Closed jjzhang10 closed 7 years ago
Looks like you initialized it randomly. On my experience Radom initialization achieves PCP score ~0.42
@asanakoy I forget to add the parameter "fix_conv_lr 10000". Training the conv and fc weights together at the very beginning may hurt the performance for the fine-tuning on imagenet. Now here is the result:
The train/pose_loss is already lower to 0.03 (you mentioned in the previous post) after 140k iterations, but the test/mPCP is around 0.47. Will wait and see whether it will achieve 0.55 By the way, will the program converge every time?
You need to train longer. Should converge
I train the LSP dataset with imagenet initialization. It has been 260k iterations, the train/pose_error is around[0.02 0.03]. The mPCP score (0.42) is still far from the result listed in the table. It does increase, but pretty slowly.
Does it mean it cannot converge for this time? I need restart the training? Thanks.