D:\trt\mmdetection3d-dev-1.x>python demo/pcd_demo.py demo/data/kitti/000008.bin configs/second/second_hv_secfpn_8xb6-80e_kitti-3d-car.py checkpoints/second_hv_secfpn_8xb6-80e_kitti-3d-car-75d9305e.pth --show
01/06 14:07:33 - mmengine - WARNING - Display device not found. `--show` is forced to False
D:\trt\mmdetection3d-dev-1.x\mmdet3d\models\dense_heads\anchor3d_head.py:95: UserWarning: dir_offset and dir_limit_offset will be depressed and be incorporated into box coder in the future
'dir_offset and dir_limit_offset will be depressed and be '
Loads checkpoint by local backend from path: checkpoints/second_hv_secfpn_8xb6-80e_kitti-3d-car-75d9305e.pth
The model and loaded state dict do not match exactly
size mismatch for middle_encoder.conv_input.0.weight: copying a param with shape torch.Size([16, 3, 3, 3, 4]) from checkpoint, the shape in current model is torch.Size([3, 3, 3, 4, 16]).
size mismatch for middle_encoder.encoder_layers.encoder_layer1.0.0.weight: copying a param with shape torch.Size([16, 3, 3, 3, 16]) from checkpoint, the shape in current model is torch.Size([3, 3, 3, 16, 16]).
size mismatch for middle_encoder.encoder_layers.encoder_layer2.0.0.weight: copying a param with shape torch.Size([32, 3, 3, 3, 16]) from checkpoint, the shape in current model is torch.Size([3, 3, 3, 16, 32]).
size mismatch for middle_encoder.encoder_layers.encoder_layer2.1.0.weight: copying a param with shape torch.Size([32, 3, 3, 3, 32]) from checkpoint, the shape in current model is torch.Size([3, 3, 3, 32, 32]).
size mismatch for middle_encoder.encoder_layers.encoder_layer2.2.0.weight: copying a param with shape torch.Size([32, 3, 3, 3, 32]) from checkpoint, the shape in current model is torch.Size([3, 3, 3, 32, 32]).
size mismatch for middle_encoder.encoder_layers.encoder_layer3.0.0.weight: copying a param with shape torch.Size([64, 3, 3, 3, 32]) from checkpoint, the shape in current model is torch.Size([3, 3, 3, 32, 64]).
size mismatch for middle_encoder.encoder_layers.encoder_layer3.1.0.weight: copying a param with shape torch.Size([64, 3, 3, 3, 64]) from checkpoint, the shape in current model is torch.Size([3, 3, 3, 64, 64]).
size mismatch for middle_encoder.encoder_layers.encoder_layer3.2.0.weight: copying a param with shape torch.Size([64, 3, 3, 3, 64]) from checkpoint, the shape in current model is torch.Size([3, 3, 3, 64, 64]).
size mismatch for middle_encoder.encoder_layers.encoder_layer4.0.0.weight: copying a param with shape torch.Size([64, 3, 3, 3, 64]) from checkpoint, the shape in current model is torch.Size([3, 3, 3, 64, 64]).
size mismatch for middle_encoder.encoder_layers.encoder_layer4.1.0.weight: copying a param with shape torch.Size([64, 3, 3, 3, 64]) from checkpoint, the shape in current model is torch.Size([3, 3, 3, 64, 64]).
size mismatch for middle_encoder.encoder_layers.encoder_layer4.2.0.weight: copying a param with shape torch.Size([64, 3, 3, 3, 64]) from checkpoint, the shape in current model is torch.Size([3, 3, 3, 64, 64]).
size mismatch for middle_encoder.conv_out.0.weight: copying a param with shape torch.Size([128, 3, 1, 1, 64]) from checkpoint, the shape in current model is torch.Size([3, 1, 1, 64, 128]).
01/06 14:07:33 - mmengine - WARNING - Failed to search registry with scope "mmdet3d" in the "function" registry tree. As a workaround, the current "function" registry in "mmengine" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmdet3d" is a correct scope, or whether the registry is initialized.
01/06 14:07:36 - mmengine - WARNING - `Visualizer` backend is not initialized because save_dir is None.
C:\Users\Administrator\miniforge3\envs\DDD\lib\site-packages\torch\functional.py:478: UserWarning: torch.meshgrid: in anupcoming release, it will be required to pass the indexing argument. (Triggered internally at
C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\TensorShape.cpp:2895.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
Inference ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
01/06 14:07:39 - mmengine - INFO - results have been saved at output输出的json文件为空，是什么问题？
最新发布
扫一扫
1070
到【灌水乐园】发言
