Pytorch模型如何转onnx模型 Pytorch模型转onnx模型代码实例

本篇文章小编给大家分享一下Pytorch模型转onnx模型代码实例，小编觉得挺不错的，现在分享给大家供大家参考，有需要的小伙伴们可以来看看。

代码如下所示：

import io
import torch
import torch.onnx
from models.C3AEModel import PlainC3AENetCBAM

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

def test():
  model = PlainC3AENetCBAM()
 
  pthfile = r'/home/joy/Projects/models/emotion/PlainC3AENet.pth'
  loaded_model = torch.load(pthfile, map_location='cpu')
  # try:
  #   loaded_model.eval()
  # except AttributeError as error:
  #   print(error)

  model.load_state_dict(loaded_model['state_dict'])
  # model = model.to(device)

  #data type nchw
  dummy_input1 = torch.randn(1, 3, 64, 64)
  # dummy_input2 = torch.randn(1, 3, 64, 64)
  # dummy_input3 = torch.randn(1, 3, 64, 64)
  input_names = [ "actual_input_1"]
  output_names = [ "output1" ]
  # torch.onnx.export(model, (dummy_input1, dummy_input2, dummy_input3), "C3AE.onnx", verbose=True, input_names=input_names, output_names=output_names)
  torch.onnx.export(model, dummy_input1, "C3AE_emotion.onnx", verbose=True, input_names=input_names, output_names=output_names)

if __name__ == "__main__":
 test()

直接将PlainC3AENetCBAM替换成需要转换的模型，然后修改pthfile，输入和onnx模型名字然后执行即可。

注意：上面代码中注释的dummy_input2，dummy_input3，torch.onnx.export对应的是多个输入的例子。

在转换过程中遇到的问题汇总

RuntimeError: Failed to export an ONNX attribute, since it's not constant, please try to make things (e.g., kernel size) static if possible

在转换过程中遇到RuntimeError: Failed to export an ONNX attribute, since it's not constant, please try to make things (e.g., kernel size) static if possible的错误。

根据报的错误日志信息打开/home/joy/.tensorflow/venv/lib/python3.6/site-packages/torch/onnx/symbolic_helper.py，在相应位置添加print之后，可以定位到具体哪个op出问题。

例如：

在相应位置添加

print（v.node()）

输出信息如下：

%124 : Long() = onnx::Gather[axis=0](%122, %121), scope: PlainC3AENetCBAM/Bottleneck[cbam]/CBAM[cbam]/ChannelGate[ChannelGate] # /home/joy/Projects/models/emotion/WhatsTheemotion/models/cbam.py:46:0

原因是pytorch中的tensor.size(1)方式onnx识别不了，需要修改成常量。