Jiannan Xiang
Jiannan Xiang
> 请问您的问题解决了吗我的也出现了这个问题 Sorry I didn't continue to investigate the issue
@knighton +1 for the feature request! In my case my dataset is also a interleaved text and image one, so in one sample we may have multiple images, like `[img1,...
@knighton @karan6181 Any updates on this?
I update my solution here for anyone that needs help. In streaming, each jpeg is saved as bytes, which can be seen from here: https://github.com/mosaicml/streaming/blob/59f6ec5f8f97cc5f9a75954fef4bef3221460ff8/streaming/base/format/mds/encodings.py#L207-L223 Therefore, if we want to...
Thanks for appreciating our work! We plan to release the training code later. Stay tuned for more updates!
We plan to release more details later. Stay tuned for more updates!
Since the frame_stride and frame number (16) are fixed, you may only sample from part of the video (e.g., with frame_stride as 6, the latest frame we can get is...