1144181135

Thank you Kai Zhang. I have a question about training dpsr https://arxiv.org/pdf/2008.13751.pdf. About the optimization of eq. 6a and 6b, in the Algorithm 1, it seems that K iterations are...

Question about training USRNet

2

Hello, I have some questions about training USRNet. When I read the training code, I can not find where the optimization of equation 5 and 6. In the lines 149-152...

Hi jukebox teams, I have some questions about training and sampling on new categories. I have trained a prior (level 2) on my defined 18 categories, and I uses y_bins=(18,...

via fine-tune

1

what is the "--model_name_or_path pretrained_models/base-vg-labels/ep_107_1192087"? I didn't fine such a file.

VQA finetune

2

Hi Oscar teams: I read your code and find that some parser_argument may loss, like "--model_name_or_path vinvl/model_ckpts/vqa/base/checkpoint-2000000" and "--tokenizer_name". Can you provide this file? Thanks.

The order of landmarks

1

Hello. Can you provide a demo for the order of landmarks, i.e., which landmark corresponds which parts ? Thanks

Hi FOMM teams, Can you provide your training log on vox dataset for our reference ? Thanks !

Hi AliaksandrSiarohin: Thanks for your exciting work! How to pro-process the train dataset VoxCeleb? Can you release this part of code?

pretrained models

4

hello, thanks for your work. Could you provide google drive url for your pretrained models? thanks

Hi, can you provide your finetun model weight file (i.e., the weight of VQA_model.py) on VQA2.0 dataset ? I have some difficulty to download the pretrained features as the bannd...