KAF Training

For the figure, the each step corresponds to a processed batch(16).

Resdcn + FPNx2 (↓:32,16,8,4)

Use PSR dataset before remove bg samples (12415 training samples)

python train.py --log_name resdcn_all \
                --data_dir ~/cyl/Data/PSR_final \
                --arch resdcn_101 \
                --lr 5e-5 \
                --lr_step 40,70 \
                --batch_size 16 \
                --num_epochs 90 --num_workers 0 --log_interval 5

### Use PSR dataset after remove bg samples (11729 samples)

HRNet (↓:4,4,4,4)

Use PSR dataset after remove bg samples (11729 samples)

Hourglass (↓:4,4,4,4)

Use PSR dataset after remove bg samples (11729 samples)