RTDETR : [rank3]: File "/mnt/nas2/users/sbchoi/transformers/src/transformers/models/rt_detr/modeling_rt_detr.py", line 1357, in forward [rank3]: fused_feature_map = torch.concat([top_fpn_feature_map, backbone_feature_map], dim=1) [rank3]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [rank3]: RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 76 but got size 75 for tensor number 1 in the list. top_fpn_feature_map : 76 backbone_feature_map : 75

backbone_feature_map.shape torch.Size([8, 256, 38, 38]) top_fpn_feature_map.shape torch.Size([8, 256, 19, 19]) backbone_feature_map.shape torch.Size([8, 256, 75, 75]) top_fpn_feature_map.shape torch.Size([8, 256, 38, 38]) backbone_feature_map.shape torch.Size([8, 256, 38, 38]) top_fpn_feature_map.shape torch.Size([8, 256, 19, 19]) backbone_feature_map.shape torch.Size([8, 256, 75, 75]) top_fpn_feature_map.shape torch.Size([8, 256, 38, 38])

DFine TORCH_DISTRIBUTED_DEBUG=DETAIL

[rank1]: RuntimeError: Expected to have finished reduction in the prior iteration before starting a new one. This error indicates that your module has parameters that were not used in producing loss. You can enable unused parameter detection by passing the keyword argument find_unused_parameters=True to torch.nn.parallel.DistributedDataParallel, and by [rank1]: making sure all forward function outputs participate in calculating loss. [rank1]: If you already have done the above, then the distributed data parallel module wasn't able to locate the output tensors in the return value of your module's forward function. Please include the loss function and the structure of the return value of forward of your module when reporting this issue (e.g. list, dict, iterable). [rank1]: Parameters which did not receive grad for rank 1: model.decoder.pre_bbox_head.layers.2.bias, model.decoder.pre_bbox_head.layers.2.weight, model.decoder.pre_bbox_head.layers.1.bias, model.decoder.pre_bbox_head.layers.1.weight, model.decoder.pre_bbox_head.layers.0.bias, model.decoder.pre_bbox_head.layers.0.weight