导出onnx失败

[t973288913]

C:\Users\97328.conda\envs\torch\python.exe "E:\A_Deep learning model\pspnet-txx-yck\predict.py" E:\A_Deep learning model\pspnet-txx-yck\logs\lr0.0001\best_epoch_weights.pth model, and classes loaded. Configurations:

| keys | values|

| model_path | E:\A_Deep learning model\pspnet-txx-yck\logs\lr0.0001\best_epoch_weights.pth| | num_classes | 2| | backbone | mobilenet| | input_shape | [512, 512]| | downsample_factor | 16| | mix_type | 0| | cuda | True|

E:\A_Deep learning model\pspnet-txx-yck\logs\lr0.0001\best_epoch_weights.pth model, and classes loaded. Starting export with onnx 1.14.1. ============= Diagnostic Run torch.onnx.export version 2.0.0+cu118 ============= verbose: False, log level: Level.ERROR ======================= 0 NONE 0 NOTE 0 WARNING 0 ERROR ========================

Traceback (most recent call last): File "E:\A_Deep learning model\pspnet-txx-yck\predict.py", line 163, in pspnet.convert_to_onnx(simplify, onnx_save_path) File "E:\A_Deep learning model\pspnet-txx-yck\pspnet.py", line 277, in convert_to_onnx torch.onnx.export(self.net, File "C:\Users\97328.conda\envs\torch\lib\site-packages\torch\onnx\utils.py", line 506, in export _export( File "C:\Users\97328.conda\envs\torch\lib\site-packages\torch\onnx\utils.py", line 1548, in _export graph, params_dict, torch_out = _model_to_graph( File "C:\Users\97328.conda\envs\torch\lib\site-packages\torch\onnx\utils.py", line 1117, in _model_to_graph graph = _optimize_graph( File "C:\Users\97328.conda\envs\torch\lib\site-packages\torch\onnx\utils.py", line 665, in _optimize_graph graph = _C._jit_pass_onnx(graph, operator_export_type) File "C:\Users\97328.conda\envs\torch\lib\site-packages\torch\onnx\utils.py", line 1891, in _run_symbolic_function return symbolic_fn(graph_context, *inputs, **attrs) File "C:\Users\97328.conda\envs\torch\lib\site-packages\torch\onnx\symbolic_helper.py", line 392, in wrapper return fn(g, *args, **kwargs) File "C:\Users\97328.conda\envs\torch\lib\site-packages\torch\onnx\symbolic_opset9.py", line 1836, in symbolic_fn return symbolic_helper._unimplemented( File "C:\Users\97328.conda\envs\torch\lib\site-packages\torch\onnx\symbolic_helper.py", line 607, in _unimplemented _onnx_unsupported(f"{op}, {msg}", value) File "C:\Users\97328.conda\envs\torch\lib\site-packages\torch\onnx\symbolic_helper.py", line 618, in _onnx_unsupported raise errors.SymbolicValueError( torch.onnx.errors.SymbolicValueError: Unsupported: ONNX export of operator adaptive_avg_pool2d, output size that are not factor of input size. Please feel free to request support or submit a pull request on PyTorch GitHub: https://github.com/pytorch/pytorch/issues [Caused by the value '622 defined in (%622 : Long(2, strides=[1], device=cpu) = onnx::Constantvalue= 3 3 [ CPULongType{2} ] )' (type 'Tensor') in the TorchScript graph. The containing node has kind 'onnx::Constant'.]

Inputs:
    Empty
Outputs:
    #0: 622 defined in (%622 : Long(2, strides=[1], device=cpu) = onnx::Constant[value= 3  3 [ CPULongType{2} ]]()
)  (type 'Tensor')

进程已结束,退出代码1