I was testing the UNet model along with a mobilenetv2 and saw that there are a lot non-trainable params, which I could not explain. I quick lookup in the model revealed that besides the non-trainable BN params, there are also normal kernels that are marked as non-trainable. I guess this behavior is not desired.
I was testing the UNet model along with a mobilenetv2 and saw that there are a lot non-trainable params, which I could not explain. I quick lookup in the model revealed that besides the non-trainable BN params, there are also normal kernels that are marked as non-trainable. I guess this behavior is not desired.
Correct me if I am wrong, but I guess the default
trainable
parameter should be set totrue
? https://github.com/JanMarcelKezmann/TensorFlow-Advanced-Segmentation-Models/blob/c06d3d288f0f445fc4c8f567cd2960494a6d70ff/tensorflow_advanced_segmentation_models/models/_custom_layers_and_blocks.py#L214-L219