images_unsup_strong batchsize=1 get problem

[SouthMaiya]

The batch size of images_unsup_strong is fixed as 1, it generates issue:
preds_student_unsup = model(images_unsup_strong)
File "/home/zxr409/anaconda3/envs/zxq_cvpod/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/zxr409/anaconda3/envs/zxq_cvpod/lib/python3.7/site-packages/torch/nn/parallel/distributed.py", line 886, in forward
output = self.module(*inputs[0], **kwargs[0])
File "/home/zxr409/anaconda3/envs/zxq_cvpod/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/media/zxr409/58fab247-2ac6-40d5-9db7-af402531c0c4/zxq/work/semi-seg/SemiSeg-AEL-main/semseg/models/model_helper.py", line 48, in forward
pred_head = self.decoder([f1, f2,feat1, feat2])
File "/home/zxr409/anaconda3/envs/zxq_cvpod/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/media/zxr409/58fab247-2ac6-40d5-9db7-af402531c0c4/zxq/work/semi-seg/SemiSeg-AEL-main/semseg/models/decoder.py", line 54, in forward
aspp_out = self.aspp(x4)
File "/home/zxr409/anaconda3/envs/zxq_cvpod/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/media/zxr409/58fab247-2ac6-40d5-9db7-af402531c0c4/zxq/work/semi-seg/SemiSeg-AEL-main/semseg/models/base.py", line 47, in forward
feat1 = F.upsample(self.conv1(x), size=(h, w), mode='bilinear', align_corners=True)
File "/home/zxr409/anaconda3/envs/zxq_cvpod/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/zxr409/anaconda3/envs/zxq_cvpod/lib/python3.7/site-packages/torch/nn/modules/container.py", line 141, in forward
input = module(input)
File "/home/zxr409/anaconda3/envs/zxq_cvpod/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/zxr409/anaconda3/envs/zxq_cvpod/lib/python3.7/site-packages/torch/nn/modules/batchnorm.py", line 179, in forward
self.eps,
File "/home/zxr409/anaconda3/envs/zxq_cvpod/lib/python3.7/site-packages/torch/nn/functional.py", line 2280, in batch_norm
_verify_batch_size(input.size())
File "/home/zxr409/anaconda3/envs/zxq_cvpod/lib/python3.7/site-packages/torch/nn/functional.py", line 2248, in _verify_batch_size
raise ValueError("Expected more than 1 value per channel when training, got input size {}".format(size))
ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 256, 1, 1])

[SouthMaiya]

why the batch size of images_unsup_strong must be 1?