Closed Odaimoko closed 5 years ago
Hi, I added detailed explanation in README like below.
After training model on the COCO dataset, I set lr
, lr_dec_epoch
, end_epoch
in config.py
to 5e-5
, [150, 155]
, 160
, respectively. Then, run python train.py --gpu $GPUS --continue
.
Thank you very much. Did you also train on posetrack 17?
Unfortunately, no. You can try by changing my code.
I am sorry that I ask this question because I barely know tf. Could you pls describe what you have done and what parameters you use during training? Did you follow the training technique used on posetrack 17 in the original paper?