zoezhou1999

Question: Normal Training Information

5

Hi, recently, I am reproducing your project and experiencing debugging my reimplementation. Could I ask which epoch of the training does the evaluation metrics of composite 1k datasets reach the...

How the model be initialized before starting training?

6

Hi, I am reproducing your project. Sometimes, I found every time I trained, the converging start point is different. Did you have some specific initializer? Thank you so much~

I have read this in the document and guide, but I don't know how to use it. Can someone help me? Notice that addPeriodicSync() doesn't run the sync adapter at...

Is it possible to release the evaluation code for fair comparison? Thank you.

Is there 'regression' option in FIM_MonteCarlo?

1

Hi, Thank you for your great work. That is amazing! Is there 'regression' option in FIM_MonteCarlo?

Hi, this method does not need trimap, and then there are some trimap-needed methods in the quantitive results, in which I think they used official matlab code to evaluate with...

Thank you so much~

Can I query and update _User in leancloud using the API?

2

**Is your feature request related to a problem? Please describe.** Can I query and update _User in leancloud using the API? **Describe the solution you'd like** I see I can...

Question: Why the multi frame feature was not used? Typo?

11

Hi, In the networks.py, multi_feat is not used at all? Thank you so much! Should I change that to ` oth_feat=torch.cat([self.comb_back(torch.cat([img_feat,back_feat],dim=1)),self.comb_seg(torch.cat([img_feat,seg_feat],dim=1)),self.comb_multi(torch.cat([img_feat,multi_feat],dim=1))],dim=1)` ``` def forward(self, image,back,seg,multi): img_feat1=self.model_enc1(image) img_feat=self.model_enc2(img_feat1) back_feat=self.model_enc_back(back) seg_feat=self.model_enc_seg(seg) multi_feat=self.model_enc_multi(multi)...

USR type json file does not match DIM, HAttMatting dataset file name

1

Hi @JizhiziLi After downloading the json file, the filename for DIM and HAttMatting dataset is different from their original datasets.. Could you please provide the filename matching file? Thank you!