Varying the number of input channels

[cnr0724]

Firstly, thanks for the great work.
When I try to run Centernet with custom data, channel number change is required.
Any help would be appreciated.

[cnr0724]

Traceback (most recent call last):
File "main.py", line 102, in
main(opt)
File "main.py", line 70, in main
log_dict_train, _ = trainer.train(epoch, train_loader)
File "/root/CenterNet/src/lib/trains/base_trainer.py", line 119, in train
return self.run_epoch('train', epoch, data_loader)
File "/root/CenterNet/src/lib/trains/base_trainer.py", line 69, in run_epoch
output, loss, loss_stats = model_with_loss(batch)
File "/root/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 493, in call
result = self.forward(*input, **kwargs)
File "/root/CenterNet/src/lib/trains/base_trainer.py", line 19, in forward
outputs = self.model(batch['input'])
File "/root/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 493, in call
result = self.forward(*input, **kwargs)
File "/root/CenterNet/src/lib/models/networks/pose_dla_dcn.py", line 481, in forward
x = self.base(x)
File "/root/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 493, in call
result = self.forward(*input, **kwargs)
File "/root/CenterNet/src/lib/models/networks/pose_dla_dcn.py", line 300, in forward
x = getattr(self, 'level{}'.format(i))(x)
File "/root/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 493, in call
result = self.forward(*input, **kwargs)
File "/root/CenterNet/src/lib/models/networks/pose_dla_dcn.py", line 227, in forward
x = self.root(x2, x1, *children)
File "/root/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 493, in call
result = self.forward(*input, **kwargs)
File "/root/CenterNet/src/lib/models/networks/pose_dla_dcn.py", line 169, in forward
x = self.conv(torch.cat(x, 3))
File "/root/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py", line 493, in call
result = self.forward(*input, **kwargs)
File "/root/anaconda3/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 338, in forward
self.padding, self.dilation, self.groups)
RuntimeError: Given groups=1, weight of size 64 128 1 1, expected input[2, 64, 480, 540] to have 128 channels, but got 64 channels instead

This error happens.