icnet and dfanet error about segmentron HOT 2 CLOSED

Traceback (most recent call last):
  File "./tools/train.py", line 224, in <module>
    trainer.train()
  File "./tools/train.py", line 136, in train
    outputs = self.model(images)
  File "/usr/local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 493, in __call__
    result = self.forward(*input, **kwargs)
  File "/usr/local/lib/python3.6/site-packages/torch/nn/parallel/distributed.py", line 376, in forward
    output = self.module(*inputs[0], **kwargs[0])
  File "/usr/local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 493, in __call__
    result = self.forward(*input, **kwargs)
  File "/SegmenTron/segmentron/models/dfanet.py", line 53, in forward
    stage2_enc2 = self.enc2_2(torch.cat([stage1_enc2, stage1_out], dim=1))
RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 1. Got 196 and 193 in dimension 2 at /pytorch/aten/src/THC/generic/THCTensorMath.cu:71