Python Keras：如何在顺序模型中获取图层形状
声明：本页面是StackOverFlow热门问题的中英对照翻译，遵循CC BY-SA 4.0协议，如果您需要使用它，必须同样遵循CC BY-SA许可，注明原文地址和作者信息，同时你必须将它归于原作者（不是我）：StackOverFlow
原文地址: http://stackoverflow.com/questions/43743593/
Warning: these are provided under cc-by-sa 4.0 license. You are free to use/share it, But you must attribute it to the original authors (not me):
StackOverFlow
Keras: How to get layer shapes in a Sequential model
提问by Toke Faurby
I would like to access the layer size of all the layers in a SequentialKeras model. My code:
我想访问SequentialKeras 模型中所有层的层大小。我的代码：
model = Sequential()
model.add(Conv2D(filters=32,
kernel_size=(3,3),
input_shape=(64,64,3)
))
model.add(MaxPooling2D(pool_size=(3,3), strides=(2,2)))
Then I would like some code like the following to work
然后我想要一些像下面这样的代码来工作
for layer in model.layers:
print(layer.get_shape())
.. but it doesn't. I get the error: AttributeError: 'Conv2D' object has no attribute 'get_shape'
.. 但它没有。我收到错误：AttributeError: 'Conv2D' object has no attribute 'get_shape'
采纳答案by Dat Nguyen
According to official doc for Keras Layer, one can access layer output/input shape via layer.output_shapeor layer.input_shape.
根据Keras Layer 的官方文档，可以通过layer.output_shape或 访问层输出/输入形状layer.input_shape。
from keras.models import Sequential
from keras.layers import Conv2D, MaxPool2D
model = Sequential(layers=[
Conv2D(32, (3, 3), input_shape=(64, 64, 3)),
MaxPool2D(pool_size=(3, 3), strides=(2, 2))
])
for layer in model.layers:
print(layer.output_shape)
# Output
# (None, 62, 62, 32)
# (None, 30, 30, 32)
回答by Toke Faurby
If you want the output printed in a fancy way:
如果您希望以奇特的方式打印输出：
model.summary()
If you want the sizes in an accessible form
如果您想以可访问的形式显示尺寸
for layer in model.layers:
print(layer.get_output_at(0).get_shape().as_list())
There are probably better ways to access the shapes than this. Thanks to Daniel for the inspiration.
可能有比这更好的访问形状的方法。感谢丹尼尔的灵感。
回答by Daniel M?ller
Just use model.summary(), and it will print all layers with their output shapes.
只需使用model.summary()，它将打印所有图层及其输出形状。
If you need them as arrays, tuples or etc, you can try:
如果您需要它们作为数组、元组等，您可以尝试：
for l in model.layers:
print (l.output_shape)
For layers that are used more than once, they contain "multiple inbound nodes", and you should get each output shape separately:
对于多次使用的图层，它们包含“多个入站节点”，您应该分别获取每个输出形状：
if isinstance(layer.outputs, list):
for out in layer.outputs:
print(K.int_shape(out))
for out in layer.outputs:
It will come as a (None, 62, 62, 32) for the first layer. The Noneis related to the batch_size, and will be defined during training or predicting.
它将作为第一层的 (None, 62, 62, 32) 出现。该None是有关的batch_size，并且将训练或预测期间定义。
