Xiaodi Shi

BasicVSR++: reproduce ntire decompression results on track3

17

Hi, Thanks for your great work. When I use BasicVSR++ to reproduce ntire decompression results on track3 with the trained model you provided and official testset. the settings include: basicvsr_plusplus_c128n25_600k_ntire_decompress_track3.py...

the Training set

1

I am sorry,I can't find the training set directory which you use . Can you help. Thanks

About the test

1

Hi, sorry to bother you. Which file did you use to get the final result, the model_best.pt or model_latest ? I find the quantitative result of model_best is better than...

datasets

1

I want to reproduce your nice work and do some modifications. However, the first question is that I don't have these images you used in this paper. Would you mind...

Tendency map of batch loss

4

Hey, thanks for your sharing. It seems that there isn't tendency map of loss or psnr of evaluation to monitor the training process, and how can I know when is...

About the quantization for activation function

1

Hey, thanks for your greatest work. I am a little confused about the quantization formula for the activation function to fit the quant inputs. Can you show me the quantization...