['Car', 'Pedestrian', 'Cyclist']
3
0 -39.68 -3 69.12 39.68 1
[0.16, 0.16, 4]
32
40000
4
64
0.78539
0.0
2
[3.9, 1.6, 1.56, 0.0, 3.9, 1.6, 1.56, 1.57, 0.8, 0.6, 1.73, 0.0, 0.8, 0.6, 1.73, 1.57, 1.76, 0.6, 1.73, 0.0, 1.76, 0.6, 1.73, 1.57]
[-1.78, -0.6, -0.6]
0.1
0.01
anchors:      const float anchors[num_anchors * len_per_anchor] = {
      3.9,1.6,1.56,0.0,
      3.9,1.6,1.56,1.57,
      0.8,0.6,1.73,0.0,
      0.8,0.6,1.73,1.57,
      1.76,0.6,1.73,0.0,
      1.76,0.6,1.73,1.57,
      };

anchors:      const float anchor_bottom_heights[num_classes] = {-1.78,-0.6,-0.6,};

########
2022-03-15 11:08:59,269   INFO  ------ Convert OpenPCDet model for TensorRT ------
2022-03-15 11:09:05,030   INFO  ==> Loading parameters from checkpoint ../../checkpoint_epoch_1.pth to CPU
2022-03-15 11:09:05,171   INFO  ==> Checkpoint trained from version: pcdet+0.3.0+0642cf0
2022-03-15 11:09:05,462   INFO  ==> Done (loaded 127/127)
/home/nvidia/project/pointpillar/CUDA-PointPillars-main/tool/pcdet/models/backbones_3d/vfe/pillar_vfe.py:45: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
  if inputs.shape[0] > self.part:
/home/nvidia/project/pointpillar/CUDA-PointPillars-main/tool/pcdet/models/backbones_2d/map_to_bev/pointpillar_scatter.py:31: TracerWarning: Converting a tensor to a Python number might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
  batch_size = coords[:, 0].max().int().item() + 1
Traceback (most recent call last):
  File "exporter.py", line 150, in <module>
    main()
  File "exporter.py", line 135, in main
    output_names = ['cls_preds', 'box_preds', 'dir_cls_preds'], # the model's output names
  File "/home/nvidia/.local/lib/python3.6/site-packages/torch/onnx/__init__.py", line 208, in export
    custom_opsets, enable_onnx_checker, use_external_data_format)
  File "/home/nvidia/.local/lib/python3.6/site-packages/torch/onnx/utils.py", line 92, in export
    use_external_data_format=use_external_data_format)
  File "/home/nvidia/.local/lib/python3.6/site-packages/torch/onnx/utils.py", line 530, in _export
    fixed_batch_size=fixed_batch_size)
  File "/home/nvidia/.local/lib/python3.6/site-packages/torch/onnx/utils.py", line 366, in _model_to_graph
    graph, torch_out = _trace_and_get_graph_from_model(model, args)
  File "/home/nvidia/.local/lib/python3.6/site-packages/torch/onnx/utils.py", line 319, in _trace_and_get_graph_from_model
    torch.jit._get_trace_graph(model, args, strict=False, _force_outplace=False, _return_inputs_states=True)
  File "/home/nvidia/.local/lib/python3.6/site-packages/torch/jit/__init__.py", line 338, in _get_trace_graph
    outs = ONNXTracedModule(f, strict, _force_outplace, return_inputs, _return_inputs_states)(*args, **kwargs)
  File "/home/nvidia/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/nvidia/.local/lib/python3.6/site-packages/torch/jit/__init__.py", line 426, in forward
    self._force_outplace,
  File "/home/nvidia/.local/lib/python3.6/site-packages/torch/jit/__init__.py", line 412, in wrapper
    outs.append(self.inner(*trace_inputs))
  File "/home/nvidia/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 720, in _call_impl
    result = self._slow_forward(*input, **kwargs)
  File "/home/nvidia/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 704, in _slow_forward
    result = self.forward(*input, **kwargs)
  File "/home/nvidia/project/pointpillar/CUDA-PointPillars-main/tool/pcdet/models/detectors/pointpillar.py", line 31, in forward
    spatial_features_2d = self.module_list[2](spatial_features) #"BaseBEVBackbone"
  File "/home/nvidia/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 720, in _call_impl
    result = self._slow_forward(*input, **kwargs)
  File "/home/nvidia/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 704, in _slow_forward
    result = self.forward(*input, **kwargs)
  File "/home/nvidia/project/pointpillar/CUDA-PointPillars-main/tool/pcdet/models/backbones_2d/base_bev_backbone.py", line 103, in forward
    stride = int(spatial_features.shape[2] / x.shape[2])
RuntimeError: Integer division of tensors using div or / is no longer supported, and in a future release div will perform true division as in Python 3. Use true_divide or floor_divide (// in Python) instead.```



when I generate onnx by exporter.py, i got the error 。 How can i fix it?

I tried export.py but could not do it because it didn't get the right input. 2022-10-28 04:02:25,943 INFO ==> Loading parameters from checkpoint ./pointpillar_7728.pth to CPU

Traceback (most recent call last):
  File "exporter.py", line 150, in <module>
    main()
  File "exporter.py", line 134, in main
    output_names = ['cls_preds', 'box_preds', 'dir_cls_preds'], # the model's output names
  File "/home/rjh1016/anaconda3/envs/openpcdet/lib/python3.7/site-packages/torch/onnx/__init__.py", line 365, in export
    export_modules_as_functions,
  File "/home/rjh1016/anaconda3/envs/openpcdet/lib/python3.7/site-packages/torch/onnx/utils.py", line 178, in export
    export_modules_as_functions=export_modules_as_functions,
  File "/home/rjh1016/anaconda3/envs/openpcdet/lib/python3.7/site-packages/torch/onnx/utils.py", line 1097, in _export
    dynamic_axes=dynamic_axes,
  File "/home/rjh1016/anaconda3/envs/openpcdet/lib/python3.7/site-packages/torch/onnx/utils.py", line 737, in _model_to_graph
    graph, params, torch_out, module = _create_jit_graph(model, args)
  File "/home/rjh1016/anaconda3/envs/openpcdet/lib/python3.7/site-packages/torch/onnx/utils.py", line 611, in _create_jit_graph
    graph, torch_out = _trace_and_get_graph_from_model(model, args)
  File "/home/rjh1016/anaconda3/envs/openpcdet/lib/python3.7/site-packages/torch/onnx/utils.py", line 527, in _trace_and_get_graph_from_model
    model, args, strict=False, _force_outplace=False, _return_inputs_states=True
  File "/home/rjh1016/anaconda3/envs/openpcdet/lib/python3.7/site-packages/torch/jit/_trace.py", line 1179, in _get_trace_graph
    outs = ONNXTracedModule(f, strict, _force_outplace, return_inputs, _return_inputs_states)(*args, **kwargs)
  File "/home/rjh1016/anaconda3/envs/openpcdet/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/rjh1016/anaconda3/envs/openpcdet/lib/python3.7/site-packages/torch/jit/_trace.py", line 134, in forward
    self._force_outplace,
  File "/home/rjh1016/anaconda3/envs/openpcdet/lib/python3.7/site-packages/torch/jit/_trace.py", line 120, in wrapper
    outs.append(self.inner(*trace_inputs))
  File "/home/rjh1016/anaconda3/envs/openpcdet/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/rjh1016/anaconda3/envs/openpcdet/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1118, in _slow_forward
    result = self.forward(*input, **kwargs)
**TypeError: forward() missing 1 required positional argument: 'batch_dict'**

I guess the model architecture is still same with the OpenPCDet. But I don't know what to do first to export onnx from this file. My torch version is 1.12.1+cu102, cuda version is 11.3 and onnx version is 1.12.0

trt_infer: 1: [stdArchiveReader.cpp::nvinfer1::rt::StdArchiveReader::StdArchiveReader::35] Error Code 1: Serialization (Serialization assertion safeVersionRead == safeSerializationVersion failed.Version tag does not match. Note: Current Version: 0, Serialized Engine Version: 97) trt_infer: 4: [runtime.cpp::nvinfer1::Runtime::deserializeCudaEngine::50] Error Code 4: Internal Error (Engine deserialization failed.)

Hi, I use jetson nano 2 gb Jetpack 4.6 CUDA 10.2 tensorrt 8.0 onnx 1.8

After compling, I run the demo, got error: GPU has cuda devices: 1 ----device id: 0 info---- GPU : NVIDIA Tegra X1 Capbility: 5.3 Global memory: 1979MB Const memory: 64KB SM in a block: 48KB warp size: 32 threads in a block: 1024 block dim: (1024,1024,64) grid dim: (2147483647,65535,65535)

Building TRT engine. [libprotobuf ERROR google/protobuf/text_format.cc:298] Error parsing text-format onnx2trt_onnx.ModelProto: 1:9: Message type “onnx2trt_onnx.ModelProto” has no field named “version”. trt_infer: ModelImporter.cpp:682: Failed to parse ONNX model from file: …/…/model/pointpillar.onnx : failed to parse onnx model file, please check the onnx version and trt support op!

So can you tell me how to solve this error or which version of onnx do you use?

I just try to transform my own pth to onnx ,but exporter.py has an issue "report pytorch" , i try to set the env as readme in tools ,but cant find a pytorch1.11.0 with cuda11.4 (pytorch.org only has cu113,cu115,cu116)

thank you very much

When I follow export gride export onnx from pointpillar_7729.pth

I found this error

root@pc-MS-7B89:/workspace/ssh-docker/workspace/CUDA-PointPillars/tool# python exporter.py --ckpt ../model/pointpillar_7729.pth 2022-06-08 10:17:39,104 INFO ------ Convert OpenPCDet model for TensorRT ------ 2022-06-08 10:17:40,746 INFO ==> Loading parameters from checkpoint ../model/pointpillar_7729.pth to CPU 2022-06-08 10:17:40,760 INFO ==> Done (loaded 127/127) Traceback (most recent call last): File "exporter.py", line 150, in main() File "exporter.py", line 126, in main torch.onnx.export(model, # model being run File "/usr/local/lib/python3.8/dist-packages/torch/onnx/init.py", line 225, in export return utils.export(model, args, f, export_params, verbose, training, File "/usr/local/lib/python3.8/dist-packages/torch/onnx/utils.py", line 85, in export _export(model, args, f, export_params, verbose, training, input_names, output_names, File "/usr/local/lib/python3.8/dist-packages/torch/onnx/utils.py", line 632, in _export _model_to_graph(model, args, verbose, input_names, File "/usr/local/lib/python3.8/dist-packages/torch/onnx/utils.py", line 409, in _model_to_graph graph, params, torch_out = _create_jit_graph(model, args, File "/usr/local/lib/python3.8/dist-packages/torch/onnx/utils.py", line 379, in _create_jit_graph graph, torch_out = _trace_and_get_graph_from_model(model, args) File "/usr/local/lib/python3.8/dist-packages/torch/onnx/utils.py", line 342, in _trace_and_get_graph_from_model torch.jit._get_trace_graph(model, args, strict=False, _force_outplace=False, _return_inputs_states=True) File "/usr/local/lib/python3.8/dist-packages/torch/jit/_trace.py", line 1148, in _get_trace_graph outs = ONNXTracedModule(f, strict, _force_outplace, return_inputs, _return_inputs_states)(*args, **kwargs) File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/usr/local/lib/python3.8/dist-packages/torch/jit/_trace.py", line 93, in forward in_vars, in_desc = _flatten(args) RuntimeError: Only tuples, lists and Variables supported as JIT inputs/outputs. Dictionaries and strings are also accepted but their usage is not recommended. But got unsupported type int

