Rawal Khirodkar
Rawal Khirodkar
If you want to try, I have a [docker](https://hub.docker.com/r/rawalkhirodkar/aria_data_tools) container which works for Mac.
Please turn off distributed training in train.py and do not use syncBN.
Thank you for the reply. No modifications, right offshelf. I was also able to reproduce the reported results with the weights shared, so the test data setup is correct.
Yes, as I was reproducing results, made sure everything else is identical including the data setup. Here is the param stage train log (lixel stage log is too big to...
Thank you for the suggestion. Here is the performance all snapshots end of epoch 13 to 5 in the lixel stage. ``` snapshot 12 MPJPE from lixel mesh: 96.23 mm,...
The results are for the default setting and not the bigger batch versions. I am using the old ```get_optimizer``` bypassing the ```trainable_modules```. This should not make a difference right? ```...
Thank you for the suggestion. I did a fresh clone. The current code on this repo throws this error (one of the reasons I switched to the older versions) ```...
Do we have vgaPose3d_stage1_coco19.tar anywhere?
We do have it, update getData.sh as follows. ` if [ ! -f vgaPose3d_stage1_coco19.tar ]; then $WGET $mO vgaPose3d_stage1_coco19.tar http://domedb.perception.cs.cmu.edu/webdata/dataset/$datasetName/vgaPose3d_stage1_coco19.tar || rm -v vgaPose3d_stage1_coco19.tar fi `
Same issue.