问题
This is the two methods for creating a keras model, but the output shapes
of the summary results of the two methods are different. Obviously, the former prints more information and makes it easier to check the correctness of the network.
import tensorflow as tf
from tensorflow.keras import Input, layers, Model
class subclass(Model):
def __init__(self):
super(subclass, self).__init__()
self.conv = layers.Conv2D(28, 3, strides=1)
def call(self, x):
return self.conv(x)
def func_api():
x = Input(shape=(24, 24, 3))
y = layers.Conv2D(28, 3, strides=1)(x)
return Model(inputs=[x], outputs=[y])
if __name__ == '__main__':
func = func_api()
func.summary()
sub = subclass()
sub.build(input_shape=(None, 24, 24, 3))
sub.summary()
output:
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) (None, 24, 24, 3) 0
_________________________________________________________________
conv2d (Conv2D) (None, 22, 22, 28) 784
=================================================================
Total params: 784
Trainable params: 784
Non-trainable params: 0
_________________________________________________________________
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d_1 (Conv2D) multiple 784
=================================================================
Total params: 784
Trainable params: 784
Non-trainable params: 0
_________________________________________________________________
So, how should I use the subclass method to get the output shape
at the summary()?
回答1:
I have used this method to solve this problem, I don't know if there is an easier way.
class subclass(Model):
def __init__(self):
...
def call(self, x):
...
def model(self):
x = Input(shape=(24, 24, 3))
return Model(inputs=[x], outputs=self.call(x))
if __name__ == '__main__':
sub = subclass()
sub.model().summary()
回答2:
I guess that key point is the _init_graph_network
method in the class Network, which is the parent class of Model
. _init_graph_network
will be called if you specify the inputs
and outputs
arguments when calling __init__
method.
So there will be two possible methods:
- Manually calling the
_init_graph_network
method to build the graph of the model. - Reinitialize with the input layer and output.
and both methods need the input layer and output (required from self.call
).
Now calling summary
will give the exact output shape. However it would show the Input
layer, which isn't a part of subclassing Model.
from tensorflow import keras
from tensorflow.keras import layers as klayers
class MLP(keras.Model):
def __init__(self, input_shape=(32), **kwargs):
super(MLP, self).__init__(**kwargs)
# Add input layer
self.input_layer = klayers.Input(input_shape)
self.dense_1 = klayers.Dense(64, activation='relu')
self.dense_2 = klayers.Dense(10)
# Get output layer with `call` method
self.out = self.call(self.input_layer)
# Reinitial
super(MLP, self).__init__(
inputs=self.input_layer,
outputs=self.out,
**kwargs)
def build(self):
# Initialize the graph
self._is_graph_network = True
self._init_graph_network(
inputs=self.input_layer,
outputs=self.out
)
def call(self, inputs):
x = self.dense_1(inputs)
return self.dense_2(x)
if __name__ == '__main__':
mlp = MLP(16)
mlp.summary()
The output will be:
Model: "mlp_1"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) [(None, 16)] 0
_________________________________________________________________
dense (Dense) (None, 64) 1088
_________________________________________________________________
dense_1 (Dense) (None, 10) 650
=================================================================
Total params: 1,738
Trainable params: 1,738
Non-trainable params: 0
_________________________________________________________________
来源:https://stackoverflow.com/questions/55235212/model-summary-cant-print-output-shape-while-using-subclass-model