update default parameters (#1611)

references/detection/train.py

@@ -8,6 +8,14 @@
 The default hyperparameters are tuned for training on 8 gpus and 2 images per gpu.
     --lr 0.02 --batch-size 2 --world-size 8
 If you use different number of gpus, the learning rate should be changed to 0.02/8*$NGPU.
+
+On top of that, for training Faster/Mask R-CNN, the default hyperparameters are
+    --epochs 26 --lr-steps 16 22 --aspect-ratio-group-factor 3
+
+Also, if you train Keypoint R-CNN, the default hyperparameters are
+    --epochs 46 --lr-steps 36 43 --aspect-ratio-group-factor 3
+Because the number of images is smaller in the person keypoint subset of COCO,
+the number of epochs should be adapted so that we have the same number of iterations.
 """
 import datetime
 import os
@@ -145,7 +153,7 @@ def main(args):
     parser.add_argument('--device', default='cuda', help='device')
     parser.add_argument('-b', '--batch-size', default=2, type=int,
                         help='images per gpu, the total batch size is $NGPU x batch_size')
-    parser.add_argument('--epochs', default=13, type=int, metavar='N',
+    parser.add_argument('--epochs', default=26, type=int, metavar='N',
                         help='number of total epochs to run')
     parser.add_argument('-j', '--workers', default=4, type=int, metavar='N',
                         help='number of data loading workers (default: 4)')
@@ -158,12 +166,12 @@ def main(args):
                         metavar='W', help='weight decay (default: 1e-4)',
                         dest='weight_decay')
     parser.add_argument('--lr-step-size', default=8, type=int, help='decrease lr every step-size epochs')
-    parser.add_argument('--lr-steps', default=[8, 11], nargs='+', type=int, help='decrease lr every step-size epochs')
+    parser.add_argument('--lr-steps', default=[16, 22], nargs='+', type=int, help='decrease lr every step-size epochs')
     parser.add_argument('--lr-gamma', default=0.1, type=float, help='decrease lr by a factor of lr-gamma')
     parser.add_argument('--print-freq', default=20, type=int, help='print frequency')
     parser.add_argument('--output-dir', default='.', help='path where to save')
     parser.add_argument('--resume', default='', help='resume from checkpoint')
-    parser.add_argument('--aspect-ratio-group-factor', default=0, type=int)
+    parser.add_argument('--aspect-ratio-group-factor', default=3, type=int)
     parser.add_argument(
         "--test-only",
         dest="test_only",