The following command line will train mmmc_R_50_FPN_1x on 8 GPUs with Synchronous Stochastic Gradient Descent (SGD):
python -m torch.distributed.launch \
--nproc_per_node=8 \
--master_port=$((RANDOM + 10000)) \
tools/train_net.py \
--config-file configs/fcos/mmmc_R_50_FPN_1x.yaml \
DATALOADER.NUM_WORKERS 2 \
OUTPUT_DIR training_dir/mmmc_R_50_FPN_1x
The inference command line on coco minival split:
python tools/test_net.py \
--config-file configs/mmmc/mmmc_R_50_FPN_1x.yaml \
MODEL.WEIGHT mmmc_R_50_FPN_1x.pth \
TEST.IMS_PER_BATCH 4
backbone |
ms_train |
AP |
AP50 |
AP75 |
APS |
APM |
APL |
File |
R50 |
Y |
43.0 |
60.6 |
46.6 |
25.1 |
46.5 |
54.0 |
|
R50_dcn |
Y |
44.9 |
62.7 |
48.8 |
25.9 |
48.6 |
57.7 |
|
R101 |
Y |
46.3 |
64.3 |
50.3 |
27.9 |
50.2 |
57.9 |
|
R101_dcn |
Y |
48.0 |
66.2 |
52.0 |
28.9 |
51.6 |
61.1 |
|
X_101_64x4d |
Y |
48.5 |
67.1 |
52.6 |
30.7 |
52.2 |
60.2 |
|
X_101_64x4d_dcn |
Y |
49.9 |
68.6 |
54.2 |
31.2 |
53.6 |
62.8 |