ruslanchikbundyuk/VTON-API
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add at new repo again

Browse Source
This commit is contained in:
Руслан Бундюк
2025-01-28 21:48:35 +00:00
commit 6e660ddb3c
564 changed files with 75575 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/Base-RCNN-C4.yaml Normal file
View File

@@ -0,0 +1,18 @@
MODEL:
META_ARCHITECTURE: "GeneralizedRCNN"
RPN:
PRE_NMS_TOPK_TEST: 6000
POST_NMS_TOPK_TEST: 1000
ROI_HEADS:
NAME: "Res5ROIHeads"
DATASETS:
TRAIN: ("coco_2017_train",)
TEST: ("coco_2017_val",)
SOLVER:
IMS_PER_BATCH: 16
BASE_LR: 0.02
STEPS: (60000, 80000)
MAX_ITER: 90000
INPUT:
MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
VERSION: 2

31
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/Base-RCNN-DilatedC5.yaml Normal file
View File

@@ -0,0 +1,31 @@
MODEL:
META_ARCHITECTURE: "GeneralizedRCNN"
RESNETS:
OUT_FEATURES: ["res5"]
RES5_DILATION: 2
RPN:
IN_FEATURES: ["res5"]
PRE_NMS_TOPK_TEST: 6000
POST_NMS_TOPK_TEST: 1000
ROI_HEADS:
NAME: "StandardROIHeads"
IN_FEATURES: ["res5"]
ROI_BOX_HEAD:
NAME: "FastRCNNConvFCHead"
NUM_FC: 2
POOLER_RESOLUTION: 7
ROI_MASK_HEAD:
NAME: "MaskRCNNConvUpsampleHead"
NUM_CONV: 4
POOLER_RESOLUTION: 14
DATASETS:
TRAIN: ("coco_2017_train",)
TEST: ("coco_2017_val",)
SOLVER:
IMS_PER_BATCH: 16
BASE_LR: 0.02
STEPS: (60000, 80000)
MAX_ITER: 90000
INPUT:
MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
VERSION: 2

42
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/Base-RCNN-FPN.yaml Normal file
View File

@@ -0,0 +1,42 @@
MODEL:
META_ARCHITECTURE: "GeneralizedRCNN"
BACKBONE:
NAME: "build_resnet_fpn_backbone"
RESNETS:
OUT_FEATURES: ["res2", "res3", "res4", "res5"]
FPN:
IN_FEATURES: ["res2", "res3", "res4", "res5"]
ANCHOR_GENERATOR:
SIZES: [[32], [64], [128], [256], [512]] # One size for each in feature map
ASPECT_RATIOS: [[0.5, 1.0, 2.0]] # Three aspect ratios (same for all in feature maps)
RPN:
IN_FEATURES: ["p2", "p3", "p4", "p5", "p6"]
PRE_NMS_TOPK_TRAIN: 2000 # Per FPN level
PRE_NMS_TOPK_TEST: 1000 # Per FPN level
# Detectron1 uses 2000 proposals per-batch,
# (See "modeling/rpn/rpn_outputs.py" for details of this legacy issue)
# which is approximately 1000 proposals per-image since the default batch size for FPN is 2.
POST_NMS_TOPK_TRAIN: 1000
POST_NMS_TOPK_TEST: 1000
ROI_HEADS:
NAME: "StandardROIHeads"
IN_FEATURES: ["p2", "p3", "p4", "p5"]
ROI_BOX_HEAD:
NAME: "FastRCNNConvFCHead"
NUM_FC: 2
POOLER_RESOLUTION: 7
ROI_MASK_HEAD:
NAME: "MaskRCNNConvUpsampleHead"
NUM_CONV: 4
POOLER_RESOLUTION: 14
DATASETS:
TRAIN: ("coco_2017_train",)
TEST: ("coco_2017_val",)
SOLVER:
IMS_PER_BATCH: 16
BASE_LR: 0.02
STEPS: (60000, 80000)
MAX_ITER: 90000
INPUT:
MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
VERSION: 2

24
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/Base-RetinaNet.yaml Normal file
View File

@@ -0,0 +1,24 @@
MODEL:
META_ARCHITECTURE: "RetinaNet"
BACKBONE:
NAME: "build_retinanet_resnet_fpn_backbone"
RESNETS:
OUT_FEATURES: ["res3", "res4", "res5"]
ANCHOR_GENERATOR:
SIZES: !!python/object/apply:eval ["[[x, x * 2**(1.0/3), x * 2**(2.0/3) ] for x in [32, 64, 128, 256, 512 ]]"]
FPN:
IN_FEATURES: ["res3", "res4", "res5"]
RETINANET:
IOU_THRESHOLDS: [0.4, 0.5]
IOU_LABELS: [0, -1, 1]
DATASETS:
TRAIN: ("coco_2017_train",)
TEST: ("coco_2017_val",)
SOLVER:
IMS_PER_BATCH: 16
BASE_LR: 0.01 # Note that RetinaNet uses a different default learning rate
STEPS: (60000, 80000)
MAX_ITER: 90000
INPUT:
MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
VERSION: 2

17
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-Detection/fast_rcnn_R_50_FPN_1x.yaml Normal file
View File

@@ -0,0 +1,17 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: False
LOAD_PROPOSALS: True
RESNETS:
DEPTH: 50
PROPOSAL_GENERATOR:
NAME: "PrecomputedProposals"
DATASETS:
TRAIN: ("coco_2017_train",)
PROPOSAL_FILES_TRAIN: ("detectron2://COCO-Detection/rpn_R_50_FPN_1x/137258492/coco_2017_train_box_proposals_21bc3a.pkl", )
TEST: ("coco_2017_val",)
PROPOSAL_FILES_TEST: ("detectron2://COCO-Detection/rpn_R_50_FPN_1x/137258492/coco_2017_val_box_proposals_ee0dad.pkl", )
DATALOADER:
# proposals are part of the dataset_dicts, and take a lot of RAM
NUM_WORKERS: 2

9
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-Detection/faster_rcnn_R_101_C4_3x.yaml Normal file
View File

@@ -0,0 +1,9 @@
_BASE_: "../Base-RCNN-C4.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
MASK_ON: False
RESNETS:
DEPTH: 101
SOLVER:
STEPS: (210000, 250000)
MAX_ITER: 270000

9
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-Detection/faster_rcnn_R_101_DC5_3x.yaml Normal file
View File

@@ -0,0 +1,9 @@
_BASE_: "../Base-RCNN-DilatedC5.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
MASK_ON: False
RESNETS:
DEPTH: 101
SOLVER:
STEPS: (210000, 250000)
MAX_ITER: 270000

9
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-Detection/faster_rcnn_R_101_FPN_3x.yaml Normal file
View File

@@ -0,0 +1,9 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
MASK_ON: False
RESNETS:
DEPTH: 101
SOLVER:
STEPS: (210000, 250000)
MAX_ITER: 270000

6
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-Detection/faster_rcnn_R_50_C4_1x.yaml Normal file
View File

@@ -0,0 +1,6 @@
_BASE_: "../Base-RCNN-C4.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: False
RESNETS:
DEPTH: 50

9
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-Detection/faster_rcnn_R_50_C4_3x.yaml Normal file
View File

@@ -0,0 +1,9 @@
_BASE_: "../Base-RCNN-C4.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: False
RESNETS:
DEPTH: 50
SOLVER:
STEPS: (210000, 250000)
MAX_ITER: 270000

6
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-Detection/faster_rcnn_R_50_DC5_1x.yaml Normal file
View File

@@ -0,0 +1,6 @@
_BASE_: "../Base-RCNN-DilatedC5.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: False
RESNETS:
DEPTH: 50

9
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-Detection/faster_rcnn_R_50_DC5_3x.yaml Normal file
View File

