Panda-70M
Panda-70M copied to clipboard
snap-research
[CVPR 2024] Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers
Hi, Since the download can take a long time, is it possible to parallelize it across multiple jobs without SLURM? E.g. an option in the config or launch args to...
File "/mnt/disk/Panda-70M/dataset_dataloading/video2dataset/video2dataset/data_writer.py", line 44, in flush df = pa.Table.from_pydict(self.buffer, self.schema) File "pyarrow/table.pxi", line 1813, in pyarrow.lib._Tabular.from_pydict File "pyarrow/table.pxi", line 5356, in pyarrow.lib._from_pydict File "pyarrow/array.pxi", line 374, in pyarrow.lib.asarray File "pyarrow/array.pxi",...
Hi, can anyone share your resource usage and settings for downloading the dataset? We have tried to download the 10M sub-dataset in 720p without audio. But it requires more than...
The first time I ran the code, it worked fine, but it was slow, so I stopped and changed the 'processes_count' in the cfg file. However, when I executed the...
Can you open source the model weights of the Unmasked Teacher fine tuned on panda?
Has anyone downloaded successfully? Could you share the 2M or 10M Training set with a torrent or goole link. This dataset is almost impossible to download completely, which is absurd....
  Hello, I used the download script to download validation videos but found that they are compressed a lot and, as a result, of low quality. Do you have...
Hi, thank you for your contribution to this open source dataset. In my understanding, I believe the dataset can be freely used for research purposes. Am I right, or are...
Hi, great work and thank you for your contribution~ Is there any plan to release the caption model's training script? Thank you
Metadata
Owner
Metadata
[CVPR 2024] Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers