mirrors
/
OWOD
mirror of https://github.com/JosephKJ/OWOD.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Updating the finetuning image_list, the earlier version was used for an ablation + other minor changes.

pull/42/head
Joseph 2021-05-11 10:28:04 +05:30
parent 787f2a24a5
commit 45da4b5cd0
8 changed files with 6848 additions and 1015 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -51,6 +51,8 @@ Sample command on a 4 GPU machine:
python tools/train_net.py --num-gpus 4 --config-file <Change to the appropriate config file> SOLVER.IMS_PER_BATCH 4 SOLVER.BASE_LR 0.005
```
Kindly run `replicate.sh` to replicate results from the models shared on the Google Drive.
Kindly check `run.sh` file for a task workflow.

14
configs/OWOD/t1/t1_ft.yaml
View File

@ -1,14 +0,0 @@
_BASE_: "../../Base-RCNN-C4-OWOD.yaml"
MODEL:
WEIGHTS: "/home/fk1/workspace/OWOD/output/t1_expr/model_final.pth"
DATASETS:
TRAIN: ('t1_voc_coco_2007_ft', ) # t1_voc_coco_2007_train, t1_voc_coco_2007_ft
TEST: (, ) # voc_coco_2007_test
SOLVER:
STEPS: (12000, 16000)
MAX_ITER: 18000
WARMUP_ITERS: 100
OUTPUT_DIR: "./output/t1_ft"
OWOD:
PREV_INTRODUCED_CLS: 0
CUR_INTRODUCED_CLS: 20

100
datasets/OWOD_imagesets/t1_ft.txt
View File

@ -1,100 +0,0 @@
2010_000889
007089
004746
2009_004532
2011_000780
009287
2008_006382
2010_001934
2008_004036
2010_004173
2008_000176
002045
2011_001862
2011_000477
2011_002697
006233
2008_008725
2010_001036
007538
2009_002676
2008_002776
000997
005081
2009_001326
2011_000725
2011_000485
2008_006543
2009_003522
2008_008511
009603
2008_008206
006719
2009_002054
2009_001493
2011_002674
002891
007524
2009_002317
2009_003087
2008_001199
2011_001854
001858
2010_005922
2008_006282
002058
004867
003611
003301
2008_001649
2010_003779
2010_002873
2010_003467
2009_001812
009283
009773
2008_004431
002055
2011_000971
2009_003613
2010_005731
2010_001315
2008_004515
2010_005424
2008_006682
2008_000817
000294
2008_006433
2010_000602
2008_008043
2009_001848
2009_004986
2008_004106
2011_001611
006124
2008_007124
2009_002792
2008_006285
007868
2008_001070
2008_008671
2008_000626
2008_000078
009734
007809
2008_000815
2010_000254
2010_003630
006896
2011_003059
004033
002757
007040
009166
001110
2008_003881
2008_000619
2010_002747
2009_003507
009155
000492

1937
datasets/OWOD_imagesets/t2_ft.txt
View File

File diff suppressed because it is too large Load Diff

2651
datasets/OWOD_imagesets/t3_ft.txt
View File

File diff suppressed because it is too large Load Diff

3143
datasets/OWOD_imagesets/t4_ft.txt
View File

File diff suppressed because it is too large Load Diff

6
detectron2/data/datasets/builtin.py
View File

@ -223,14 +223,8 @@ def register_all_pascal_voc(root):
("t1_voc_coco_2007_known_test", "VOC2007", "t1_known_test"),
("voc_coco_2007_test", "VOC2007", "all_task_test"),