@@ -0,0 +1,9 @@
_BASE_: "../Base-RCNN-DilatedC5.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: False
RESNETS:
DEPTH: 50
SOLVER:
STEPS: (210000, 250000)
MAX_ITER: 270000

6
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-Detection/faster_rcnn_R_50_FPN_1x.yaml Normal file
View File

@@ -0,0 +1,6 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: False
RESNETS:
DEPTH: 50

9
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-Detection/faster_rcnn_R_50_FPN_3x.yaml Normal file
View File

@@ -0,0 +1,9 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: False
RESNETS:
DEPTH: 50
SOLVER:
STEPS: (210000, 250000)
MAX_ITER: 270000

13
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-Detection/faster_rcnn_X_101_32x8d_FPN_3x.yaml Normal file
View File

@@ -0,0 +1,13 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
MASK_ON: False
WEIGHTS: "detectron2://ImageNetPretrained/FAIR/X-101-32x8d.pkl"
PIXEL_STD: [57.375, 57.120, 58.395]
RESNETS:
STRIDE_IN_1X1: False # this is a C2 model
NUM_GROUPS: 32
WIDTH_PER_GROUP: 8
DEPTH: 101
SOLVER:
STEPS: (210000, 250000)
MAX_ITER: 270000

8
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-Detection/retinanet_R_101_FPN_3x.yaml Normal file
View File

@@ -0,0 +1,8 @@
_BASE_: "../Base-RetinaNet.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
RESNETS:
DEPTH: 101
SOLVER:
STEPS: (210000, 250000)
MAX_ITER: 270000

5
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-Detection/retinanet_R_50_FPN_1x.yaml Normal file
View File

@@ -0,0 +1,5 @@
_BASE_: "../Base-RetinaNet.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
RESNETS:
DEPTH: 50

8
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-Detection/retinanet_R_50_FPN_3x.yaml Normal file
View File

@@ -0,0 +1,8 @@
_BASE_: "../Base-RetinaNet.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
RESNETS:
DEPTH: 50
SOLVER:
STEPS: (210000, 250000)
MAX_ITER: 270000

10
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-Detection/rpn_R_50_C4_1x.yaml Normal file
View File

@@ -0,0 +1,10 @@
_BASE_: "../Base-RCNN-C4.yaml"
MODEL:
META_ARCHITECTURE: "ProposalNetwork"
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: False
RESNETS:
DEPTH: 50
RPN:
PRE_NMS_TOPK_TEST: 12000
POST_NMS_TOPK_TEST: 2000

9
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-Detection/rpn_R_50_FPN_1x.yaml Normal file
View File

@@ -0,0 +1,9 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
META_ARCHITECTURE: "ProposalNetwork"
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: False
RESNETS:
DEPTH: 50
RPN:
POST_NMS_TOPK_TEST: 2000

9
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-InstanceSegmentation/mask_rcnn_R_101_C4_3x.yaml Normal file
View File

@@ -0,0 +1,9 @@
_BASE_: "../Base-RCNN-C4.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
MASK_ON: True
RESNETS:
DEPTH: 101
SOLVER:
STEPS: (210000, 250000)
MAX_ITER: 270000

9
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-InstanceSegmentation/mask_rcnn_R_101_DC5_3x.yaml Normal file
View File

@@ -0,0 +1,9 @@
_BASE_: "../Base-RCNN-DilatedC5.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
MASK_ON: True
RESNETS:
DEPTH: 101
SOLVER:
STEPS: (210000, 250000)
MAX_ITER: 270000

9
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-InstanceSegmentation/mask_rcnn_R_101_FPN_3x.yaml Normal file
View File

@@ -0,0 +1,9 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
MASK_ON: True
RESNETS:
DEPTH: 101
SOLVER:
STEPS: (210000, 250000)
MAX_ITER: 270000

6
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_C4_1x.yaml Normal file
View File

@@ -0,0 +1,6 @@
_BASE_: "../Base-RCNN-C4.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: True
RESNETS:
DEPTH: 50

9
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_C4_3x.yaml Normal file
View File

@@ -0,0 +1,9 @@
_BASE_: "../Base-RCNN-C4.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: True
RESNETS:
DEPTH: 50
SOLVER:
STEPS: (210000, 250000)
MAX_ITER: 270000

6
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_1x.yaml Normal file
View File

@@ -0,0 +1,6 @@
_BASE_: "../Base-RCNN-DilatedC5.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: True
RESNETS:
DEPTH: 50

9
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_3x.yaml Normal file
View File

@@ -0,0 +1,9 @@
_BASE_: "../Base-RCNN-DilatedC5.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: True
RESNETS:
DEPTH: 50
SOLVER:
STEPS: (210000, 250000)
MAX_ITER: 270000

6
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml Normal file
View File

@@ -0,0 +1,6 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: True
RESNETS:
DEPTH: 50

9
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml Normal file
View File

@@ -0,0 +1,9 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: True
RESNETS:
DEPTH: 50
SOLVER:
STEPS: (210000, 250000)
MAX_ITER: 270000

13
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_3x.yaml Normal file
View File

@@ -0,0 +1,13 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
MASK_ON: True
WEIGHTS: "detectron2://ImageNetPretrained/FAIR/X-101-32x8d.pkl"
PIXEL_STD: [57.375, 57.120, 58.395]
RESNETS:
STRIDE_IN_1X1: False # this is a C2 model
NUM_GROUPS: 32
WIDTH_PER_GROUP: 8
DEPTH: 101
SOLVER:
STEPS: (210000, 250000)
MAX_ITER: 270000

15
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-Keypoints/Base-Keypoint-RCNN-FPN.yaml Normal file
View File

@@ -0,0 +1,15 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
KEYPOINT_ON: True
ROI_HEADS:
NUM_CLASSES: 1
ROI_BOX_HEAD:
SMOOTH_L1_BETA: 0.5 # Keypoint AP degrades (though box AP improves) when using plain L1 loss
RPN:
# Detectron1 uses 2000 proposals per-batch, but this option is per-image in detectron2.
# 1000 proposals per-image is found to hurt box AP.
# Therefore we increase it to 1500 per-image.
POST_NMS_TOPK_TRAIN: 1500
DATASETS:
TRAIN: ("keypoints_coco_2017_train",)
TEST: ("keypoints_coco_2017_val",)

8
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-Keypoints/keypoint_rcnn_R_101_FPN_3x.yaml Normal file
View File

@@ -0,0 +1,8 @@
_BASE_: "Base-Keypoint-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
RESNETS:
DEPTH: 101
SOLVER:
STEPS: (210000, 250000)
MAX_ITER: 270000

5
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-Keypoints/keypoint_rcnn_R_50_FPN_1x.yaml Normal file
View File

@@ -0,0 +1,5 @@
_BASE_: "Base-Keypoint-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
RESNETS:
DEPTH: 50

8
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-Keypoints/keypoint_rcnn_R_50_FPN_3x.yaml Normal file
View File

@@ -0,0 +1,8 @@
_BASE_: "Base-Keypoint-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
RESNETS:
DEPTH: 50
SOLVER:
STEPS: (210000, 250000)
MAX_ITER: 270000

12
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-Keypoints/keypoint_rcnn_X_101_32x8d_FPN_3x.yaml Normal file
View File

@@ -0,0 +1,12 @@
_BASE_: "Base-Keypoint-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/FAIR/X-101-32x8d.pkl"
PIXEL_STD: [57.375, 57.120, 58.395]
RESNETS:
STRIDE_IN_1X1: False # this is a C2 model
NUM_GROUPS: 32
WIDTH_PER_GROUP: 8
DEPTH: 101
SOLVER:
STEPS: (210000, 250000)
MAX_ITER: 270000

9
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-PanopticSegmentation/Base-Panoptic-FPN.yaml Normal file
View File

