Meng-Jiun Chiou

Hi @hukkai @kennymckormick , is there any update on supporting AVA-Kinetics? Thanks!

Note that the repository has gone through a big update just now (see the commit `v0.2 update`) since the original codebase consists of some unused code segments which make it...

Would like to know if there's source code available too!

Same issue here.

Adding `--cfg-option gpu_ids=[0]` to the commands would work without modifying the config files.

Yes I found I did not follow the same hyper parameters (hidden size, batch_size, learning rate decay). I will fix them and try again. Thanks very much! :)

@pzzhang Really appreciate it if you could clarify this! - GPU type, number of GPUs, memory of each GPU used, training time The example command you provided in [oscarplus-pretraining](https://github.com/microsoft/Oscar/blob/master/VinVL_MODEL_ZOO.md#oscarplus-pretraining) shows...

@pzzhang Thank you for your reply! How about the training resources (gpu type/memory/time) you used? I'm working on less capable GPUs, so I am also wondering how I should modify...

Hi @pzzhang I see that I need ~22 days to pretrain OSCAR+ on 8 V100 GPUs, each 21GB memory occupied. As V100 has 32G memory available, I am considering increase...

@pzzhang Thank you for your detailed reply. I really appreciate it! :) I have another two critical questions - Oscar+ consists of two types of training samples, namely, __ or...