RuntimeError: Only tuples, lists and Variables are supported as JIT inputs/outputs. Dictionaries and strings are also accepted, but their usage is not recommended. Here, received an input of unsupported type: int
darrenearl opened this issue · comments
(pcdet) exinova@exinova-B560M-AORUS-PRO-AX:/media/exinova/ssd/CUDA-PointPillars/tool$ python exporter.py --ckpt pointpillar_7728.pth --cfg_file cfgs/custom_models/pointpillar.yaml
2022-10-28 14:55:09,684 INFO ------ Convert OpenPCDet model for TensorRT ------
2022-10-28 14:55:11,488 INFO ==> Loading parameters from checkpoint pointpillar_7728.pth to CPU
2022-10-28 14:55:11,499 INFO Not updated weight vfe.pfn_layers.0.linear.weight: torch.Size([64, 9])
2022-10-28 14:55:11,499 INFO ==> Done (loaded 126/127)
/home/exinova/anaconda3/envs/pcdet/lib/python3.7/site-packages/torch/onnx/utils.py:355: UserWarning: Skipping _decide_input_format
-1
warnings.warn("Skipping _decide_input_format\n {}".format(e.args[0]))
Traceback (most recent call last):
File "exporter.py", line 155, in
main()
File "exporter.py", line 139, in main
output_names = ['cls_preds', 'box_preds', 'dir_cls_preds'], # the model's output names
File "/home/exinova/anaconda3/envs/pcdet/lib/python3.7/site-packages/torch/onnx/init.py", line 276, in export
custom_opsets, enable_onnx_checker, use_external_data_format)
File "/home/exinova/anaconda3/envs/pcdet/lib/python3.7/site-packages/torch/onnx/utils.py", line 94, in export
use_external_data_format=use_external_data_format)
File "/home/exinova/anaconda3/envs/pcdet/lib/python3.7/site-packages/torch/onnx/utils.py", line 701, in _export
dynamic_axes=dynamic_axes)
File "/home/exinova/anaconda3/envs/pcdet/lib/python3.7/site-packages/torch/onnx/utils.py", line 459, in _model_to_graph
use_new_jit_passes)
File "/home/exinova/anaconda3/envs/pcdet/lib/python3.7/site-packages/torch/onnx/utils.py", line 420, in _create_jit_graph
graph, torch_out = _trace_and_get_graph_from_model(model, args)
File "/home/exinova/anaconda3/envs/pcdet/lib/python3.7/site-packages/torch/onnx/utils.py", line 380, 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/exinova/anaconda3/envs/pcdet/lib/python3.7/site-packages/torch/jit/_trace.py", line 1139, in _get_trace_graph
outs = ONNXTracedModule(f, strict, _force_outplace, return_inputs, _return_inputs_states)(*args, **kwargs)
File "/home/exinova/anaconda3/envs/pcdet/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/exinova/anaconda3/envs/pcdet/lib/python3.7/site-packages/torch/jit/_trace.py", line 93, in forward
in_vars, in_desc = _flatten(args)
RuntimeError: Only tuples, lists and Variables are supported as JIT inputs/outputs. Dictionaries and strings are also accepted, but their usage is not recommended. Here, received an input of unsupported type: int
Have you solved it, please?
截止目前最新代码commit tag: (ce7e2bd694c90207435c8751d61cdb38d48a9f4c), 文件：tool/export_onnx.py 中126行，dummy_input['batch_size'] = 1 需要修改为dummy_input['batch_size'] = torch.tensor(1)#1，这句话导致JIT报错int问题，官方有时间麻烦可以修改下。