wolfam0108

I tried running transer_RRDB_models.py. But the result: ``` (base) vova@wolfram-pc:/tmp/ESRGAN$ python3 ./transer_RRDB_models.py ################################### Traceback (most recent call last): File "./transer_RRDB_models.py", line 31, in crt_net['conv_first.weight'] = pretrained_net['model.0.weight'] KeyError: 'model.0.weight' ```

Thanks for the answer. Is there a description of how to change the structure of the ESRGAN network? Or at least in what direction to dig?

When I apply the model, I get this: ``` (base) vova@wolfram-pc:/tmp/ESRGAN$ python test.py Traceback (most recent call last): File "test.py", line 15, in model.load_state_dict(torch.load(model_path), strict=True) File "/home/vova/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 847, in...

File "test.py" from [ESRGAN](https://github.com/xinntao/ESRGAN) project: ``` import os.path as osp import glob import cv2 import numpy as np import torch import RRDBNet_arch as arch model_path = 'models/net_g_18000.pth' # models/RRDB_ESRGAN_x4.pth OR...

I tried running transer_RRDB_models.py. But the result: ``` (base) vova@wolfram-pc:/tmp/ESRGAN$ python3 ./transer_RRDB_models.py ################################### Traceback (most recent call last): File "./transer_RRDB_models.py", line 31, in crt_net['conv_first.weight'] = pretrained_net['model.0.weight'] KeyError: 'model.0.weight' ```

Is it possible to do without dataroot_gt in testing? If I have already trained the model. And I need to apply this to images.

Thank you, it works! Will this work with EDVR?

If I change the type: VideoTestDataset to the type: SingleImageDataset in the file test_EDVR_L_x4_SR_Vid4?