1. running demo twice，but has different nms_pred. first time result: `0 0 Pedestrian 0 0 0 0 0 0 0 8.801592 -22.979778 -0.887550 0.699091 1.681269 0.955211 6.057534 0.886240

0 1 Car 0 0 0 0 0 0 0 12.719068 -28.110558 -0.953992 1.454717 1.440981 3.581757 1.694893 0.868306

0 2 Car 0 0 0 0 0 0 0 47.362293 -28.365889 -0.973110 1.458381 1.436911 3.486596 1.667450 0.857365

0 3 Cyclist 0 0 0 0 0 0 0 6.083002 -20.606743 -0.793952 0.521009 1.870310 1.742529 6.440432 0.723123

0 4 Pedestrian 0 0 0 0 0 0 0 38.801476 -24.652239 -0.866866 0.633589 1.681634 0.863217 7.058193 0.640031

1 0 Car 0 0 0 0 0 0 0 12.139722 -28.273060 -0.901822 1.527452 1.430591 3.621138 1.697318 0.906442

1 1 Car 0 0 0 0 0 0 0 46.858337 -28.242884 -0.900239 1.531207 1.431682 3.568392 1.667983 0.901812

1 2 Pedestrian 0 0 0 0 0 0 0 8.465889 -23.032154 -0.846444 0.645208 1.671196 0.881344 6.123196 0.870731

1 3 Pedestrian 0 0 0 0 0 0 0 38.177109 -24.687294 -0.824349 0.597974 1.776301 0.773330 6.553991 0.749789

1 4 Cyclist 0 0 0 0 0 0 0 6.105674 -20.675518 -0.786540 0.537707 1.857258 1.734642 6.339981 0.717096

2 0 Car 0 0 0 0 0 0 0 11.585449 -28.402311 -0.755955 1.502408 1.468927 3.476464 1.708760 0.914412

2 1 Car 0 0 0 0 0 0 0 46.331028 -28.403627 -0.756222 1.510054 1.459696 3.494760 1.701342 0.892783

2 2 Pedestrian 0 0 0 0 0 0 0 2.864436 -24.456514 -0.795387 0.683705 1.716824 0.740641 6.564042 0.670138`

and second result:

`0 0 Pedestrian 0 0 0 0 0 0 0 8.803576 -22.977654 -0.887780 0.696375 1.681500 0.958435 6.070025 0.884506

0 1 Car 0 0 0 0 0 0 0 12.719075 -28.110571 -0.954006 1.454742 1.441006 3.581787 1.694892 0.868305

0 2 Car 0 0 0 0 0 0 0 47.362247 -28.365870 -0.973042 1.458364 1.436905 3.486571 1.667452 0.857371

0 3 Cyclist 0 0 0 0 0 0 0 6.087093 -20.607618 -0.795005 0.520003 1.870543 1.743158 6.437171 0.718292

0 4 Pedestrian 0 0 0 0 0 0 0 38.801697 -24.651608 -0.866716 0.631521 1.683618 0.862992 3.981019 0.638015

1 0 Car 0 0 0 0 0 0 0 12.137152 -28.273653 -0.905428 1.524646 1.433306 3.596805 1.698718 0.907847

1 1 Car 0 0 0 0 0 0 0 46.859871 -28.246393 -0.904772 1.531922 1.435942 3.555500 1.668782 0.903067

2 0 Car 0 0 0 0 0 0 0 11.584668 -28.394022 -0.754803 1.500816 1.474386 3.450029 1.709120 0.922249

2 1 Car 0 0 0 0 0 0 0 46.331684 -28.388617 -0.756081 1.507665 1.464798 3.450339 1.705996 0.903383

2 2 Pedestrian 0 0 0 0 0 0 0 2.865523 -24.451092 -0.794181 0.643265 1.719354 0.729399 7.015512 0.763062

