technical problem

[Tong-Gao-dream]

technical problem

[gengshan-y]

Hi, you will need to download the data first (as here)

bash misc/processed/download.sh cat-pikachiu

[Tong-Gao-dream]

Thank you very much for your reply. I have downloaded pre-processed data via script before. But still there will be "AssertionError: datasets should not be an empty iterable"

[gengshan-y]

This error suggests the config file is not found:

banmo/utils/io.py

Lines 305 to 310 in b9dab80

	numvid = len(config.sections())-1
	datalist = []
	for i in range(numvid):
	dataset = get_config_info(opts, config, 'data_%d'%i, i, is_eval=is_eval)
	datalist = datalist + dataset
	dataset = torch.utils.data.ConcatDataset(datalist)

Can you make sure the following?

1. running echo $seqname in the terminal returns cat-pikachiu-sub. If it does not, you can directly run python preprocess/img2lines.py --seqname cat-pikachiu-sub
2. file configs/cat-pikachiu-sub.config exists

[Tong-Gao-dream]

Thank you very much for your patience, I understand what the problem is. grateful!

[fansunqi]

Hi,
I'm having the same problem reproducing the thesis work, but I can't figure out the problem. When I run python preprocess/img2lines.py --seqname $seqname, It will be AssertionError: datasets should not be an empty iterable . I have already downloaded pre-processed data via script before and it's in the database/DAVIS/... folder. The $seqname is also right.
Could you tell me how to solve it? Thank you very much!

[fansunqi]

Oh I figure out why.
Actually I download raw videos and pre-process raw videos into banmo format, following the instructions herehttps://github.com/facebookresearch/banmo/tree/main/preprocess. Then the dataset is like:
DAVIS/ JPEGImages/ Full-Resolution/ cat_pikachiu001/ {%05d}.jpg
However, my config/cat-pikachiu.config is like :
[data_1] ks = 1920 1920 540 960 datapath = database/DAVIS/JPEGImages/Full-Resolution/cat-pikachiu01/

a zero is missed after cat-pikachiu TT