老白

Results 4 comments of 老白

I encountered similar case. I have two onnx models. ![image](https://user-images.githubusercontent.com/26358799/191700158-6c10c08d-06e9-4f9d-8ee7-153baf3902c4.png) err info is: ![image](https://user-images.githubusercontent.com/26358799/191700431-8804d25a-10da-4278-85da-e07b12e17ad0.png) `[StatusCode.INTERNAL] onnx runtime error 6: Non-zero status code returned while running FusedConv node. Name:'Conv_60_Relu_61' Status Message:...

Hi @rmccorm4 , When I haven't requested for a day, the GPU memory usage of the triton server still hasn't decreased.(About 3G) Therefore, I believe that at least one stage...

谢谢,已经在看了。

感谢您的回复。我自己试了试,用svm_hist.xml这个模型,我测试的结果是,蓝色车牌和非车牌判断的正确率很高,但是对于黄色的车牌,正确率却非常低。请问,是这个模型本身就是针对蓝色车牌和非车牌的吗?或者说是我的测试有问题。