stefan_liu

train parameters size mismatch

37

- follow [testing](https://github.com/mbrossar/ai-imu-dr#:~:text=imu%2Ddr.git-,Testing,-Download%20reformated%20pickle) steps, but meet the following error. It seems that the model parameters do not correspond to the model definition. ```bash /data/github_code/ai-imu-dr/src/main_kitti.py in launch(args) 29 30 if args.test_filter:...

The feature before the last GAP should be 7x7, but the feature in current model is 28x28. https://github.com/HolmesShuan/ResNet-18-Caffemodel-on-ImageNet/blob/master/deploy.prototxt shows a correct resnet18 structure.

Training code for okvqa and vqav2 finetune

17

Thanks for the great work. Will the code related to the following table be open source soon？And does the current code support okvqa finetune?  Thanks.

How to train on multiple GPU (w/ small vRAM)

4

Thanks for the great work. Do you have any recommended solutions for running finetune.py code on multiple small memory GPUs (such like finetune lamma-30b on 8xV100)? Is it possible for...

MoVQ implementation question

2

I have some questions regarding the implementation of MoVQ and would appreciate your clarification. From the original MoVQ paper, it is mentioned that a multi-channle VQ is adopted.  However,...

Fail to reproduce the reconstruction result

1

Thank you for the excellent open-source work. - reproduce the reconstruction result （ImageNet dataset） （refer to Table 2 from https://arxiv.org/pdf/2312.03511.pdf ） | | FID ↓ | SSIM ↑ | PSNR...