rahimentezari
rahimentezari
I could not build crfasrnn yet. would you please which link of caffe-crfasrnn i should use?
Solved. I created another dataset 32x32 for CIFAR, using the code in https://github.com/CSAILVision/NetDissect/blob/release1/script/makebroden.sh
@ZhuweiQin Could you use it for VGG on CIFAR10?
@andrewilyas Probably my question is related to this: I want to use FFCV on my tensor dataset, not ImageFolder, because I need to train SimCLR and my dataset has pairs...
> Hi @rahimentezari , thanks for using our code. I think this error comes with the problem of hessian calculation. You can try the other way of calculating hessian inverse...
> > Hi @rahimentezari , thanks for using our code. I think this error comes with the problem of hessian calculation. You can try the other way of calculating hessian...
Tnx for your swift answer. So rows of mul_nor.m is the items and columns correspond to the BOW with values between [0,1]? what is items.dat?
same problem here https://github.com/Vchitect/VBench/issues/87
I downloaded the videos from the google drive uploaded by vbench team. Do you have these 4 videos above somewhere so that I can quickly check?
full_info.json ``` [ { "prompt_en": "d0", "dimension": [ "subject_consistency" ], "video_list": [ "sampled_videos/d0.mp4" ] } ] ``` eval_results.json ``` { "subject_consistency": [ 0.0, [ { "video_path": "sampled_videos/d0.mp4", "video_results": 0.0 }...