2 3 Pedestrian 0 0 0 0 0 0 0 8.110272 -23.076586 -0.753614 0.546372 1.720677 0.841813 2.003850 0.684011

2 4 Pedestrian 0 0 0 0 0 0 0 37.609577 -24.749792 -0.808255 0.581791 1.683830 0.778918 4.070107 0.650024`

Is this normal？？

2. reset score_thresh=0.5, then has much nms bbox num_obj:241072 numbers of Bndbox need to be nms:241072 why？？

3. 同样的模型，openPcdet输出结果显示正常，onnx部署之后检测结果显示异常。。。。

thanks and waiting for your reply.

i use tenrorrt8.4 and when i am running ./demo ,Building TRT engine: there are some errors: Building TRT engine. trt_infer: Could not register plugin creator - ::PillarScatterPlugin version 1 trt_infer: parsers/onnx/ModelImporter.cpp:780: While parsing node number 4 [ScatterBEV -> "479"]: trt_infer: parsers/onnx/ModelImporter.cpp:781: --- Begin node --- trt_infer: parsers/onnx/ModelImporter.cpp:782: input: "403" input: "coords" input: "params" output: "479" name: "onnx_graphsurgeon_node_0" op_type: "ScatterBEV" trt_infer: ModelImporter.cpp:751: --- End node --- trt_infer: ModelImporter.cpp:754: ERROR: builtin_op_importers.cpp:4951 In function importFallbackPluginImporter: [8] Assertion failed: creator && "Plugin not found, are the plugin name, version, and namespace correct?" : failed to parse onnx model file, please check the onnx version and trt support op! How can i fix the problem?

at line 323 of preprocess_kernels.cu, the code calcuate offset.

//calculate offset
float x_offset = voxel_x / 2 + cordsSM[pillar_idx_inBlock].w * voxel_x + range_min_x;
float y_offset = voxel_y / 2 + cordsSM[pillar_idx_inBlock].z * voxel_y + range_min_y;
float z_offset = voxel_z / 2 + cordsSM[pillar_idx_inBlock].y * voxel_z + range_min_z;

I think the w means intensity， when calcuate x_offset, why voxel_x multiply by cordsSM[pillar_idx_inBlock].w, not cordsSM[pillar_idx_inBlock].x when calcuate y_offset, why voxel_y multiply by cordsSM[pillar_idx_inBlock].z, not cordsSM[pillar_idx_inBlock].y when calcuate z_offset, why voxel_z multiply by cordsSM[pillar_idx_inBlock].y, not cordsSM[pillar_idx_inBlock].z

Hello, we saw sometime crashes happened in our application with CUDA-PointPillars integrated, after investigated and found the causes are in preprocess_kernels.cu.

1. in generateVoxels_random_kernel():

   int voxel_idx = floorf((point.x - min_x_range)/pillar_x_size); int voxel_idy = floorf((point.y - min_y_range)/pillar_y_size); our grid_y_size is 320, when (point.y - min_y_range)/pillar_y_size == 319.999998, voxel_idy = floorf(319.999998), the value of voxel_idy is 320 not 319 ! voxel_idy == grid_y_size, this caused invalid out-of-bounding access to mask and voxels, and the memory was then corrupted, so, a crash happened accordingly.

2. in generateBaseFeatures_kernel(): current_pillarId = atomicAdd(pillar_num, 1); Hereafter no checking is done for current_pillarId, if there are points scattering in a very large range and current_pillarId is greater than MAX_VOXELS(40000), memory will be corrupted by "((float4*)voxel_features)[outIndex] = ((float4*)voxels)[inIndex];" because of invalid out-of-bounding access to voxel_features.

Did a sample fix here: https://github.com/arnoldfychen/CUDA-PointPillars/commit/2c9c4a15b432e7abee2de13b0b91a4a3a52fb1ce then no crash was seen.

