my training results works out not so perfect

[MexWayne]

hi，I'm so interested in your great work！ For there is no released model，I train the model by myself based on your CRVD_dataset. Well after epoch 10000, the best model can not work as the paper shows.
So can you release a model which help me to figure out the performance of your work Hope reply soon~

[MexWayne]

looking at the black area in train window， the results not as good as the paper shows

[MexWayne]

oh，I have read your paper again. Well, the motion area which have no t-1 frame for reference will perform worse than static area. the windows of the train is just the motion area. When we look at the clothes and grape leaves，the denoised detail perform much better

[litianfugt]

请问一下 你只用CRVD数据集训练能在测试集（7-11）上达到42db吗