HRNet-Facial-Landmark-Detection
HRNet-Facial-Landmark-Detection copied to clipboard
code using probloms
hi, I've tried to use your code for some demo tests on my own images, but it seems it can't be used for single forward inference. So what should I do to make it into my practical using? thanks a lot!
You can do single image inference. Have a look at the dataloaders. Also, the inference function also computes the nme, but you can fill the ground truth with dummy values if you don't have them
Hey, I rewrote a script to do inference on single image. However, I observed that the predicted points are not correct after transformation. Any suggestions relating to it?
I am still confused by how to use the code? I wonder if you are willing to make a demo.py like what should I input and how to print the predictions on an image or show them on video like many codes do? thanks again!
I also have the same confuse as @vincentwei0919 , and also look forward to have a demo.py to show how to inference on images or video. thanks~
@vincentwei0919 Can you share any inference to check the results on webcam?