Arka Sadhu comments

Results 54 comments of


                                            Arka Sadhu

Implementation ambiguity

@pinkfloyd06 As I earlier mentioned, the author used `graph_max_pool(x, 4)`. So the number of nodes are divided by a factor of 4. In the computation of the laplacian matrices, the...

Which sentence-bert model was used? And where is it implemented in the code?

@zmykevin Thanks for the pointer. I came across the repository, but couldn't figure out which model to use. Could you clarify how you generate the weakly aligned sentences? Again, thanks...

Which sentence-bert model was used? And where is it implemented in the code?

@zmykevin Thanks for the reply. How do you perform the retrieval for large number image and text sets? Do you have any particular implementation?

Which sentence-bert model was used? And where is it implemented in the code?

@zmykevin Thanks for the reply. Do you happen to have it implemented somewhere (I couldn't find it in the repo)? Did you use the normal FlatIP (i.e. normal dot product)...

Any way to integrate this within a pytorch dataloader/dataset?

@iejMac Thanks for your reply. My current case is I have a large number of video files, I am using webvid-2M dataset (https://m-bain.github.io/webvid-dataset/). There are around 2M videos each with...

Any way to integrate this within a pytorch dataloader/dataset?

@iejMac I believe even with larger time horizon videos, having access to full videos is often useful. For instance you can sample the frames with a bit of temporal jittering...

Any way to integrate this within a pytorch dataloader/dataset?

@iejMac I agree that for CLIP it is likely not that useful. But I am not exactly training CLIP, but trying a different model. Video models such as SlowFast often...

I have downloaded situ_vidfeats_drive and vsitu_vocab, do I need to download the video?

@ttx213 sorry for the delayed reply. Could you clarify what command you used?

I have downloaded situ_vidfeats_drive and vsitu_vocab, do I need to download the video?

@zhangheng0311 have you checked https://github.com/TheShadow29/VidSitu/issues/3 and https://github.com/TheShadow29/VidSitu/issues/5 ?

I have downloaded situ_vidfeats_drive and vsitu_vocab, do I need to download the video?

@lan-lw The log files have `cmd` and `cmd_str` which refers to the command used. Let me know if it works out.