@@ -0,0 +1,9 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
META_ARCHITECTURE: "PanopticFPN"
MASK_ON: True
SEM_SEG_HEAD:
LOSS_WEIGHT: 0.5
DATASETS:
TRAIN: ("coco_2017_train_panoptic_separated",)
TEST: ("coco_2017_val_panoptic_separated",)

8
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-PanopticSegmentation/panoptic_fpn_R_101_3x.yaml Normal file
View File

@@ -0,0 +1,8 @@
_BASE_: "Base-Panoptic-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
RESNETS:
DEPTH: 101
SOLVER:
STEPS: (210000, 250000)
MAX_ITER: 270000

5
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-PanopticSegmentation/panoptic_fpn_R_50_1x.yaml Normal file
View File

@@ -0,0 +1,5 @@
_BASE_: "Base-Panoptic-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
RESNETS:
DEPTH: 50

8
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/COCO-PanopticSegmentation/panoptic_fpn_R_50_3x.yaml Normal file
View File

@@ -0,0 +1,8 @@
_BASE_: "Base-Panoptic-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
RESNETS:
DEPTH: 50
SOLVER:
STEPS: (210000, 250000)
MAX_ITER: 270000

27
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/Cityscapes/mask_rcnn_R_50_FPN.yaml Normal file
View File

@@ -0,0 +1,27 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
# WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
# For better, more stable performance initialize from COCO
WEIGHTS: "detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl"
MASK_ON: True
ROI_HEADS:
NUM_CLASSES: 8
# This is similar to the setting used in Mask R-CNN paper, Appendix A
# But there are some differences, e.g., we did not initialize the output
# layer using the corresponding classes from COCO
INPUT:
MIN_SIZE_TRAIN: (800, 832, 864, 896, 928, 960, 992, 1024)
MIN_SIZE_TRAIN_SAMPLING: "choice"
MIN_SIZE_TEST: 1024
MAX_SIZE_TRAIN: 2048
MAX_SIZE_TEST: 2048
DATASETS:
TRAIN: ("cityscapes_fine_instance_seg_train",)
TEST: ("cityscapes_fine_instance_seg_val",)
SOLVER:
BASE_LR: 0.01
STEPS: (18000,)
MAX_ITER: 24000
IMS_PER_BATCH: 8
TEST:
EVAL_PERIOD: 8000

83
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/Detectron1-Comparisons/README.md Normal file
View File

@@ -0,0 +1,83 @@
Detectron2 model zoo's experimental settings and a few implementation details are different from Detectron.
The differences in implementation details are shared in
[Compatibility with Other Libraries](../../docs/notes/compatibility.md).
The differences in model zoo's experimental settings include:
* Use scale augmentation during training. This improves AP with lower training cost.
* Use L1 loss instead of smooth L1 loss for simplicity. This sometimes improves box AP but may
affect other AP.
* Use `POOLER_SAMPLING_RATIO=0` instead of 2. This does not significantly affect AP.
* Use `ROIAlignV2`. This does not significantly affect AP.
In this directory, we provide a few configs that __do not__ have the above changes.
They mimic Detectron's behavior as close as possible,
and provide a fair comparison of accuracy and speed against Detectron.
<!--
./gen_html_table.py --config 'Detectron1-Comparisons/*.yaml' --name "Faster R-CNN" "Keypoint R-CNN" "Mask R-CNN" --fields lr_sched train_speed inference_speed mem box_AP mask_AP keypoint_AP --base-dir ../../../configs/Detectron1-Comparisons
-->
<table><tbody>
<!-- START TABLE -->
<!-- TABLE HEADER -->
<th valign="bottom">Name</th>
<th valign="bottom">lr<br/>sched</th>
<th valign="bottom">train<br/>time<br/>(s/iter)</th>
<th valign="bottom">inference<br/>time<br/>(s/im)</th>
<th valign="bottom">train<br/>mem<br/>(GB)</th>
<th valign="bottom">box<br/>AP</th>
<th valign="bottom">mask<br/>AP</th>
<th valign="bottom">kp.<br/>AP</th>
<th valign="bottom">model id</th>
<th valign="bottom">download</th>
<!-- TABLE BODY -->
<!-- ROW: faster_rcnn_R_50_FPN_noaug_1x -->
<tr><td align="left"><a href="faster_rcnn_R_50_FPN_noaug_1x.yaml">Faster R-CNN</a></td>
<td align="center">1x</td>
<td align="center">0.219</td>
<td align="center">0.038</td>
<td align="center">3.1</td>
<td align="center">36.9</td>
<td align="center"></td>
<td align="center"></td>
<td align="center">137781054</td>
<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/Detectron1-Comparisons/faster_rcnn_R_50_FPN_noaug_1x/137781054/model_final_7ab50c.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/Detectron1-Comparisons/faster_rcnn_R_50_FPN_noaug_1x/137781054/metrics.json">metrics</a></td>
</tr>
<!-- ROW: keypoint_rcnn_R_50_FPN_1x -->
<tr><td align="left"><a href="keypoint_rcnn_R_50_FPN_1x.yaml">Keypoint R-CNN</a></td>
<td align="center">1x</td>
<td align="center">0.313</td>
<td align="center">0.071</td>
<td align="center">5.0</td>
<td align="center">53.1</td>
<td align="center"></td>
<td align="center">64.2</td>
<td align="center">137781195</td>
<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/Detectron1-Comparisons/keypoint_rcnn_R_50_FPN_1x/137781195/model_final_cce136.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/Detectron1-Comparisons/keypoint_rcnn_R_50_FPN_1x/137781195/metrics.json">metrics</a></td>
</tr>
<!-- ROW: mask_rcnn_R_50_FPN_noaug_1x -->
<tr><td align="left"><a href="mask_rcnn_R_50_FPN_noaug_1x.yaml">Mask R-CNN</a></td>
<td align="center">1x</td>
<td align="center">0.273</td>
<td align="center">0.043</td>
<td align="center">3.4</td>
<td align="center">37.8</td>
<td align="center">34.9</td>
<td align="center"></td>
<td align="center">137781281</td>
<td align="center"><a href="https://dl.fbaipublicfiles.com/detectron2/Detectron1-Comparisons/mask_rcnn_R_50_FPN_noaug_1x/137781281/model_final_62ca52.pkl">model</a>&nbsp;|&nbsp;<a href="https://dl.fbaipublicfiles.com/detectron2/Detectron1-Comparisons/mask_rcnn_R_50_FPN_noaug_1x/137781281/metrics.json">metrics</a></td>
</tr>
</tbody></table>
## Comparisons:
* Faster R-CNN: Detectron's AP is 36.7, similar to ours.
* Keypoint R-CNN: Detectron's AP is box 53.6, keypoint 64.2. Fixing a Detectron's
[bug](https://github.com/facebookresearch/Detectron/issues/459) lead to a drop in box AP, and can be
compensated back by some parameter tuning.
* Mask R-CNN: Detectron's AP is box 37.7, mask 33.9. We're 1 AP better in mask AP, due to more correct implementation.
For speed comparison, see [benchmarks](https://detectron2.readthedocs.io/notes/benchmarks.html).

