Circle loss report errors

[ReverseSystem001]

when i run Circle loss, it reports errors like bellow: Do you run it successfully?
Traceback (most recent call last):
File "train.py", line 388, in
main()
File "train.py", line 60, in main
mp.spawn(main_worker, nprocs=ngpus_per_node, args=(ngpus_per_node, cfg))
File "/usr/local/lib64/python3.6/site-packages/torch/multiprocessing/spawn.py", line 171, in spawn
while not spawn_context.join():
File "/usr/local/lib64/python3.6/site-packages/torch/multiprocessing/spawn.py", line 118, in join
raise Exception(msg)
Exception:

-- Process 1 terminated with the following error:
Traceback (most recent call last):
File "/usr/local/lib64/python3.6/site-packages/torch/multiprocessing/spawn.py", line 19, in _wrap
fn(i, *args)
File "/home/vision_rd/face_Recognition/cavaface.pytorch_bake/train.py", line 291, in main_worker
outputs = head(features, labels)
File "/usr/local/lib64/python3.6/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/usr/local/lib64/python3.6/site-packages/torch/nn/parallel/distributed.py", line 447, in forward
output = self.module(*inputs[0], **kwargs[0])
File "/usr/local/lib64/python3.6/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/home/vision_rd/face_Recognition/cavaface.pytorch_bake/head/metrics.py", line 590, in forward
output = torch.logsumexp(logit_n, dim=1) + torch.logsumexp(logit_p, dim=1)
IndexError: Dimension out of range (expected to be in range of [-1, 0], but got 1)

[cavalleria]

have you solved it? i have not meet this bug.

[ReverseSystem001]

have you solved it? i have not meet this bug.

I have not. I will try later.

[luameows]

@cavalleria I think the function of circle loss may have some bugs, especially in the forward step. I cannot figure out why u use torch.logsumexp to compute the output feature. For nn.CrossEntropyLoss has already done Softmax already, I think u do not neeed to compute softmax again in the forward step.

[cavalleria]

@cavalleria I think the function of circle loss may have some bugs, especially in the forward step. I cannot figure out why u use torch.logsumexp to compute the output feature. For nn.CrossEntropyLoss has already done Softmax already, I think u do not neeed to compute softmax again in the forward step.

circle loss not use nn.CrossEntropyLoss, but use softplus. please refer below code.https://github.com/cavalleria/cavaface.pytorch/blob/13182ecc349ca050fa5a877045390a41037313a7/train.py#L218