Different eval metrics for model with/without bn about icnet-tensorflow HOT 6 CLOSED

Hey, this is also my question, and I still have no idea about why it happened. Maybe there is a bug in my bn_model, but I can't find it. Another possibility is that the author did not upload the final version of bnnomerge model. If you find any thing helpful to this issue, please tell me, thanks.

from icnet-tensorflow.

The weights provided by them are fine as I can actually convert the train_30k_bnnomerge weights to train_30k weights by merging the batchnorm layer weights with conv layer weights. I also tried to compare the activations after every bn layer(for bn model) and conv layer(for no bn model) and noticed that the error between them keeps on increasing as we go deeper. My guess is that bn weights are somehow not being loaded properly or something else that is buggy with the bn model.

from icnet-tensorflow.

Hey, can you tell me how you convert weights by merging the batchnorm layer weights with conv weights? Did you do this using .npy or .caffemodel ? I think maybe the problem is that bn weights not converted properly, I'll check again.

from icnet-tensorflow.

I used the npy weights. Here's the script I wrote:

https://github.com/alasin/python-scripts/blob/master/convert_bn.py

from icnet-tensorflow.

Thank you for the script. I'll check the method I load bn weight, also the model.

from icnet-tensorflow.

Hey @alasin, issue #41 have solved this problem.

from icnet-tensorflow.