li-haoran
li-haoran
Thanks for your sharing result. Mine seems going to bad result. i also realize this human scale issue, so i use the beam_width is the ratio of the width and...
I trained 100 epochs, actually almost 50~60 epochs convergence. The loss  is quiet small. the heatmap is perfect, but the paf is not good. i think my ratio 0.2...
after i fix some bugs, the heatmap converge seems good. i post some samples and loss fig, both show the results is good.