("voc_coco_2007_val", "VOC2007", "all_task_val"),
("t1_voc_coco_2007_ft", "VOC2007", "t1_ft"),
("t2_voc_coco_2007_train", "VOC2007", "t2_train"),
("t2_voc_coco_2007_ft", "VOC2007", "t2_ft"),
("t2_voc_coco_2007_ft_10", "VOC2007", "t2_ft_10"),
("t2_voc_coco_2007_ft_20", "VOC2007", "t2_ft_20"),
("t2_voc_coco_2007_ft_50", "VOC2007", "t2_ft_50"),
("t2_voc_coco_2007_ft_200", "VOC2007", "t2_ft_200"),
("t2_voc_coco_2007_ft_400", "VOC2007", "t2_ft_400"),
("t3_voc_coco_2007_train", "VOC2007", "t3_train"),
("t3_voc_coco_2007_ft", "VOC2007", "t3_ft"),
("t4_voc_coco_2007_train", "VOC2007", "t4_train"),

10
run.sh
View File

@ -13,17 +13,15 @@
# Task 1
python tools/train_net.py --num-gpus 8 --dist-url='tcp://127.0.0.1:52125' --resume --config-file ./configs/OWOD/t1/t1_train.yaml SOLVER.IMS_PER_BATCH 8 SOLVER.BASE_LR 0.01 OUTPUT_DIR "./output/t1"
cp -r /home/joseph/workspace/OWOD/output/t1 /home/joseph/workspace/OWOD/output/t1_ft
# No need to finetune in Task 1, as there is no incremental component.
python tools/train_net.py --num-gpus 8 --dist-url='tcp://127.0.0.1:52126' --resume --config-file ./configs/OWOD/t1/t1_ft.yaml SOLVER.IMS_PER_BATCH 8 SOLVER.BASE_LR 0.01 OUTPUT_DIR "./output/t1_ft" MODEL.WEIGHTS "/home/joseph/workspace/OWOD/output/t1_ft/model_final.pth"
python tools/train_net.py --num-gpus 8 --dist-url='tcp://127.0.0.1:52133' --config-file ./configs/OWOD/t1/t1_val.yaml SOLVER.IMS_PER_BATCH 8 SOLVER.BASE_LR 0.01 OWOD.TEMPERATURE 1.5 OUTPUT_DIR "./output/t1_final" MODEL.WEIGHTS "/home/joseph/workspace/OWOD/output/t1/model_final.pth"
python tools/train_net.py --num-gpus 8 --dist-url='tcp://127.0.0.1:52133' --config-file ./configs/OWOD/t1/t1_val.yaml SOLVER.IMS_PER_BATCH 8 SOLVER.BASE_LR 0.01 OWOD.TEMPERATURE 1.5 OUTPUT_DIR "./output/t1_final" MODEL.WEIGHTS "/home/joseph/workspace/OWOD/output/t1_ft/model_final.pth"
python tools/train_net.py --num-gpus 8 --eval-only --config-file ./configs/OWOD/t1/t1_test.yaml SOLVER.IMS_PER_BATCH 8 SOLVER.BASE_LR 0.005 OUTPUT_DIR "./output/t1_final" MODEL.WEIGHTS "/home/joseph/workspace/OWOD/output/t1_ft/model_final.pth"
python tools/train_net.py --num-gpus 8 --eval-only --config-file ./configs/OWOD/t1/t1_test.yaml SOLVER.IMS_PER_BATCH 8 SOLVER.BASE_LR 0.005 OUTPUT_DIR "./output/t1_final" MODEL.WEIGHTS "/home/joseph/workspace/OWOD/output/t1/model_final.pth"
# Task 2
cp -r /home/joseph/workspace/OWOD/output/t1_ft /home/joseph/workspace/OWOD/output/t2
cp -r /home/joseph/workspace/OWOD/output/t1 /home/joseph/workspace/OWOD/output/t2
python tools/train_net.py --num-gpus 8 --dist-url='tcp://127.0.0.1:52127' --resume --config-file ./configs/OWOD/t2/t2_train.yaml SOLVER.IMS_PER_BATCH 8 SOLVER.BASE_LR 0.01 OUTPUT_DIR "./output/t2" MODEL.WEIGHTS "/home/joseph/workspace/OWOD/output/t2/model_final.pth"