Run trainval_net_SCL.py with custom dataset raises RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. about scl HOT 4 CLOSED

Hi, I think it's data loader problem so it should be coming for both scl and strong-weak. Maybe you should try to find for which data point exactly this problem is coming. And for training strong-weak which code did you use?

from scl.

@harsh-99 I used the strong-weak code in this repository. Just with:

CUDA_VISIBLE_DEVICES=$1 python trainval_net_global_local.py --cuda --net vgg16 --dataset mydataset_source --dataset_t mydataset_target --gc --lc --save_dir output

from scl.

I've figured it out. The SCL do not support batch size other than 1. Because if batch size = 2, "pooled_feat" will add 256 channels after each one in "feat1, feat2, feat3". This will cause a shape mismatch in "netD_inst" because the channels are hard-coded like 2048+128+128+128. So I just changed the cfgs and train it for a longer time. Still appreciate your great work!

from scl.

@SkeletonOne Thanks a lot for pointing out that. I will try to add the functionality of batch size greater 1. In case if you have done that, feel free to send PR.

from scl.