Keras中维度报错
在运行keras代码的时候,出现了以下的错误:
Traceback (most recent call last):
File "segnet_train.py", line 254, in <module>
train(args)
File "segnet_train.py", line 210, in train
model = SegNet()
File "segnet_train.py", line 134, in SegNet
model.add(MaxPooling2D(pool_size=(2,2)))
File "/usr/local/lib/python2.7/dist-packages/keras/engine/sequential.py", line 181, in add
output_tensor = layer(self.outputs[0])
File "/usr/local/lib/python2.7/dist-packages/keras/engine/base_layer.py", line 457, in __call__
output = self.call(inputs, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/keras/layers/pooling.py", line 205, in call
data_format=self.data_format)
File "/usr/local/lib/python2.7/dist-packages/keras/layers/pooling.py", line 268, in _pooling_function
pool_mode='max')
File "/usr/local/lib/python2.7/dist-packages/keras/backend/tensorflow_backend.py", line 3978, in pool2d
data_format=tf_data_format)
File "/home/ys/.local/lib/python2.7/site-packages/tensorflow/python/ops/nn_ops.py", line 2154, in max_pool
name=name)
File "/home/ys/.local/lib/python2.7/site-packages/tensorflow/python/ops/gen_nn_ops.py", line 4640, in max_pool
data_format=data_format, name=name)
File "/home/ys/.local/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/home/ys/.local/lib/python2.7/site-packages/tensorflow/python/util/deprecation.py", line 454, in new_func
return func(*args, **kwargs)
File "/home/ys/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 3155, in create_op
op_def=op_def)
File "/home/ys/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1731, in __init__
control_input_ops)
File "/home/ys/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1579, in _create_c_op
raise ValueError(str(e))
ValueError: Negative dimension size caused by subtracting 2 from 1 for 'max_pooling2d_2/MaxPool' (op: 'MaxPool') with input shapes: [?,1,128,128].
Keras的图片处理文档中给出:
dim_ordering: One of {“th”, “tf”}. “tf” mode means that the images should have shape (samples, height, width, channels), “th” mode means that the images should have shape (samples, channels, height, width). It defaults to the image_dim_ordering value found in your Keras config file at ~/.keras/keras.json. If you never set it, then it will be “tf”.
即:
关于图片的维度顺序有两种类型,分别是“th”和”tf“,它们的差别如下:
图片维序类型为 th 时(dim_ordering='th'): 输入数据格式为[samples][channels][rows][cols];
图片维序类型为 tf 时(dim_ordering='tf'):输入数据格式为[samples][rows][cols][channels];
在Keras里默认的是“tf”顺序,如果想要改为“th”顺序,需要手动在前面加上如下代码:
from keras import backend as K
K.set_image_dim_ordering('th')