This software uses UMDFaces and Pytorch to train deep networks for face recognition.
The steps are:
- Generate thumbnails to train. Use
compute_aligned_images.py
for this task, point to the three batches of UMDFaces, run it three times. - Copy the create.py script to the val directory and run it there. This will create the missing directories in val that are required for validation to work.
- Train. I used
python main.py --pretrained --epochs 200 --lr 0.1 --print-freq 1 /scratch2/umdfaces-thumbnails/
. You should come back 12 hours later. - Generate features, for example. I used the
compute_features.py
script for this task. - Generate plots/statistics, whatever you want, I used
run_lfw.py
for this.