i use one common image without face to test, but one bug occurs? expect to explain it?

[upsx]

File ".\demo.py", line 74, in detect
y = net(x)
File "C:\Users\xxxxx\Miniconda3\lib\site-packages\torch\nn\modules\module.py", line 493, in call
result = self.forward(*input, **kwargs)
File "C:\Users\xxxxx\Desktop\local\Pyramidbox.pytorch\pyramidbox.py", line 252, in forward
priors)
File "C:\Users\xxxxx\Desktop\local\Pyramidbox.pytorch\layers\functions\detection.py", line 65, in forward
boxes_, scores, self.nms_thresh, self.top_k)
ValueError: not enough values to unpack (expected 2, got 0)
PS C:\Users\shuxin\Desktop\local\Pyramidbox.pytorch>

[zz827]

File ".\demo.py", line 74, in detect
y = net(x)
File "C:\Users\xxxxx\Miniconda3\lib\site-packages\torch\nn\modules\module.py", line 493, in call
result = self.forward(*input, **kwargs)
File "C:\Users\xxxxx\Desktop\local\Pyramidbox.pytorch\pyramidbox.py", line 252, in forward
priors)
File "C:\Users\xxxxx\Desktop\local\Pyramidbox.pytorch\layers\functions\detection.py", line 65, in forward
boxes_, scores, self.nms_thresh, self.top_k)
ValueError: not enough values to unpack (expected 2, got 0)
PS C:\Users\shuxin\Desktop\local\Pyramidbox.pytorch>

try to return keep and 0 in the nms function, that works for me.

[zyselvis]

In the function of nms, there is an exception return needs one more value

keep = scores.new(scores.size(0)).zero_().long()
if boxes.numel() == 0:
    return keep

solved by replacing by

keep = scores.new(scores.size(0)).zero_().long()
if boxes.numel() == 0:
    return keep, 0

[Llq201809]

In the function of nms, there is an exception return needs one more value

keep = scores.new(scores.size(0)).zero_().long()
if boxes.numel() == 0:
    return keep

solved by replacing by

keep = scores.new(scores.size(0)).zero_().long()
if boxes.numel() == 0:
    return keep, 0

but it occurs a new error after replacing:

File "/home/XXXX/Pyramidbox.pytorch-master/layers/functions/detection.py", line 66, in forward
output[i, cl, :count] = torch.cat((scores[ids[:count]].unsqueeze(1),
RuntimeError: cannot unsqueeze empty tensor

Have you encountered this problem? How to solve it?

[ZZH2950228]

i have got the same problem as you,and how to deal with this problem