Thank you very much for your work.
I want to use your work in the tensorflow2.5. There are some problems.
The following Variables were used a Lambda layer's call (tf.nn.bias_add), but
are not present in its tracked objects:
<tf.Variable 'discriminator_ConvSN2D_1/bias:0' shape=(64,) dtype=float32>
It is possible that this is intended behavior, but it is more likely
an omission. This is a strong indication that this layer should be
formulated as a subclassed Layer rather than a Lambda layer.```
Looking forward to your reply. Thank you very much.
Best regards
Dear,
Thank you very much for your work.
I want to use your work in the tensorflow2.5. There are some problems.
from keras.legacy import interfaces, which is not used in current keras version.(I don't see you use this function)from tensorflow.keras.layers import InputSpec, there is a warning.