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

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)