17
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/Detectron1-Comparisons/faster_rcnn_R_50_FPN_noaug_1x.yaml Normal file
View File

@@ -0,0 +1,17 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: False
RESNETS:
DEPTH: 50
# Detectron1 uses smooth L1 loss with some magic beta values.
# The defaults are changed to L1 loss in Detectron2.
RPN:
SMOOTH_L1_BETA: 0.1111
ROI_BOX_HEAD:
SMOOTH_L1_BETA: 1.0
POOLER_SAMPLING_RATIO: 2
POOLER_TYPE: "ROIAlign"
INPUT:
# no scale augmentation
MIN_SIZE_TRAIN: (800, )

27
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/Detectron1-Comparisons/keypoint_rcnn_R_50_FPN_1x.yaml Normal file
View File

@@ -0,0 +1,27 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
KEYPOINT_ON: True
RESNETS:
DEPTH: 50
ROI_HEADS:
NUM_CLASSES: 1
ROI_KEYPOINT_HEAD:
POOLER_RESOLUTION: 14
POOLER_SAMPLING_RATIO: 2
POOLER_TYPE: "ROIAlign"
# Detectron1 uses smooth L1 loss with some magic beta values.
# The defaults are changed to L1 loss in Detectron2.
ROI_BOX_HEAD:
SMOOTH_L1_BETA: 1.0
POOLER_SAMPLING_RATIO: 2
POOLER_TYPE: "ROIAlign"
RPN:
SMOOTH_L1_BETA: 0.1111
# Detectron1 uses 2000 proposals per-batch, but this option is per-image in detectron2
# 1000 proposals per-image is found to hurt box AP.
# Therefore we increase it to 1500 per-image.
POST_NMS_TOPK_TRAIN: 1500
DATASETS:
TRAIN: ("keypoints_coco_2017_train",)
TEST: ("keypoints_coco_2017_val",)

20
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/Detectron1-Comparisons/mask_rcnn_R_50_FPN_noaug_1x.yaml Normal file
View File

@@ -0,0 +1,20 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: True
RESNETS:
DEPTH: 50
# Detectron1 uses smooth L1 loss with some magic beta values.
# The defaults are changed to L1 loss in Detectron2.
RPN:
SMOOTH_L1_BETA: 0.1111
ROI_BOX_HEAD:
SMOOTH_L1_BETA: 1.0
POOLER_SAMPLING_RATIO: 2
POOLER_TYPE: "ROIAlign"
ROI_MASK_HEAD:
POOLER_SAMPLING_RATIO: 2
POOLER_TYPE: "ROIAlign"
INPUT:
# no scale augmentation
MIN_SIZE_TRAIN: (800, )

19
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/LVIS-InstanceSegmentation/mask_rcnn_R_101_FPN_1x.yaml Normal file
View File

@@ -0,0 +1,19 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
MASK_ON: True
RESNETS:
DEPTH: 101
ROI_HEADS:
NUM_CLASSES: 1230
SCORE_THRESH_TEST: 0.0001
INPUT:
MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
DATASETS:
TRAIN: ("lvis_v0.5_train",)
TEST: ("lvis_v0.5_val",)
TEST:
DETECTIONS_PER_IMAGE: 300 # LVIS allows up to 300
DATALOADER:
SAMPLER_TRAIN: "RepeatFactorTrainingSampler"
REPEAT_THRESHOLD: 0.001

19
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/LVIS-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml Normal file
View File

@@ -0,0 +1,19 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: True
RESNETS:
DEPTH: 50
ROI_HEADS:
NUM_CLASSES: 1230
SCORE_THRESH_TEST: 0.0001
INPUT:
MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
DATASETS:
TRAIN: ("lvis_v0.5_train",)
TEST: ("lvis_v0.5_val",)
TEST:
DETECTIONS_PER_IMAGE: 300 # LVIS allows up to 300
DATALOADER:
SAMPLER_TRAIN: "RepeatFactorTrainingSampler"
REPEAT_THRESHOLD: 0.001

23
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/LVIS-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_1x.yaml Normal file
View File

@@ -0,0 +1,23 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/FAIR/X-101-32x8d.pkl"
PIXEL_STD: [57.375, 57.120, 58.395]
MASK_ON: True
RESNETS:
STRIDE_IN_1X1: False # this is a C2 model
NUM_GROUPS: 32
WIDTH_PER_GROUP: 8
DEPTH: 101
ROI_HEADS:
NUM_CLASSES: 1230
SCORE_THRESH_TEST: 0.0001
INPUT:
MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
DATASETS:
TRAIN: ("lvis_v0.5_train",)
TEST: ("lvis_v0.5_val",)
TEST:
DETECTIONS_PER_IMAGE: 300 # LVIS allows up to 300
DATALOADER:
SAMPLER_TRAIN: "RepeatFactorTrainingSampler"
REPEAT_THRESHOLD: 0.001

12
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/cascade_mask_rcnn_R_50_FPN_1x.yaml Normal file
View File

@@ -0,0 +1,12 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: True
RESNETS:
DEPTH: 50
ROI_HEADS:
NAME: CascadeROIHeads
ROI_BOX_HEAD:
CLS_AGNOSTIC_BBOX_REG: True
RPN:
POST_NMS_TOPK_TRAIN: 2000

15
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/cascade_mask_rcnn_R_50_FPN_3x.yaml Normal file
View File

@@ -0,0 +1,15 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: True
RESNETS:
DEPTH: 50
ROI_HEADS:
NAME: CascadeROIHeads
ROI_BOX_HEAD:
CLS_AGNOSTIC_BBOX_REG: True
RPN:
POST_NMS_TOPK_TRAIN: 2000
SOLVER:
STEPS: (210000, 250000)
MAX_ITER: 270000

36
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/cascade_mask_rcnn_X_152_32x8d_FPN_IN5k_gn_dconv.yaml Normal file
View File

@@ -0,0 +1,36 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
MASK_ON: True
WEIGHTS: "catalog://ImageNetPretrained/FAIR/X-152-32x8d-IN5k"
RESNETS:
STRIDE_IN_1X1: False # this is a C2 model
NUM_GROUPS: 32
WIDTH_PER_GROUP: 8
DEPTH: 152
DEFORM_ON_PER_STAGE: [False, True, True, True]
ROI_HEADS:
NAME: "CascadeROIHeads"
ROI_BOX_HEAD:
NAME: "FastRCNNConvFCHead"
NUM_CONV: 4
NUM_FC: 1
NORM: "GN"
CLS_AGNOSTIC_BBOX_REG: True
ROI_MASK_HEAD:
NUM_CONV: 8
NORM: "GN"
RPN:
POST_NMS_TOPK_TRAIN: 2000
SOLVER:
IMS_PER_BATCH: 128
STEPS: (35000, 45000)
MAX_ITER: 50000
BASE_LR: 0.16
INPUT:
MIN_SIZE_TRAIN: (640, 864)
MIN_SIZE_TRAIN_SAMPLING: "range"
MAX_SIZE_TRAIN: 1440
CROP:
ENABLED: True
TEST:
EVAL_PERIOD: 2500

42
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/cascade_mask_rcnn_X_152_32x8d_FPN_IN5k_gn_dconv_parsing.yaml Normal file
View File

@@ -0,0 +1,42 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
MASK_ON: True
# WEIGHTS: "catalog://ImageNetPretrained/FAIR/X-152-32x8d-IN5k"
WEIGHTS: "model_0039999_e76410.pkl"
RESNETS:
STRIDE_IN_1X1: False # this is a C2 model
NUM_GROUPS: 32
WIDTH_PER_GROUP: 8
DEPTH: 152
DEFORM_ON_PER_STAGE: [False, True, True, True]
ROI_HEADS:
NAME: "CascadeROIHeads"
NUM_CLASSES: 1
ROI_BOX_HEAD:
NAME: "FastRCNNConvFCHead"
NUM_CONV: 4
NUM_FC: 1
NORM: "GN"
CLS_AGNOSTIC_BBOX_REG: True
ROI_MASK_HEAD:
NUM_CONV: 8
NORM: "GN"
RPN:
POST_NMS_TOPK_TRAIN: 2000
SOLVER:
# IMS_PER_BATCH: 128
IMS_PER_BATCH: 1
STEPS: (35000, 45000)
MAX_ITER: 50000
BASE_LR: 0.16
INPUT:
MIN_SIZE_TRAIN: (640, 864)
MIN_SIZE_TRAIN_SAMPLING: "range"
MAX_SIZE_TRAIN: 1440
CROP:
ENABLED: True
TEST:
EVAL_PERIOD: 2500
DATASETS:
TRAIN: ("CIHP_train","VIP_trainval")
TEST: ("CIHP_val",)

