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

[ttx213]

np.stack([self.read_img(f) for f in frm_pths_for_ev])

File "/home/wangtao/VidSitu/vidsitu_code/dat_loader.py", line 475, in np.stack([self.read_img(f) for f in frm_pths_for_ev]) File "/home/wangtao/VidSitu/vidsitu_code/dat_loader.py", line 187, in read_img img = Image.open(img_fpath).convert("RGB") File "/home/wangtao/miniconda3/envs/vsitu_pyt/lib/python3.7/site-packages/PIL/Image.py", line 2878, in open fp = builtins.open(filename, "rb") FileNotFoundError: [Errno 2] No such file or directory: '/home/wangtao/VidSitu/data/vsitu_frames/v_BQO5Xy2ebhs_seg_20_30/v_BQO5Xy2ebhs_seg_20_30_000001.jpg'

[ttx213]

If I use the vsitu_vis_feats , which file do I need to run

[TheShadow29]

@ttx213 sorry for the delayed reply.

Could you clarify what command you used?

[ttx213]

I have solved the problem, thank you :)

[zhangheng0311]

hi :) I ran verb prediction task, but downloaded video dataset is incomplete. so could you help me , and provide the full dataset？

[TheShadow29]

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

[zhangheng0311]

Now, I see , thank you :)

[lan-lw]

@TheShadow29 can you please provide the command to train using pre-extracted features?

[TheShadow29]

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

[lan-lw]

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

Yes I found them, thanks!