The PCK under reprojection for horse

[linpeisensh]

Thank you for your excellent work!

I have run your acsm code and found the PCK under reprojection for horse is much smaller than you show in your paper. The PCK transfer is fine.

as you can see in the following picture, the predict key points are not so close to the ground truth.


I have run this to test:
python -m acsm.benchmark.pascal.kp_project --name=acsm_horse_8parts --category=horse --parts_file=acsm/part_files/horse.txt --use_html --dl_out_pascal=True --dl_out_imnet=False --split=val --num_train_epoch=400 --num_hypo_cams=8 --env_name=acsm_horse_8parts_pck_val --multiple_cam=True --visuals_freq=5 --visualize=True --n_data_workers=4 --scale_bias=0.75 --resnet_style_decoder=True --resnet_blocks=4
Have I done something wrong?

[nileshkulkarni]

Hi @linpeisensh,

I think the command is missing two parameters --el_euler_range=20 --cyc_euler_range=20 that is the reason I think the numbers are so low. Hope that fixes it. I will edit the command on the readme. Thanks for pointing out. Please refer to this commit

Best,
Nilesh

[linpeisensh]

Thank you!

It works.