Hello,

Thanks about your excellent job,

I want to know about the time for all processing modules

So, how can i know about time of scatter procedure

Thank u for reading

When I rosplay the .bag file and change the format into kitti's format as the input， the detected results is very terrible. Does anyone have the same problem?

Hello, author! I wanted to use onnxruntime to compare the onnx to the pytorch model, but the call got the following error.

sess = onnxruntime.InferenceSession("pointpillar.onnx", None) File "E:\Anaconda3\envs\innovativePractice\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 347, in init self._create_inference_session(providers, provider_options, disabled_optimizers) File "E:\Anaconda3\envs\innovativePractice\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 384, in _create_inference_session sess = C.InferenceSession(session_options, self._model_path, True, self._read_config_from_model) onnxruntime.capi.onnxruntime_pybind11_state.InvalidGraph: [ONNXRuntimeError] : 10 : INVALID_GRAPH : Load model from pointpillar.onnx failed:This is an invalid model. In Node, ("ReduceMax_166", ReduceMax, "", -1) : ("onnx::ReduceMax_332": tensor(float),) -> ("onnx::Squeeze_333": tensor(float),) , Error Mismatched attribute type in 'ReduceMax_166 : keepdims'

What is the reason for this? I am a beginner, if it is convenient, can you give me some suggestions for evaluating pointpillar.onnx with onnxruntime.

@NVIDIA-AI-IOT thank you for your works，this is very helpful for me. but there are some questions in mmdet3d conversion：i can't directly convert the model of mmdet3d, and i have no specific idea of revision ，because there are differences in the definition and use of pointpillars in mmdet3d and pcdet。 --------------mmdet3d-pointpillars-------------------- 0 backbone.blocks.0.0.weight 1 backbone.blocks.0.1.weight 2 backbone.blocks.0.1.bias 3 backbone.blocks.0.3.weight 4 backbone.blocks.0.4.weight 5 backbone.blocks.0.4.bias 6 backbone.blocks.0.6.weight 7 backbone.blocks.0.7.weight 8 backbone.blocks.0.7.bias 9 backbone.blocks.0.9.weight 10 backbone.blocks.0.10.weight 11 backbone.blocks.0.10.bias 12 backbone.blocks.1.0.weight 13 backbone.blocks.1.1.weight 14 backbone.blocks.1.1.bias 15 backbone.blocks.1.3.weight 16 backbone.blocks.1.4.weight 17 backbone.blocks.1.4.bias 18 backbone.blocks.1.6.weight 19 backbone.blocks.1.7.weight 20 backbone.blocks.1.7.bias 21 backbone.blocks.1.9.weight 22 backbone.blocks.1.10.weight 23 backbone.blocks.1.10.bias 24 backbone.blocks.1.12.weight 25 backbone.blocks.1.13.weight 26 backbone.blocks.1.13.bias 27 backbone.blocks.1.15.weight 28 backbone.blocks.1.16.weight 29 backbone.blocks.1.16.bias 30 backbone.blocks.2.0.weight 31 backbone.blocks.2.1.weight 32 backbone.blocks.2.1.bias 33 backbone.blocks.2.3.weight 34 backbone.blocks.2.4.weight 35 backbone.blocks.2.4.bias 36 backbone.blocks.2.6.weight 37 backbone.blocks.2.7.weight 38 backbone.blocks.2.7.bias 39 backbone.blocks.2.9.weight 40 backbone.blocks.2.10.weight 41 backbone.blocks.2.10.bias 42 backbone.blocks.2.12.weight 43 backbone.blocks.2.13.weight 44 backbone.blocks.2.13.bias 45 backbone.blocks.2.15.weight 46 backbone.blocks.2.16.weight 47 backbone.blocks.2.16.bias 48 neck.deblocks.0.0.weight 49 neck.deblocks.0.1.weight 50 neck.deblocks.0.1.bias 51 neck.deblocks.1.0.weight 52 neck.deblocks.1.1.weight 53 neck.deblocks.1.1.bias 54 neck.deblocks.2.0.weight 55 neck.deblocks.2.1.weight 56 neck.deblocks.2.1.bias 57 bbox_head.conv_cls.weight 58 bbox_head.conv_cls.bias 59 bbox_head.conv_reg.weight 60 bbox_head.conv_reg.bias 61 bbox_head.conv_dir_cls.weight 62 bbox_head.conv_dir_cls.bias 63 voxel_encoder.pfn_layers.0.norm.weight 64 voxel_encoder.pfn_layers.0.norm.bias 65 voxel_encoder.pfn_layers.0.linear.weight

