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].
首先我看到了一些问题所在的答案Tensorflow
版本所以我升级Tensorflow
到0.12.0
,但仍然存在,是网络问题还是我遗漏了什么,应该怎么办input_shape
好像?
Update 这是./keras/keras.json
:
{
"image_dim_ordering": "tf",
"epsilon": 1e-07,
"floatx": "float32",
"backend": "tensorflow"
}
答案
您的问题来自于image_ordering_dim
在keras.json
。
dim_ordering:{“th”,“tf”}之一。
Keras 将卷积运算映射到所选后端(theano 或张量流)。
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。image_ordering_dim="th"
它需要 Theano 风格的排序(NCHW,您代码中的排序)并且如果image_ordering_dim="tf"
它需要张量流式排序(NHWC)。
自从你的image_ordering_dim
被设定为"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)