-
Notifications
You must be signed in to change notification settings - Fork 157
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
depthwise_conv2d, this model cannot be exported to ONNX. #1276
Labels
Bug
Something isn't working
Comments
麻烦看下这个是BUG吗,目前有没有快速解决的办法? |
应该是nn.Conv2D中dilation!= 1时设置的padding=‘same’卷积核不支持转换 |
这个具体是哪个套件的模型呢? |
是PaddleSeg下的ESPNet(ESPNetV2),麻烦看下,谢谢! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
[Paddle2ONNX] Start to parse PaddlePaddle model...
[Paddle2ONNX] Model file path: export/food_det_both_416x128_eps_v0/model.pdmodel
[Paddle2ONNX] Parameters file path: export/food_det_both_416x128_eps_v0/model.pdiparams
[Paddle2ONNX] Start to parsing Paddle model...
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_1.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_2.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_3.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[Paddle2ONNX] Detected there's control flow 'while' op in your model, this requires the minimal opset version of 13.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_5.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_6.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_7.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[Paddle2ONNX] Detected there's control flow 'while' op in your model, this requires the minimal opset version of 13.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_9.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_10.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_11.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_13.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_14.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_15.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_17.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_18.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_19.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_21.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_22.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_23.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[Paddle2ONNX] Detected there's control flow 'while' op in your model, this requires the minimal opset version of 13.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_26.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_27.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_30.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_31.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_34.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_35.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_38.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_39.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_42.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_43.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_46.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_47.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_50.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_51.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_54.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR][Paddle2ONNX] [depthwise_conv2d: depthwise_conv2d_55.tmp_0] While dilations != 1, cannot support padding = 'SAME'.
[Paddle2ONNX] Due to the operator: depthwise_conv2d, this model cannot be exported to ONNX.
[ERROR] Model exporting failed, you can report this problem to https://github.com/PaddlePaddle/Paddle2ONNX.git.
C++ Traceback (most recent call last):
0 paddle2onnx::Export(char const*, char const*, char**, int*, int, bool, bool, bool, bool, bool, paddle2onnx::CustomOp*, int, char const*, char**, int*, char const*, bool*, bool, char**, int)
Error Message Summary:
FatalError:
Process abort signal
is detected by the operating system.[TimeInfo: *** Aborted at 1717583184 (unix time) try "date -d @1717583184" if you are using GNU date ***]
[SignalInfo: *** SIGABRT (@0x3eb000019ab) received by PID 6571 (TID 0x7f5103486440) from PID 6571 ***]
Aborted (core dumped)
The text was updated successfully, but these errors were encountered: