litingsjj

I have same problem, and I want RGB picture, how to deal with it?

Same question！

Also, I train mobilenetv2 in cifar-10. here is the acc with grafting: Namespace(a=0.4, batch_size=128, c=500, cifar=10, cos=True, device='cuda', difflr=True, epochs=200, i=1, lr=0.1, model='mobilenetv2', num=2, print_frequence=1000, r=None, s='checkpoint/grafting_cifar10_mobilenetv2') Session:checkpoint/grafting_cifar10_mobilenetv2 Model:1 PID:27213...

I calculate the number of weights which less than 0.001, not filters.

I guess combine lables with 'van', 'truck' to 'car' and 'Person_sitting' to 'Pedestrian'? But why calculate 'dontcare' and ignore 'tram'?

Same question.

@nqanh Thanks! But I still don't understand, for pascal_voc dataset, I find segmentationclass only have 2913 .png less than train samples. If I want use it to affordanceNet and don't...

And about your dataset(IIT), I download the `IIT_Affordances_2017`dataset. Can you tell me how to deal with it to get dataset like yours? I find the dataset don't have .png. I'm...

@thanhtoando thanks!

roi_alignment is implemented