ABlueLight

这是windows下编译的嘛 我没有在windows下验证过，那个编译sigmoid_focal_loss_cuda可能只在Linxu下可以成功

@jmwample thanks for your suggestion

@Ma-Dan Thank you for your code! I convert the model to onnx ,but the results is different from pytorch outpus,such loc , mask and proto, but conf is same! Do...

@Ma-Dan Hi, i convert to onnx ssuccessfully，but i found results is not corrent . can you share the version of the pytorch and onnxruntime are you using? Thx

i convert to onnx successfully and results is correct, today. Thx @Ma-Dan @sicarioakki @abhigoku10 My package dependencies include pytorch1.0.0 torchvision0.2.1 onnx-tf1.3.0 onnxruntime0.4.0 onnx1.5.0 tensorflow-gpu1.14.0. Just use @Ma-Dan code is ok...

@abhigoku10 TensorFlow and it can run correctly

> @ABlueLight how did you import it to Tensorflow? https://github.com/onnx/onnx-tensorflow

@ridasalam I convert it to pure tensorflow and it const about 400~500ms on i5 cpu。 On GPU，pytorch and tensorflow cost time are almost equal.

@sicarioakki ONNX model should be loaded by onnx.load(),i think..

nihuinihuini