what is the meaning of warning says" tensorflow using weight layer instead of variable layer"

44 Views Asked by At

I work with transfer-learning, I use pretrained-model as feature-extraction, then add dense_layer, but the layer I add is Dense_Flipout_layer(this layer from tensor_probability-_library). after apply (model.compile) then(model.fit), it shows this message, what does it mean? have I change layer or paramter?

/usr/local/lib/python3.10/dist-packages/tensorflow_probability/python/layers/util.py:98: UserWarning: layer.add_variable is deprecated and will be removed in a future version. Please use the layer.add_weight() method instead. loc = add_variable_fn( /usr/local/lib/python3.10/dist-packages/tensorflow_probability/python/layers/util.py:108: UserWarning: layer.add_variable is deprecated and will be removed in a future version. Please use the layer.add_weight() method instead. untransformed_scale = add_variable_fn(

0

There are 0 best solutions below