Question

尝试使用ONNX转换this pytorch模型会给我这个错误。我搜索了github，此错误在1.1.0版之前出现过，但显然已得到纠正。现在，我正在使用割炬1.4.0。（python 3.6.9），我看到此错误。

File "/usr/local/lib/python3.6/dist-packages/torch/onnx/init.py", line 148, in export
strip_doc_string, dynamic_axes, keep_initializers_as_inputs)
File "/usr/local/lib/python3.6/dist-packages/torch/onnx/utils.py", line 66, in export
dynamic_axes=dynamic_axes, keep_initializers_as_inputs=keep_initializers_as_inputs)
File "/usr/local/lib/python3.6/dist-packages/torch/onnx/utils.py", line 416, in _export
fixed_batch_size=fixed_batch_size)
File "/usr/local/lib/python3.6/dist-packages/torch/onnx/utils.py", line 296, in _model_to_graph
fixed_batch_size=fixed_batch_size, params_dict=params_dict)
File "/usr/local/lib/python3.6/dist-packages/torch/onnx/utils.py", line 135, in _optimize_graph
graph = torch._C._jit_pass_onnx(graph, operator_export_type)
File "/usr/local/lib/python3.6/dist-packages/torch/onnx/init.py", line 179, in _run_symbolic_function
return utils._run_symbolic_function(*args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/torch/onnx/utils.py", line 657, in _run_symbolic_function
return op_fn(g, *inputs, **attrs)
File "/usr/local/lib/python3.6/dist-packages/torch/onnx/symbolic_helper.py", line 128, in wrapper
args = [_parse_arg(arg, arg_desc) for arg, arg_desc in zip(args, arg_descriptors)]
File "/usr/local/lib/python3.6/dist-packages/torch/onnx/symbolic_helper.py", line 128, in
args = [_parse_arg(arg, arg_desc) for arg, arg_desc in zip(args, arg_descriptors)]
File "/usr/local/lib/python3.6/dist-packages/torch/onnx/symbolic_helper.py", line 81, in _parse_arg
"', since it's not constant, please try to make "
RuntimeError: Failed to export an ONNX attribute 'onnx::Gather', since it's not constant, please try to make things (e.g., kernel size) static if possible

如何解决？我还尝试了最新的每晚构建，出现同样的错误。

我的代码：

from model import BiSeNet
import torch.onnx
import torch

net = BiSeNet(19)
net.cuda()
net.load_state_dict(torch.load('/content/drive/My Drive/Collab/fp/res/cp/79999_iter.pth'))
net.eval()

dummy = torch.rand(1,3,512,512).cuda()
torch.onnx.export(net, dummy, "Model.onnx", input_names=["image"], output_names=["output"])

在引发运行时错误之前，我将print (v.node ())添加到了symbolic_helper.py上，以查看导致该错误的原因。

这是输出：%595 : Long() = onnx::Gather[axis=0](%592, %594) # /content/drive/My Drive/Collab/fp/model.py:111:0

model.py中111中的那一行是：avg = F.avg_pool2d(feat32, feat32.size()[2:])

此source建议pytorch中的tensor.size方法无法被onnx识别，需要将其修改为常量。

Answer 1

您可以：

print(feat32.size()[2:])

并替换：

F.avg_pool2d(feat32, feat32.size()[2:])

具有：

F.avg_pool2d(feat32, your_print_contant_result)

Answer 2

我一直在努力解决同样的问题。

在我的情况下，不支持

F.adaptive_avg_pool2d。您必须尝试其他操作。

我希望这会有所帮助。

谢谢

Answer 3

更改

的实例

x = F.avg_pool2d(x, x.shape[2:])

到

x_shape = [int(s) for s in x.shape[2:]]
x = F.avg_pool2d(x, x_shape)

使得avg_pool2d的输入形状为常数[k,k]，而不是here所述的torch.Size([k, k])。

Answer 4

我曾经在使用导出时遇到过类似的错误

torch.onnx.export(model, x, ONNX_FILE_PATH)

我通过像这样指定 opset_version 来修复它：

torch.onnx.export(model, x, ONNX_FILE_PATH, opset_version = 11)

无法将Pytorch转换为ONNX

4 个答案: