Junfa Liu

Hi~ I found **cv2.ellipse2Poly** in **top_dow.py/bottom_up.py** highly slow the inference speed. If I replace it with **cv2.line**, **hrnet_w32_wholebody_256×192_dark** will speed up from **3.0fps** to **16.0fps** on a **1060**. There are...

@jinfagang I did not test the time it takes for post-processing. I just replace cv2.ellipse2Poly with cv2.line to speed up inference.

@jinfagang It can reach 16fps on a GTX1060 when I combine hrnet_w32_wholebody_256×192_dark and yolov3 (from mmdetection) to estimate whole-body keypoints.

Hi @wondervictor I met the same problem. The training phase shows that the model achieves a high AP. But in the inference stage, it gets a bad performance. I trained...

> Hi @fabro66, could you provide a model config with weights for me? This problem is strange. OK! [model & configs & weights](https://drive.google.com/file/d/1t9nJVRZfFwK_uKeGsz4O2F35DDzftOJH/view?usp=sharing) Please check it!

> It seems that the results are normal through two ways of evaluation. Can you provide more details about the inconsistency between training and testing? BTW, I'm concerned about the...

Hi @wondervictor When I fixed the input format bug, it still gets bad performance. Do you know where the problem is? I'm guessing that the model is overfitting because it...

Hi @wondervictor. I have compared the results before/after changing the image format. It will get better performance than before changing the image format. However, it still gets bad performance in...

Hi @wondervictor . As long as I keep training sparseinst-yolonet, the AP keeps improving. For the validation dataset, some images are segmented well, even some people of small size. In...

Hi @wondervictor. I used the pretrained model with ResNet-50 for visualization on val2017 and got good performance, which confirms that my environment is ok. I don't sure whether my batch...