于您的image_ordering_dim设置为"tf" ，如果您将数据重塑为张量流样式，它应该可以工作：

X_train = X_train.reshape(X_train.shape[0], img_cols, img_rows, 1)
X_test = X_test.reshape(X_test.shape[0], img_cols, img_rows, 1)

和

input_shape=(img_cols, img_rows, 1)

Answer 2

FWIW，我用一些 strides 或 kernel_size 但不是全部的值反复得到这个错误，后端和 image_ordering 已经设置为张量流，当我添加padding="same"时它们都消失了

Answer 3

只需添加这个：

from keras import backend as K
K.set_image_dim_ordering('th')

Answer 4

我也有同样的问题。 但是，我使用的每个 Conv3D 层都在减少输入的大小。 因此，在声明 Conv2D/3D 层时包含一个参数 padding='same' 解决了这个问题。 这是演示代码

model.add(Conv3D(32,kernel_size=(3,3,3),activation='relu',padding='same'))

减小过滤器的尺寸也可以解决问题。

实际上，Conv3D 或 Conv2D 层减少了输入数据。 但是，当您的下一层没有收到任何输入或大小不适合该层的输入时，就会发生此错误。 通过填充，我们使 Conv3Dor2D 的输出保持与输入相同的大小，以便下一层获得所需的输入

Answer 5

我遇到了同样的问题，但通过更改 conv2d 函数解决了：

if K.image_data_format=='channels_first':
    x_train = x_train.reshape(x_train.shape[0], 1,img_cols,img_rows)
    x_test = x_test.reshape(x_test.shape[0], 1,img_cols,img_rows)
    input_shape = (1,img_cols,img_rows)
else:
    x_train = x_train.reshape(x_train.shape[0],img_cols,img_rows,1)
    x_test = x_test.reshape(x_test.shape[0],img_cols,img_rows,1)
    input_shape = (img_cols,img_rows,1)
model.add(Convolution2D(32,(3, 3), input_shape = input_shape, activation="relu"))

Answer 6

使用括号提供过滤器的大小，例如：

model.add(Convolution2D(nb_filters,( nb_conv, nb_conv) ,border_mode='valid',
input_shape=(1, img_rows, img_cols)))

它适用于我的情况，并且还将 X_train 、 X_test 更改为：

X_train = X_train.reshape(X_train.shape[0], img_cols, img_rows, 1)
X_test = X_test.reshape(X_test.shape[0], img_cols, img_rows, 1)

Answer 7

另一个解决方案可以帮助改变：

from keras.layers import Convolution2D, MaxPooling2D

到

from keras.layers import Conv2D, MaxPooling2D

之后，为了运行预处理输入数据，我更改：

X_train = X_train.reshape(X_train.shape[0], 1, 28, 28)
X_test = X_test.reshape(X_test.shape[0], 1, 28, 28)

到

X_train = X_train.reshape(X_train.shape[0], 28, 28, 1)
X_test.reshape(X_test.shape[0], 28, 28, 1)

最后，我改变：

model.add(Convolution2D(32, 3, 3, activation='relu',input_shape=(1,28,28))) 
model.add(Convolution2D(32, 3, 3,activation='relu'))

到

model.add(Conv2D(32, (3, 3), activation='relu',input_shape=(28,28,1)))
model.add(Conv2D(32, (3, 3), activation='relu'))

Answer 8

刚遇到这个问题。 下面是使用新 API 的解决方案。

K.set_image_dim_ordering('tf') --> K.set_image_data_format('channels_last')
K.set_image_dim_ordering('th') --> K.set_image_data_format('channels_first')
K.image_dim_ordering() == 'tf' --> K.image_data_format() == 'channels_last'
K.image_dim_ordering() == 'th' --> K.image_data_format() == 'channels_first'

在这里查看更多

Answer 9

   %store -r le
   %store -r x_train 
   %store -r x_test 
   %store -r y_train 
   %store -r y_test 
   %store -r yy 
    import numpy as np
    import keras
    from keras.models import Sequential
    from keras.layers import Dense, Dropout, Activation, Flatten
    from keras.layers import Conv2D, MaxPooling2D, GlobalAveragePooling2D
    from keras.optimizers import Adam
    from keras.utils import np_utils
    from sklearn import metrics
    num_rows = 40
    num_columns = 174
    num_channels = 1
    x_train = x_train.reshape(x_train.shape[0],num_rows , num_columns, num_channels)
    x_test = x_test.reshape(x_test.shape[0], num_rows, num_columns,num_channels )
num_labels = yy.shape[1]
filter_size = 2
# Construct model 
model = Sequential()

model.add(Conv2D(filters=16, kernel_size=2, activation='relu',input_shape=( 
40,174,1)))
model.add(MaxPooling2D(pool_size=2))
model.add(Dropout(0.2))

model.add(Conv2D(filters=32, kernel_size=2, activation='relu'))
model.add(MaxPooling2D(pool_size=2))
model.add(Dropout(0.2))

model.add(Conv2D(filters=64, kernel_size=2, activation='relu'))
model.add(MaxPooling2D(pool_size=2))
model.add(Dropout(0.2))

model.add(Conv2D(filters=128, kernel_size=2, activation='relu'))
model.add(MaxPooling2D(pool_size=2))
model.add(Dropout(0.2))
model.add(GlobalAveragePooling2D())

model.add(Dense(num_labels, activation='softmax'))