Zhenfang Chen

Yes, it supports as long as you comment the codes in row_pooling_cuda.c. Please read the code for details. And I have been using it for a while and so far...

> Dear auhtor, > > I cannot download features from the link provided by you, It outputs error information as follows: > > 抱歉，您目前无法查看或下载此文件。 > > 最近查看或下载此文件的用户过多。请稍后再尝试访问此文件。如果您尝试访问的文件特别大或由很多人一起共享，则可能需要长达 24 小时才能查看或下载该文件。如果 24...

Dear Meng, Since I have always been using an educational (professional) google account, which has no file size limit. I suspect the reason is that the file have been too...

1. Thank you for your interest and questions! 2. Currently, I have no time to check the frames. One possible reason may be the frame decoder of the videos have...

> Assuming we have the following: > > ``` > CHECKPOINT=/path/to/fsdp_sharded_checkpoint/checkpoint_last > CONSOLIDATED=/path/to/new_consolidated_checkpoint/ > RESHARDED=/path/to/new_resharded_checkpoint/ > MP=16 > ``` > > ### Step 0 > (Optional, if necessary) [Consolidate the...

Dear klshuster, Thanks for your reply. I have installed the Apex library carefully, following https://github.com/facebookresearch/metaseq/blob/main/docs/setup.md . Is there any. other possibility for the problem? Regards, Zhenfang

It seems that they are trying loading parameters of all the layer into the a single graphic card and then out of memory.

Hi, @huybery @liminghao1630 Thanks again for your exciting work! Is there any update on the issue mentioned? Regards,

Hi Minghao, Thanks for the great work! Could you please share some results and examples on how to evaluate existing models on your benchmark like how to get the results...