xiaojuan123

how can achieve video superresolution?

error:argument --checkpoint is required

1

why,I need help .thanks

How to find the clean images of DND/NC12/Nam

1

don't have the clean images of DND/NC12/Nam,how to calculate the PSNR value.

please!Great God, I need your help.

6

/usr/bin/python3.5 /home/prl/fg-foucouse/CODE/SRMD-pytorch-master/main.py Namespace(batch_size=2, beta1=0.5, beta2=0.999, conv_dim=128, device=device(type='cuda'), image_path='./Database/train', image_size=40, iteration=0, log_path='./logs', log_step=10, lr=0.001, mode='train', model_save_path='./models', model_save_step=1000, num_blocks=11, num_channels=18, num_workers=4, pause=0, result_path='./results', sample_step=100, scale_factor=2, total_step=200000, trained_model=None, use_tensorboard=True) Traceback (most recent call...

Do the traindata need to be downloaded online? The following error occurred during operation#question

2

requests.exceptions.ConnectionError: HTTPConnectionPool(host='localhost', port=8097): Max retries exceeded with url: /env/main (Caused by NewConnectionError(': Failed to establish a new connection: [Errno 111] Connection refused',))

can't reach the performace as you say ,why?

2

I have traind 20 layers ,but my Generated HR images are not the same quality as Original one.I want ask help for you?what mistake I have made??thanks

you code is very good .but i want to know why not remove BN and Group conv just like the paper??