yyyouy
yyyouy
Thank you for your good work! I also wonder, can you release the inference scripts to be able to reproduce your results? I just tried to reproduce your result on...
the author released the ADM version. Ant the number in table 2.07 is ADM(dropout). The Paper released the fid of ADM is 2.61. so your code is correct.
> Hi, we used detectron2 library to estimate densepose, and the checkpoint we released was not trained on TED-Talk dataset. May I ask if the results mentioned in your paper...
> Yes, it was trained on TED-Talk. The detectron2 has different visualizers, we use the semantic map one, and its background is purple. Thank you very much. Do you have...
> Yes, it was trained on TED-Talk. The detectron2 has different visualizers, we use the semantic map one, and its background is purple. We have been utilizing the DensePose with...
> have you successfully reproduced the base/large model results? I haven't tried it yet, and I'm wondering if it's possible for the huge model to have a sudden deterioration of...
I found out that this problem occurs if you use full precision, but not if you change to mixed precision
> have you successfully reproduced the base/large model results? I haven't tried it yet, and I'm wondering if it's possible for the huge model to have a sudden deterioration of...
你好，我们目前没有微调工具。
Thanks for your work~ We will try it.