search

stevenlsw / Semi-Hand-Object

125 stars 13 forks source link

Semi-Supervised Learning and Pseudo Labels #2

Open neilsong opened 3 years ago

neilsong commented 3 years ago

Hi! I was wondering if the pseudo labeled dataset (including the selected frames and labels from the something-something dataset) are available for training. I assume that the model trained by running traineval.py and following the steps in the readme gives the baseline supervised model? If so, is the combined dataset with pseudo labels available for download? Also does the current loss.py implement the binary mask for object pose loss?

Thanks!

zeakey commented 3 years ago

I have the same question.

I got the following results after training with traineval.py:

REP-5
{'021_bleach_cleanser': 0.026674570243034972, '006_mustard_bottle': 0.046067415730337076, '010_potted_meat_can': 0.014577259475218658}
ADD-10
{'021_bleach_cleanser': 0.6357439241256668, '006_mustard_bottle': 0.5741573033707865, '010_potted_meat_can': 0.23615160349854228}

I use 3 GPUs and the default settings. How about you @neilsong ?