Problem in training with resNet18 backbone

Thanks for the great job.
So far I m trying to train with "resnet18 + without DCN". But it occurs error as bellow.
`
File "/home/administrator/anaconda3/envs/CenterNet/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 778, in forward
output_padding, self.groups, self.dilation)
RuntimeError: Given transposed=1, weight of size 2048 256 4 4, expected input[8, 512, 16, 16] to have 2048 channels, but got 512 channels instead
`

Start by reproducing training with the resnet18 backbone and DCN disabled, then inspect the backbone and transposed-convolution configuration implicated by the torch.nn.modules.conv.py traceback. Compare the expected and actual channel counts and confirm that training proceeds without the mismatch; the issue names no project files or tests.

Written by the indexing model from the issue text.