25
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/demo.yaml Normal file
View File

@@ -0,0 +1,25 @@
_BASE_: "cascade_mask_rcnn_X_152_32x8d_FPN_IN5k_gn_dconv.yaml"
MODEL:
MASK_ON: True
ROI_HEADS:
NMS_THRESH_TEST: 0.95
SCORE_THRESH_TEST: 0.5
NUM_CLASSES: 1
SOLVER:
IMS_PER_BATCH: 1
STEPS: (30000, 45000)
MAX_ITER: 50000
BASE_LR: 0.02
INPUT:
MIN_SIZE_TRAIN: (640, 864)
MIN_SIZE_TRAIN_SAMPLING: "range"
MAX_SIZE_TRAIN: 1440
CROP:
ENABLED: True
TEST:
AUG:
ENABLED: True
DATASETS:
TRAIN: ("demo_train",)
TEST: ("demo_val",)
OUTPUT_DIR: "../../data/DemoDataset/detectron2_prediction"

10
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/mask_rcnn_R_50_FPN_1x_cls_agnostic.yaml Normal file
View File

@@ -0,0 +1,10 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: True
RESNETS:
DEPTH: 50
ROI_BOX_HEAD:
CLS_AGNOSTIC_BBOX_REG: True
ROI_MASK_HEAD:
CLS_AGNOSTIC_MASK: True

8
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/mask_rcnn_R_50_FPN_1x_dconv_c3-c5.yaml Normal file
View File

@@ -0,0 +1,8 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: True
RESNETS:
DEPTH: 50
DEFORM_ON_PER_STAGE: [False, True, True, True] # on Res3,Res4,Res5
DEFORM_MODULATED: False

11
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/mask_rcnn_R_50_FPN_3x_dconv_c3-c5.yaml Normal file
View File

@@ -0,0 +1,11 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: True
RESNETS:
DEPTH: 50
DEFORM_ON_PER_STAGE: [False, True, True, True] # on Res3,Res4,Res5
DEFORM_MODULATED: False
SOLVER:
STEPS: (210000, 250000)
MAX_ITER: 270000

21
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/mask_rcnn_R_50_FPN_3x_gn.yaml Normal file
View File

@@ -0,0 +1,21 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "catalog://ImageNetPretrained/FAIR/R-50-GN"
MASK_ON: True
RESNETS:
DEPTH: 50
NORM: "GN"
STRIDE_IN_1X1: False
FPN:
NORM: "GN"
ROI_BOX_HEAD:
NAME: "FastRCNNConvFCHead"
NUM_CONV: 4
NUM_FC: 1
NORM: "GN"
ROI_MASK_HEAD:
NORM: "GN"
SOLVER:
# 3x schedule
STEPS: (210000, 250000)
MAX_ITER: 270000

24
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/mask_rcnn_R_50_FPN_3x_syncbn.yaml Normal file
View File

@@ -0,0 +1,24 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: True
RESNETS:
DEPTH: 50
NORM: "SyncBN"
STRIDE_IN_1X1: True
FPN:
NORM: "SyncBN"
ROI_BOX_HEAD:
NAME: "FastRCNNConvFCHead"
NUM_CONV: 4
NUM_FC: 1
NORM: "SyncBN"
ROI_MASK_HEAD:
NORM: "SyncBN"
SOLVER:
# 3x schedule
STEPS: (210000, 250000)
MAX_ITER: 270000
TEST:
PRECISE_BN:
ENABLED: True

26
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/panoptic_fpn_R_101_dconv_cascade_gn_3x.yaml Normal file
View File

@@ -0,0 +1,26 @@
# A large PanopticFPN for demo purposes.
# Use GN on backbone to support semantic seg.
# Use Cascade + Deform Conv to improve localization.
_BASE_: "../COCO-PanopticSegmentation/Base-Panoptic-FPN.yaml"
MODEL:
WEIGHTS: "catalog://ImageNetPretrained/FAIR/R-101-GN"
RESNETS:
DEPTH: 101
NORM: "GN"
DEFORM_ON_PER_STAGE: [False, True, True, True]
STRIDE_IN_1X1: False
FPN:
NORM: "GN"
ROI_HEADS:
NAME: CascadeROIHeads
ROI_BOX_HEAD:
CLS_AGNOSTIC_BBOX_REG: True
ROI_MASK_HEAD:
NORM: "GN"
RPN:
POST_NMS_TOPK_TRAIN: 2000
SOLVER:
STEPS: (105000, 125000)
MAX_ITER: 135000
IMS_PER_BATCH: 32
BASE_LR: 0.04

24
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/parsing_finetune_cihp.yaml Normal file
View File

@@ -0,0 +1,24 @@
_BASE_: "cascade_mask_rcnn_X_152_32x8d_FPN_IN5k_gn_dconv.yaml"
MODEL:
MASK_ON: True
WEIGHTS: "model_0039999_e76410.pkl"
ROI_HEADS:
NUM_CLASSES: 1
SOLVER:
IMS_PER_BATCH: 16
STEPS: (140000, 180000)
MAX_ITER: 200000
BASE_LR: 0.02
INPUT:
MIN_SIZE_TRAIN: (640, 864)
MIN_SIZE_TRAIN_SAMPLING: "range"
MAX_SIZE_TRAIN: 1440
CROP:
ENABLED: True
TEST:
EVAL_PERIOD: 0
DATASETS:
TRAIN: ("CIHP_train")
TEST: ("CIHP_val",)
OUTPUT_DIR: "./finetune_output"

26
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/parsing_inference.yaml Normal file
View File

@@ -0,0 +1,26 @@
_BASE_: "cascade_mask_rcnn_X_152_32x8d_FPN_IN5k_gn_dconv.yaml"
MODEL:
MASK_ON: True
WEIGHTS: "./finetune_ouput/model_final.pth"
ROI_HEADS:
NMS_THRESH_TEST: 0.95
SCORE_THRESH_TEST: 0.5
NUM_CLASSES: 1
SOLVER:
IMS_PER_BATCH: 1
STEPS: (30000, 45000)
MAX_ITER: 50000
BASE_LR: 0.02
INPUT:
MIN_SIZE_TRAIN: (640, 864)
MIN_SIZE_TRAIN_SAMPLING: "range"
MAX_SIZE_TRAIN: 1440
CROP:
ENABLED: True
TEST:
AUG:
ENABLED: True
DATASETS:
TRAIN: ("CIHP_trainval",)
TEST: ("CIHP_test",)
OUTPUT_DIR: "./inference_output"

13
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/scratch_mask_rcnn_R_50_FPN_3x_gn.yaml Normal file
View File

@@ -0,0 +1,13 @@
_BASE_: "mask_rcnn_R_50_FPN_3x_gn.yaml"
MODEL:
# Train from random initialization.
WEIGHTS: ""
# It makes sense to divide by STD when training from scratch
# But it seems to make no difference on the results and C2's models didn't do this.
# So we keep things consistent with C2.
# PIXEL_STD: [57.375, 57.12, 58.395]
MASK_ON: True
BACKBONE:
FREEZE_AT: 0
# NOTE: Please refer to Rethinking ImageNet Pre-training https://arxiv.org/abs/1811.08883
# to learn what you need for training from scratch.

