Tensorflow2.0 reuse layers - tensorflow2.0

Question

def head(self, input, num_anchors, name, flatten=False):
out_channels = (self.num_classes + 4) * num_anchors
conv = layers.Conv2D(256, 3, 1, 'same', activation='relu', name=name+'_conv1')(input)
conv = layers.Conv2D(256, 3, 1, 'same', activation='relu', name=name+'_conv2')(conv)
conv = layers.Conv2D(256, 3, 1, 'same', activation='relu', name=name+'_conv3')(conv)
out = layers.Conv2D(out_channels, 3, 1, 'same', name=name+'output')(conv)
if flatten is True:
batch_size = tf.shape(out)[0]
out = tf.reshape(out, [batch_size, -1, num_anchors, self.num_classes+4])
out = tf.reshape(out, [batch_size, -1, self.num_classes+4])
return out
I want to know how to reuse these layers as tf.variable_scope(scope resue=tf.AUTO_REUSE) in tensorflow1
In tensorflow1
with tf.variable_scope('', resue=tf.AUTO_REUSE) as scope:
all layers here could be auto reuse

Answer 1

You can reuse the layers by just having a common reference. I have attached a sample code below. I am making use of a variable named as common_layer which will be used in three separate models (sequential and functional). The first model is trained and after that we subtract the weights from common_layer of all the three models. It proves that what changes happen in first model's layer gets reflected in other model's common layer.
import tensorflow as tf
import numpy as np
common_layer = tf.keras.layers.Dense(100, name='common_layer')
model1 = tf.keras.models.Sequential([
tf.keras.layers.Input((100)),
common_layer,
tf.keras.layers.Dense(1)
])
model2 = tf.keras.models.Sequential([
tf.keras.layers.Input((100)),
common_layer,
tf.keras.layers.Dense(10)
])
input_layer = tf.keras.layers.Input((100))
output_layer = common_layer(input_layer)
output_layer = tf.keras.layers.Dense(20)(output_layer)
model3 = tf.keras.Model(inputs=[input_layer], outputs=[output_layer])
model1.compile('adam', loss='mse')
model1.fit(np.random.rand(128, 100), np.random.rand(128, 1))
weights1 = model1.get_weights()[0]
weights2 = model2.get_weights()[0]
weights3 = model3.get_weights()[0]
print(np.sum(weights1 - weights2)) # 0.0
print(np.sum(weights1 - weights3)) # 0.0