michael312319999
michael312319999
@Gzzgz What is the seg-parse? How did you fix the problem?
What happens if I don't include it in the training? Will the results be worse?
Is it personal image (width/height) on a cloth image (width/height) or something similar ?
Dear authors, 1. What is the inference time the model processes images? 2. Also, how long did you train the model?