19
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/scratch_mask_rcnn_R_50_FPN_9x_gn.yaml Normal file
View File

@@ -0,0 +1,19 @@
_BASE_: "mask_rcnn_R_50_FPN_3x_gn.yaml"
MODEL:
PIXEL_STD: [57.375, 57.12, 58.395]
WEIGHTS: ""
MASK_ON: True
RESNETS:
STRIDE_IN_1X1: False
BACKBONE:
FREEZE_AT: 0
SOLVER:
# 9x schedule
IMS_PER_BATCH: 64 # 4x the standard
STEPS: (187500, 197500) # last 60/4==15k and last 20/4==5k
MAX_ITER: 202500 # 90k * 9 / 4
BASE_LR: 0.08
TEST:
EVAL_PERIOD: 2500
# NOTE: Please refer to Rethinking ImageNet Pre-training https://arxiv.org/abs/1811.08883
# to learn what you need for training from scratch.

19
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/scratch_mask_rcnn_R_50_FPN_9x_syncbn.yaml Normal file
View File

@@ -0,0 +1,19 @@
_BASE_: "mask_rcnn_R_50_FPN_3x_syncbn.yaml"
MODEL:
PIXEL_STD: [57.375, 57.12, 58.395]
WEIGHTS: ""
MASK_ON: True
RESNETS:
STRIDE_IN_1X1: False
BACKBONE:
FREEZE_AT: 0
SOLVER:
# 9x schedule
IMS_PER_BATCH: 64 # 4x the standard
STEPS: (187500, 197500) # last 60/4==15k and last 20/4==5k
MAX_ITER: 202500 # 90k * 9 / 4
BASE_LR: 0.08
TEST:
EVAL_PERIOD: 2500
# NOTE: Please refer to Rethinking ImageNet Pre-training https://arxiv.org/abs/1811.08883
# to learn what you need for training from scratch.

11
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/Misc/semantic_R_50_FPN_1x.yaml Normal file
View File

@@ -0,0 +1,11 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
META_ARCHITECTURE: "SemanticSegmentor"
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
RESNETS:
DEPTH: 50
DATASETS:
TRAIN: ("coco_2017_train_panoptic_stuffonly",)
TEST: ("coco_2017_val_panoptic_stuffonly",)
INPUT:
MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)

18
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/PascalVOC-Detection/faster_rcnn_R_50_C4.yaml Normal file
View File

@@ -0,0 +1,18 @@
_BASE_: "../Base-RCNN-C4.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: False
RESNETS:
DEPTH: 50
ROI_HEADS:
NUM_CLASSES: 20
INPUT:
MIN_SIZE_TRAIN: (480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 800)
MIN_SIZE_TEST: 800
DATASETS:
TRAIN: ('voc_2007_trainval', 'voc_2012_trainval')
TEST: ('voc_2007_test',)
SOLVER:
STEPS: (12000, 16000)
MAX_ITER: 18000 # 17.4 epochs
WARMUP_ITERS: 100

18
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/PascalVOC-Detection/faster_rcnn_R_50_FPN.yaml Normal file
View File

@@ -0,0 +1,18 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: False
RESNETS:
DEPTH: 50
ROI_HEADS:
NUM_CLASSES: 20
INPUT:
MIN_SIZE_TRAIN: (480, 512, 544, 576, 608, 640, 672, 704, 736, 768, 800)
MIN_SIZE_TEST: 800
DATASETS:
TRAIN: ('voc_2007_trainval', 'voc_2012_trainval')
TEST: ('voc_2007_test',)
SOLVER:
STEPS: (12000, 16000)
MAX_ITER: 18000 # 17.4 epochs
WARMUP_ITERS: 100

42
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/my_Base-RCNN-FPN.yaml Normal file
View File

@@ -0,0 +1,42 @@
MODEL:
META_ARCHITECTURE: "GeneralizedRCNN"
BACKBONE:
NAME: "build_resnet_fpn_backbone"
RESNETS:
OUT_FEATURES: ["res2", "res3", "res4", "res5"]
FPN:
IN_FEATURES: ["res2", "res3", "res4", "res5"]
ANCHOR_GENERATOR:
SIZES: [[32], [64], [128], [256], [512]] # One size for each in feature map
ASPECT_RATIOS: [[0.5, 1.0, 2.0]] # Three aspect ratios (same for all in feature maps)
RPN:
IN_FEATURES: ["p2", "p3", "p4", "p5", "p6"]
PRE_NMS_TOPK_TRAIN: 2000 # Per FPN level
PRE_NMS_TOPK_TEST: 1000 # Per FPN level
# Detectron1 uses 2000 proposals per-batch,
# (See "modeling/rpn/rpn_outputs.py" for details of this legacy issue)
# which is approximately 1000 proposals per-image since the default batch size for FPN is 2.
POST_NMS_TOPK_TRAIN: 1000
POST_NMS_TOPK_TEST: 1000
ROI_HEADS:
NAME: "StandardROIHeads"
IN_FEATURES: ["p2", "p3", "p4", "p5"]
ROI_BOX_HEAD:
NAME: "FastRCNNConvFCHead"
NUM_FC: 2
POOLER_RESOLUTION: 7
ROI_MASK_HEAD:
NAME: "MaskRCNNConvUpsampleHead"
NUM_CONV: 4
POOLER_RESOLUTION: 14
DATASETS:
TRAIN: ("coco_2017_train",)
TEST: ("coco_2017_val",)
SOLVER:
IMS_PER_BATCH: 2
BASE_LR: 0.02
STEPS: (60000, 80000)
MAX_ITER: 90000
INPUT:
MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
VERSION: 2

1
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/README.md Normal file
View File

@@ -0,0 +1 @@
These are quick configs for performance or accuracy regression tracking purposes.

7
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/cascade_mask_rcnn_R_50_FPN_inference_acc_test.yaml Normal file
View File

@@ -0,0 +1,7 @@
_BASE_: "../Misc/cascade_mask_rcnn_R_50_FPN_3x.yaml"
MODEL:
WEIGHTS: "detectron2://Misc/cascade_mask_rcnn_R_50_FPN_3x/144998488/model_final_480dd8.pkl"
DATASETS:
TEST: ("coco_2017_val_100",)
TEST:
EXPECTED_RESULTS: [["bbox", "AP", 50.18, 0.02], ["segm", "AP", 43.87, 0.02]]

11
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/cascade_mask_rcnn_R_50_FPN_instant_test.yaml Normal file
View File

@@ -0,0 +1,11 @@
_BASE_: "../Misc/cascade_mask_rcnn_R_50_FPN_3x.yaml"
DATASETS:
TRAIN: ("coco_2017_val_100",)
TEST: ("coco_2017_val_100",)
SOLVER:
BASE_LR: 0.005
STEPS: (30,)
MAX_ITER: 40
IMS_PER_BATCH: 4
DATALOADER:
NUM_WORKERS: 2

7
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/fast_rcnn_R_50_FPN_inference_acc_test.yaml Normal file
View File

@@ -0,0 +1,7 @@
_BASE_: "../COCO-Detection/fast_rcnn_R_50_FPN_1x.yaml"
MODEL:
WEIGHTS: "detectron2://COCO-Detection/fast_rcnn_R_50_FPN_1x/137635226/model_final_e5f7ce.pkl"
DATASETS:
TEST: ("coco_2017_val_100",)
TEST:
EXPECTED_RESULTS: [["bbox", "AP", 45.70, 0.02]]

15
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/fast_rcnn_R_50_FPN_instant_test.yaml Normal file
View File

@@ -0,0 +1,15 @@
_BASE_: "../COCO-Detection/fast_rcnn_R_50_FPN_1x.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
DATASETS:
TRAIN: ("coco_2017_val_100",)
PROPOSAL_FILES_TRAIN: ("detectron2://COCO-Detection/rpn_R_50_FPN_1x/137258492/coco_2017_val_box_proposals_ee0dad.pkl", )
TEST: ("coco_2017_val_100",)
PROPOSAL_FILES_TEST: ("detectron2://COCO-Detection/rpn_R_50_FPN_1x/137258492/coco_2017_val_box_proposals_ee0dad.pkl", )
SOLVER:
BASE_LR: 0.005
STEPS: (30,)
MAX_ITER: 40
IMS_PER_BATCH: 4
DATALOADER:
NUM_WORKERS: 2

