Francesco
Francesco
This is an effect of the noise cancelling model we provide, there is a few things you could do: - re-train the current model, with some data that is similar...
Answer: #37 Close if it works, thanks
Hi, are you able to reproduce the results on colab?
Could you post a screenshot of the results?
Thank for this good suggestion. I'll put this on top of the todos. Feel free to PR a change in case you can.
could you post the entire error logs?
thanks @altear, there is a discrepancy in the readme. I will probably just remove this option or make it default if there is no match. @dpincic is correct, thanks for...
Hi, I'm reaching out on the fly so I can't elaborate, but with RRDN(weights='gans') you're loading the pretrained model. You need to initialize the model with the correct architecture parameters...
Hi, from your model weights, these should be the parameters: `rrdn = RRDN(arch_params={'C':4, 'D':3, 'G':64, 'G0':64, 'T':10, 'x':4})` then you can ``` import numpy as np from PIL import Image...
For individual images you should be able to just use a load_weights call `model.load_weights('weights/rrdn-C4-D3-G64-G064-T10-x4/2021-05-29_1003/rrdn-C4-D3-G64-G064-T10-x4_best-val_generator_PSNR_Y_epoch133.hdf5')` edit: you actually need to use `model.model.load_weights('weights/rrdn-C4-D3-G64-G064-T10-x4/2021-05-29_1003/rrdn-C4-D3-G64-G064-T10-x4_best-val_generator_PSNR_Y_epoch133.hdf5')` as the model is an attribute of RRDN