panyi95 / getanet Goto Github PK

hello,

I noticed that the processed DroneRGBT dataset you provided is no longer available. Could you please share it again?
Thank for your awesome work!

Best regards

True torch.Size([4, 1024]) torch.Size([1, 4096])
Traceback (most recent call last):
File "/home//work/crowd/DEFNet-main/DEFNet/train.py", line 57, in
trainer.train()
File "/home//work/crowd/DEFNet-main/DEFNet/utils/regression_trainer.py", line 113, in train
self.train_eopch()
File "/home//work/crowd/DEFNet-main/DEFNet/utils/regression_trainer.py", line 142, in train_eopch
loss = self.criterion(prob_list, outputs)
File "/environment/miniconda3/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home//work/crowd/DEFNet-main/DEFNet/losses/bay_loss.py", line 25, in forward
pre_count = torch.sum(pre_density[idx].view((1, -1)) * prob, dim=1) # flatten into vector
RuntimeError: The size of tensor a (4096) must match the size of tensor b (1024) at non-singleton dimension 1