--------------pcdet-pointpillars----------------------------------- 0 vfe.pfn_layers.0.linear.weight 1 vfe.pfn_layers.0.norm.weight 2 vfe.pfn_layers.0.norm.bias 3 backbone_2d.blocks.0.1.weight 4 backbone_2d.blocks.0.2.weight 5 backbone_2d.blocks.0.2.bias 6 backbone_2d.blocks.0.4.weight 7 backbone_2d.blocks.0.5.weight 8 backbone_2d.blocks.0.5.bias 9 backbone_2d.blocks.0.7.weight 10 backbone_2d.blocks.0.8.weight 11 backbone_2d.blocks.0.8.bias 12 backbone_2d.blocks.0.10.weight 13 backbone_2d.blocks.0.11.weight 14 backbone_2d.blocks.0.11.bias 15 backbone_2d.blocks.1.1.weight 16 backbone_2d.blocks.1.2.weight 17 backbone_2d.blocks.1.2.bias 18 backbone_2d.blocks.1.4.weight 19 backbone_2d.blocks.1.5.weight 20 backbone_2d.blocks.1.5.bias 21 backbone_2d.blocks.1.7.weight 22 backbone_2d.blocks.1.8.weight 23 backbone_2d.blocks.1.8.bias 24 backbone_2d.blocks.1.10.weight 25 backbone_2d.blocks.1.11.weight 26 backbone_2d.blocks.1.11.bias 27 backbone_2d.blocks.1.13.weight 28 backbone_2d.blocks.1.14.weight 29 backbone_2d.blocks.1.14.bias 30 backbone_2d.blocks.1.16.weight 31 backbone_2d.blocks.1.17.weight 32 backbone_2d.blocks.1.17.bias 33 backbone_2d.blocks.2.1.weight 34 backbone_2d.blocks.2.2.weight 35 backbone_2d.blocks.2.2.bias 36 backbone_2d.blocks.2.4.weight 37 backbone_2d.blocks.2.5.weight 38 backbone_2d.blocks.2.5.bias 39 backbone_2d.blocks.2.7.weight 40 backbone_2d.blocks.2.8.weight 41 backbone_2d.blocks.2.8.bias 42 backbone_2d.blocks.2.10.weight 43 backbone_2d.blocks.2.11.weight 44 backbone_2d.blocks.2.11.bias 45 backbone_2d.blocks.2.13.weight 46 backbone_2d.blocks.2.14.weight 47 backbone_2d.blocks.2.14.bias 48 backbone_2d.blocks.2.16.weight 49 backbone_2d.blocks.2.17.weight 50 backbone_2d.blocks.2.17.bias 51 backbone_2d.deblocks.0.0.weight 52 backbone_2d.deblocks.0.1.weight 53 backbone_2d.deblocks.0.1.bias 54 backbone_2d.deblocks.1.0.weight 55 backbone_2d.deblocks.1.1.weight 56 backbone_2d.deblocks.1.1.bias 57 backbone_2d.deblocks.2.0.weight 58 backbone_2d.deblocks.2.1.weight 59 backbone_2d.deblocks.2.1.bias 60 dense_head.conv_cls.weight 61 dense_head.conv_cls.bias 62 dense_head.conv_box.weight 63 dense_head.conv_box.bias 64 dense_head.conv_dir_cls.weight 65 dense_head.conv_dir_cls.bias