pangsu0613 / CLOCs

CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detection
MIT License
351 stars 68 forks source link

About evaluation #73

Closed 2757 closed 2 years ago

2757 commented 2 years ago

Hello! @pangsu0613 The model I trained myself can be evaluated, but it will make mistakes when I use your model.I don't think I have changed your code. Traceback (most recent call last): File "./pytorch/train.py", line 966, in fire.Fire() File "/root/anaconda3/envs/CLOCs/lib/python3.6/site-packages/fire/core.py", line 141, in Fire
component_trace = _Fire(component, args, parsed_flag_args, context, name) File "/root/anaconda3/envs/CLOCs/lib/python3.6/site-packages/fire/core.py", line 471, in _Fire
target=component.name) File "/root/anaconda3/envs/CLOCs/lib/python3.6/site-packages/fire/core.py", line 681, in _CallAndUpdateTrace component = fn(*varargs, **kwargs) File "./pytorch/train.py", line 660, in evaluate torchplus.train.try_restore_latest_checkpoints(model_dir, [fusion_layer]) File "/root/CLOCs/torchplus/train/checkpoint.py", line 146, in try_restore_latest_checkpoints
restore(latest_ckpt, model) File "/root/CLOCs/torchplus/train/checkpoint.py", line 117, in restore model.load_state_dict(torch.load(ckpt_path)) File "/root/anaconda3/envs/CLOCs/lib/python3.6/site-packages/torch/nn/modules/module.py", line 777, in load_state_dict self.class.name, "\n\t".join(error_msgs))) RuntimeError: Error(s) in loading state_dict for fusion: size mismatch for fuse_2d_3d.0.weight: copying a param with shape torch.Size([18, 4, 1, 1]) from checkpoint, the shape in current model is torch.Size([18, 5, 1, 1]).