How can I load model? about fgsegnet_v2

[lim-anggun]

hi @Wisgon,
there is an InstanceNormalization file inside the scripts folder. What you need to do is:

1. Copy and paste instance_normalization.py into the same folder as Jupyter Notebook
2. load the model as following (I did't test yet, but hope it works):

# ... the rest of your code ...
from instance_normalization import InstanceNormalization
model = load_model(mdl_path, custom_objects={'MyUpSampling2D': MyUpSampling2D, 'InstanceNormalization': InstanceNormalization})

Let me know if it works.

[Wisgon]

It works!
But, I found that I should add something else to make it work:

from FgSegNet_v2_module.py import loss2, acc2
model = load_model(mdl_path, custom_objects={'MyUpSampling2D': MyUpSampling2D, 'InstanceNormalization': InstanceNormalization, 'loss2':loss2, 'acc2':acc2})

If you don't add loss2 and acc2, it will raise "Unknow loss function: loss2"

[Wisgon]

Ahha, I found https://github.com/lim-anggun/FgSegNet/blob/master/test_prediction.ipynb
Closing the issue.

[Wisgon]

I use model = load_model(mdl_path, custom_objects={'MyUpSampling2D': MyUpSampling2D}) to load model, but it still raise "ValueError: Unknow layer: InstanceNormalization"

[124399839]

@Wisgon 请问你在自己的数据上，该方法表现效果如何？