OpenGVLab / OpenGVLab/InternVideo
NotImplementedError: We need json file!!!
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2.4k
- Forks
- 160
- PR merge metrics
- No merged PRs in 30d
Description
Hi,
When I try to run sh eval_msrvtt.sh, I am getting the following error:
[rank0]: File "/workspace/InternVideo2/multi_modality/tasks/pretrain.py", line 315, in main
[rank0]: train_loaders, test_name2loaders, train_media_types = setup_dataloaders(
[rank0]: File "/workspace/InternVideo2/multi_modality/tasks/pretrain.py", line 245, in setup_dataloaders
[rank0]: train_datasets = create_dataset(f"{mode}_train", config)
[rank0]: File "/workspace/InternVideo2/multi_modality/dataset/init.py", line 234, in create_dataset
[rank0]: datasets.append(dataset_cls(**dataset_kwargs))
[rank0]: File "/workspace/InternVideo2/multi_modality/dataset/pt_dataset.py", line 208, in init
[rank0]: super().init(ann_file, transform, num_epochs)
[rank0]: File "/workspace/InternVideo2/multi_modality/dataset/pt_dataset.py", line 122, in init
[rank0]: raise NotImplementedError("We need json file!!!")
[rank0]: NotImplementedError: We need json file!!!
Please let me know, how I can download the dataset automatically
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with eval_msrvtt.sh and trace the reported setup_dataloaders and create_dataset calls in multi_modality/tasks/pretrain.py. Read multi_modality/dataset/pt_dataset.py around lines 122 and 208 to identify the required JSON input and how the dataset is expected to be prepared. Done means the documented setup lets eval_msrvtt.sh proceed without the NotImplementedError.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- data, machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100