zgplvyou

有新版本的后续吗？

12

我觉得这种loss非常有用的，尤其对于那些类别数差距很大的训练样本。新版本出来了不能编译了，不知道作者是否有后续的新版本兼容的带权loss呢（ps：看你id中文名，就以母语提问了）

about the cuhk03 evaluation

15

thanks for your evaluation code , but i am a little confused about one line of it. could you tell me what 'ff = ff.ff1' and 'ff =ff.ff2' mean. i...

How to transform custom ops to onnx

5

I try to transform the custom ops to onnx as the nms set. I define the static symbolic method. when the output is single, I got the custom onnx node....

the function show_mask in onnx_model_example.ipynb receives the mask as input, while there are usually multiple masks created by the predictor, so in the example point input, the masks is dimensional...

Preprocess for classification model

1

Hi, I try to infer the classification models on onnxruntime engin. however, I can`t get the consistent accuracy in the page except resnet mobilenet and shufflenet. I think the preprocess...