7
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/keypoint_rcnn_R_50_FPN_inference_acc_test.yaml Normal file
View File

@@ -0,0 +1,7 @@
_BASE_: "../COCO-Keypoints/keypoint_rcnn_R_50_FPN_3x.yaml"
MODEL:
WEIGHTS: "detectron2://COCO-Keypoints/keypoint_rcnn_R_50_FPN_3x/137849621/model_final_a6e10b.pkl"
DATASETS:
TEST: ("keypoints_coco_2017_val_100",)
TEST:
EXPECTED_RESULTS: [["bbox", "AP", 52.47, 0.02], ["keypoints", "AP", 67.36, 0.02]]

14
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/keypoint_rcnn_R_50_FPN_instant_test.yaml Normal file
View File

@@ -0,0 +1,14 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
KEYPOINT_ON: True
DATASETS:
TRAIN: ("keypoints_coco_2017_val_100",)
TEST: ("keypoints_coco_2017_val_100",)
SOLVER:
BASE_LR: 0.005
STEPS: (30,)
MAX_ITER: 40
IMS_PER_BATCH: 4
DATALOADER:
NUM_WORKERS: 2

30
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/keypoint_rcnn_R_50_FPN_normalized_training_acc_test.yaml Normal file
View File

@@ -0,0 +1,30 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
KEYPOINT_ON: True
RESNETS:
DEPTH: 50
ROI_HEADS:
BATCH_SIZE_PER_IMAGE: 256
NUM_CLASSES: 1
ROI_KEYPOINT_HEAD:
POOLER_RESOLUTION: 14
POOLER_SAMPLING_RATIO: 2
NORMALIZE_LOSS_BY_VISIBLE_KEYPOINTS: False
LOSS_WEIGHT: 4.0
ROI_BOX_HEAD:
SMOOTH_L1_BETA: 1.0 # Keypoint AP degrades when using plain L1 loss
RPN:
SMOOTH_L1_BETA: 0.2 # Keypoint AP degrades when using plain L1 loss
DATASETS:
TRAIN: ("keypoints_coco_2017_val",)
TEST: ("keypoints_coco_2017_val",)
INPUT:
MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
SOLVER:
WARMUP_FACTOR: 0.33333333
WARMUP_ITERS: 100
STEPS: (5500, 5800)
MAX_ITER: 6000
TEST:
EXPECTED_RESULTS: [["bbox", "AP", 55.35, 1.0], ["keypoints", "AP", 76.91, 1.0]]

28
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/keypoint_rcnn_R_50_FPN_training_acc_test.yaml Normal file
View File

@@ -0,0 +1,28 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
KEYPOINT_ON: True
RESNETS:
DEPTH: 50
ROI_HEADS:
BATCH_SIZE_PER_IMAGE: 256
NUM_CLASSES: 1
ROI_KEYPOINT_HEAD:
POOLER_RESOLUTION: 14
POOLER_SAMPLING_RATIO: 2
ROI_BOX_HEAD:
SMOOTH_L1_BETA: 1.0 # Keypoint AP degrades when using plain L1 loss
RPN:
SMOOTH_L1_BETA: 0.2 # Keypoint AP degrades when using plain L1 loss
DATASETS:
TRAIN: ("keypoints_coco_2017_val",)
TEST: ("keypoints_coco_2017_val",)
INPUT:
MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
SOLVER:
WARMUP_FACTOR: 0.33333333
WARMUP_ITERS: 100
STEPS: (5500, 5800)
MAX_ITER: 6000
TEST:
EXPECTED_RESULTS: [["bbox", "AP", 53.5, 1.0], ["keypoints", "AP", 72.4, 1.0]]

18
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/mask_rcnn_R_50_C4_GCV_instant_test.yaml Normal file
View File

@@ -0,0 +1,18 @@
_BASE_: "../Base-RCNN-C4.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: True
DATASETS:
TRAIN: ("coco_2017_val_100",)
TEST: ("coco_2017_val_100",)
SOLVER:
BASE_LR: 0.001
STEPS: (30,)
MAX_ITER: 40
IMS_PER_BATCH: 4
CLIP_GRADIENTS:
ENABLED: True
CLIP_TYPE: "value"
CLIP_VALUE: 1.0
DATALOADER:
NUM_WORKERS: 2

7
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/mask_rcnn_R_50_C4_inference_acc_test.yaml Normal file
View File

@@ -0,0 +1,7 @@
_BASE_: "../COCO-InstanceSegmentation/mask_rcnn_R_50_C4_3x.yaml"
MODEL:
WEIGHTS: "detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_C4_3x/137849525/model_final_4ce675.pkl"
DATASETS:
TEST: ("coco_2017_val_100",)
TEST:
EXPECTED_RESULTS: [["bbox", "AP", 47.37, 0.02], ["segm", "AP", 40.99, 0.02]]

14
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/mask_rcnn_R_50_C4_instant_test.yaml Normal file
View File

@@ -0,0 +1,14 @@
_BASE_: "../Base-RCNN-C4.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: True
DATASETS:
TRAIN: ("coco_2017_val_100",)
TEST: ("coco_2017_val_100",)
SOLVER:
BASE_LR: 0.001
STEPS: (30,)
MAX_ITER: 40
IMS_PER_BATCH: 4
DATALOADER:
NUM_WORKERS: 2

22
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/mask_rcnn_R_50_C4_training_acc_test.yaml Normal file
View File

@@ -0,0 +1,22 @@
_BASE_: "../Base-RCNN-C4.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
ROI_HEADS:
BATCH_SIZE_PER_IMAGE: 256
MASK_ON: True
DATASETS:
TRAIN: ("coco_2017_val",)
TEST: ("coco_2017_val",)
INPUT:
MIN_SIZE_TRAIN: (600,)
MAX_SIZE_TRAIN: 1000
MIN_SIZE_TEST: 800
MAX_SIZE_TEST: 1000
SOLVER:
IMS_PER_BATCH: 8 # base uses 16
WARMUP_FACTOR: 0.33333
WARMUP_ITERS: 100
STEPS: (11000, 11600)
MAX_ITER: 12000
TEST:
EXPECTED_RESULTS: [["bbox", "AP", 41.88, 0.7], ["segm", "AP", 33.79, 0.5]]

7
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/mask_rcnn_R_50_DC5_inference_acc_test.yaml Normal file
View File

@@ -0,0 +1,7 @@
_BASE_: "../COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_3x.yaml"
MODEL:
WEIGHTS: "detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_3x/137849551/model_final_84107b.pkl"
DATASETS:
TEST: ("coco_2017_val_100",)
TEST:
EXPECTED_RESULTS: [["bbox", "AP", 47.44, 0.02], ["segm", "AP", 42.94, 0.02]]

10
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/mask_rcnn_R_50_FPN_inference_acc_test.yaml Normal file
View File

@@ -0,0 +1,10 @@
_BASE_: "../COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml"
MODEL:
WEIGHTS: "detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl"
DATASETS:
TEST: ("coco_2017_val_100",)
TEST:
EXPECTED_RESULTS: [["bbox", "AP", 47.34, 0.02], ["segm", "AP", 42.67, 0.02], ["bbox_TTA", "AP", 49.11, 0.02], ["segm_TTA", "AP", 45.04, 0.02]]
AUG:
ENABLED: True
MIN_SIZES: (700, 800) # to save some time

14
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/mask_rcnn_R_50_FPN_instant_test.yaml Normal file
View File

