HigherHRNet-Human-Pose-Estimation
HigherHRNet-Human-Pose-Estimation copied to clipboard
HRNet
Use own images
Hi, I am interested in testing your network on my own images. However I don't know how to use your code with my own images. Could you tell me what should I change in the code or do to get the 2d locations? Thanks
I tried. I updated tools/valid.py to inference my images.
save_valid_image(image, final_results, result_image_path)
But the results looks bad. See results in Issue17
@plmsmile thanks for your advice! I tried changing "person_keypoints_val2017.json" so that "file_name" becomes my filename. Then I've run "valid.py", I successfully got results. However, I couldn't find another way. Is there any way to run without annotation-file?
@plmsmile thanks for your advice! I tried changing "person_keypoints_val2017.json" so that "file_name" becomes my filename. Then I've run "valid.py", I successfully got results. However, I couldn't find another way. Is there any way to run without annotation-file?
Without annotation-file，we can get results，but results referred to image_id are repeatable，why?
我知道了。我更新了 toolsvalid.py 来预测/我的图像。
save_valid_image(image, final_results, result_image_path)但结果显示很不错。在第 17 期中查看结果。
Hello, can you explain it in detail? I just started to use this model, but I still don't know it very well. Thank you
@plmsmile谢谢你的建议！ 我尝试更改“person_keypoints_val2017.json”，以便“file_name”成为我的文件名。 然后我运行“valid.py”，我成功得到了结果。 但是，我找不到其他方法。 没有注释文件有什么方法可以运行吗？
没有annotation-file，我们可以得到结果，但是引用image_id的结果是重复的，为什么？
Hello, can you explain it in detail? I just started to use this model, but I still don't know it very well. Thank you
Hello, could you please explain how to use the model on your own images?
