Yoonho Shin

Did you mean embedding_size in config.py to change the type? It is 2048 and I checked the large model uses 2048 embedding channels on paper. The other setting in config.py...

It actually made an error like this : File "/home/unolab/Yoonho/Pose/MobileHumanPose/main/model.py", line 67, in forward loss_coord = torch.abs(coord - target_coord) * target_vis RuntimeError: The size of tensor a (8) must match...

@SangbumChoi Thank you :)

I checked it works for training and it will take about 50 hours with RTX 2080. Thank you for your support!

Protocol 1 error (PA MPJPE) >> tot: 40.13 Directions: 34.42 Discussion: 35.80 Eating: 44.37 Greeting: 41.69 Phoning: 38.69 Posing: 37.26 Purchases: 34.61 Sitting: 42.46 SittingDown: 54.30 Smoking: 42.58 Photo: 48.37...

@SangbumChoi I will try and let you know. Thank you.

@SangbumChoi Is there only difference in line 130 of lpnet_ski_concat.py?

09-02 09:52:46 Protocol 1 error (PA MPJPE) >> tot: 40.21 Directions: 36.56 Discussion: 37.00 Eating: 42.51 Greeting: 41.39 Phoning: 38.17 Posing: 36.55 Purchases: 36.60 Sitting: 42.26 SittingDown: 55.09 Smoking: 41.85...

@SangbumChoi Hi, 1. Yes, I used this version : https://github.com/SangbumChoi/MobileHumanPose/commit/70baeafff0d57ab74a72abedb30c12e739da18ec So I asked you whether the difference is only line 130 of lpnet_ski_concat.py between large branch and 70baeaf. 2. Batch...

@SangbumChoi Thanks for your support :)