@@ -0,0 +1,14 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: True
DATASETS:
TRAIN: ("coco_2017_val_100",)
TEST: ("coco_2017_val_100",)
SOLVER:
BASE_LR: 0.005
STEPS: (30,)
MAX_ITER: 40
IMS_PER_BATCH: 4
DATALOADER:
NUM_WORKERS: 2

21
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/mask_rcnn_R_50_FPN_training_acc_test.yaml Normal file
View File

@@ -0,0 +1,21 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
ROI_HEADS:
BATCH_SIZE_PER_IMAGE: 256
MASK_ON: True
DATASETS:
TRAIN: ("coco_2017_val",)
TEST: ("coco_2017_val",)
INPUT:
MIN_SIZE_TRAIN: (600,)
MAX_SIZE_TRAIN: 1000
MIN_SIZE_TEST: 800
MAX_SIZE_TEST: 1000
SOLVER:
WARMUP_FACTOR: 0.3333333
WARMUP_ITERS: 100
STEPS: (5500, 5800)
MAX_ITER: 6000
TEST:
EXPECTED_RESULTS: [["bbox", "AP", 42.0, 1.6], ["segm", "AP", 35.4, 1.25]]

7
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/panoptic_fpn_R_50_inference_acc_test.yaml Normal file
View File

@@ -0,0 +1,7 @@
_BASE_: "../COCO-PanopticSegmentation/panoptic_fpn_R_50_3x.yaml"
MODEL:
WEIGHTS: "detectron2://COCO-PanopticSegmentation/panoptic_fpn_R_50_3x/139514569/model_final_c10459.pkl"
DATASETS:
TEST: ("coco_2017_val_100_panoptic_separated",)
TEST:
EXPECTED_RESULTS: [["bbox", "AP", 46.47, 0.02], ["segm", "AP", 43.39, 0.02], ["sem_seg", "mIoU", 42.55, 0.02], ["panoptic_seg", "PQ", 38.99, 0.02]]

19
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/panoptic_fpn_R_50_instant_test.yaml Normal file
View File

@@ -0,0 +1,19 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
META_ARCHITECTURE: "PanopticFPN"
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: True
RESNETS:
DEPTH: 50
SEM_SEG_HEAD:
LOSS_WEIGHT: 0.5
DATASETS:
TRAIN: ("coco_2017_val_100_panoptic_separated",)
TEST: ("coco_2017_val_100_panoptic_separated",)
SOLVER:
BASE_LR: 0.005
STEPS: (30,)
MAX_ITER: 40
IMS_PER_BATCH: 4
DATALOADER:
NUM_WORKERS: 1

20
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/panoptic_fpn_R_50_training_acc_test.yaml Normal file
View File

@@ -0,0 +1,20 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
META_ARCHITECTURE: "PanopticFPN"
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
MASK_ON: True
RESNETS:
DEPTH: 50
SEM_SEG_HEAD:
LOSS_WEIGHT: 0.5
DATASETS:
TRAIN: ("coco_2017_val_panoptic_separated",)
TEST: ("coco_2017_val_panoptic_separated",)
SOLVER:
BASE_LR: 0.01
WARMUP_FACTOR: 0.001
WARMUP_ITERS: 500
STEPS: (5500,)
MAX_ITER: 7000
TEST:
EXPECTED_RESULTS: [["bbox", "AP", 46.70, 1.1], ["segm", "AP", 38.73, 0.7], ["sem_seg", "mIoU", 64.73, 1.2], ["panoptic_seg", "PQ", 48.13, 0.8]]

7
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/retinanet_R_50_FPN_inference_acc_test.yaml Normal file
View File

@@ -0,0 +1,7 @@
_BASE_: "../COCO-Detection/retinanet_R_50_FPN_3x.yaml"
MODEL:
WEIGHTS: "detectron2://COCO-Detection/retinanet_R_50_FPN_3x/137849486/model_final_4cafe0.pkl"
DATASETS:
TEST: ("coco_2017_val_100",)
TEST:
EXPECTED_RESULTS: [["bbox", "AP", 44.36, 0.02]]

13
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/retinanet_R_50_FPN_instant_test.yaml Normal file
View File

@@ -0,0 +1,13 @@
_BASE_: "../COCO-Detection/retinanet_R_50_FPN_1x.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
DATASETS:
TRAIN: ("coco_2017_val_100",)
TEST: ("coco_2017_val_100",)
SOLVER:
BASE_LR: 0.005
STEPS: (30,)
MAX_ITER: 40
IMS_PER_BATCH: 4
DATALOADER:
NUM_WORKERS: 2

7
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/rpn_R_50_FPN_inference_acc_test.yaml Normal file
View File

@@ -0,0 +1,7 @@
_BASE_: "../COCO-Detection/rpn_R_50_FPN_1x.yaml"
MODEL:
WEIGHTS: "detectron2://COCO-Detection/rpn_R_50_FPN_1x/137258492/model_final_02ce48.pkl"
DATASETS:
TEST: ("coco_2017_val_100",)
TEST:
EXPECTED_RESULTS: [["box_proposals", "AR@1000", 58.16, 0.02]]

13
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/rpn_R_50_FPN_instant_test.yaml Normal file
View File

@@ -0,0 +1,13 @@
_BASE_: "../COCO-Detection/rpn_R_50_FPN_1x.yaml"
MODEL:
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
DATASETS:
TRAIN: ("coco_2017_val_100",)
TEST: ("coco_2017_val_100",)
SOLVER:
STEPS: (30,)
MAX_ITER: 40
BASE_LR: 0.005
IMS_PER_BATCH: 4
DATALOADER:
NUM_WORKERS: 2

10
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/semantic_R_50_FPN_inference_acc_test.yaml Normal file
View File

@@ -0,0 +1,10 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
META_ARCHITECTURE: "SemanticSegmentor"
WEIGHTS: "detectron2://semantic_R_50_FPN_1x/111802073/model_final_c18079783c55a94968edc28b7101c5f0.pkl"
RESNETS:
DEPTH: 50
DATASETS:
TEST: ("coco_2017_val_100_panoptic_stuffonly",)
TEST:
EXPECTED_RESULTS: [["sem_seg", "mIoU", 39.53, 0.02], ["sem_seg", "mACC", 51.50, 0.02]]

18
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/semantic_R_50_FPN_instant_test.yaml Normal file
View File

@@ -0,0 +1,18 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
META_ARCHITECTURE: "SemanticSegmentor"
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
RESNETS:
DEPTH: 50
DATASETS:
TRAIN: ("coco_2017_val_100_panoptic_stuffonly",)
TEST: ("coco_2017_val_100_panoptic_stuffonly",)
INPUT:
MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
SOLVER:
BASE_LR: 0.005
STEPS: (30,)
MAX_ITER: 40
IMS_PER_BATCH: 4
DATALOADER:
NUM_WORKERS: 2

20
vton-api/preprocess/humanparsing/mhp_extension/detectron2/configs/quick_schedules/semantic_R_50_FPN_training_acc_test.yaml Normal file
View File

@@ -0,0 +1,20 @@
_BASE_: "../Base-RCNN-FPN.yaml"
MODEL:
META_ARCHITECTURE: "SemanticSegmentor"
WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
RESNETS:
DEPTH: 50
DATASETS:
TRAIN: ("coco_2017_val_panoptic_stuffonly",)
TEST: ("coco_2017_val_panoptic_stuffonly",)
SOLVER:
BASE_LR: 0.01
WARMUP_FACTOR: 0.001
WARMUP_ITERS: 300
STEPS: (5500,)
MAX_ITER: 7000
TEST:
EXPECTED_RESULTS: [["sem_seg", "mIoU", 76.51, 1.0], ["sem_seg", "mACC", 83.25, 1.0]]
INPUT:
# no scale augmentation
MIN_SIZE_TRAIN: (800, )