public-data
/

Yet-Another-Anime-Segmenter

Model card Files Files and versions

xet

Community

hysts HF Staff commited on Jan 24, 2022

Commit

3d33f91

1 Parent(s): 97a2fc2

Add files

Browse files

Files changed (3) hide show

README.md +6 -0
SOLOv2.pth +3 -0
SOLOv2.yaml +493 -0

README.md ADDED Viewed

	@@ -0,0 +1,6 @@

+# Yet-Another-Anime-Segmenter
+- Repo: https://github.com/zymk9/Yet-Another-Anime-Segmenter
+    - https://drive.google.com/file/d/1-wFdQ4jwSTeJ7wGD3YKNJdcpSS5Ho8c9/view?usp=sharing
+    - https://raw.githubusercontent.com/zymk9/Yet-Another-Anime-Segmenter/main/configs/SOLOv2.yaml

SOLOv2.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:638a3afc4c8415d2b48cd8e3746df80a3fd83725b3c48a881c304aa197d08887
+size 261510761

SOLOv2.yaml ADDED Viewed

	@@ -0,0 +1,493 @@

+INPUT:
+  FORMAT: BGR
+  MAX_SIZE_TEST: 1600
+  MIN_SIZE_TEST: 800
+MODEL:
+  ANCHOR_GENERATOR:
+    ANGLES:
+    - - -90
+      - 0
+      - 90
+    ASPECT_RATIOS:
+    - - 0.5
+      - 1.0
+      - 2.0
+    NAME: DefaultAnchorGenerator
+    OFFSET: 0.0
+    SIZES:
+    - - 32
+      - 64
+      - 128
+      - 256
+      - 512
+  BACKBONE:
+    ANTI_ALIAS: false
+    FREEZE_AT: 2
+    NAME: build_resnet_fpn_backbone
+  BASIS_MODULE:
+    ANN_SET: coco
+    COMMON_STRIDE: 8
+    CONVS_DIM: 128
+    IN_FEATURES:
+    - p3
+    - p4
+    - p5
+    LOSS_ON: false
+    LOSS_WEIGHT: 0.3
+    NAME: ProtoNet
+    NORM: SyncBN
+    NUM_BASES: 4
+    NUM_CLASSES: 1
+    NUM_CONVS: 3
+  BATEXT:
+    CANONICAL_SIZE: 96
+    CONV_DIM: 256
+    IN_FEATURES:
+    - p2
+    - p3
+    - p4
+    NUM_CHARS: 25
+    NUM_CONV: 2
+    POOLER_RESOLUTION:
+    - 8
+    - 32
+    POOLER_SCALES:
+    - 0.25
+    - 0.125
+    - 0.0625
+    RECOGNITION_LOSS: ctc
+    RECOGNIZER: attn
+    SAMPLING_RATIO: 1
+    VOC_SIZE: 96
+  BLENDMASK:
+    ATTN_SIZE: 14
+    BOTTOM_RESOLUTION: 56
+    INSTANCE_LOSS_WEIGHT: 1.0
+    POOLER_SAMPLING_RATIO: 1
+    POOLER_SCALES:
+    - 0.25
+    POOLER_TYPE: ROIAlignV2
+    TOP_INTERP: bilinear
+    VISUALIZE: false
+  BiFPN:
+    IN_FEATURES:
+    - res2
+    - res3
+    - res4
+    - res5
+    NORM: ''
+    NUM_REPEATS: 6
+    OUT_CHANNELS: 160
+  CONDINST:
+    MASK_BRANCH:
+      CHANNELS: 128
+      IN_FEATURES:
+      - p3
+      - p4
+      - p5
+      NORM: BN
+      NUM_CONVS: 4
+      OUT_CHANNELS: 8
+      SEMANTIC_LOSS_ON: false
+    MASK_HEAD:
+      CHANNELS: 8
+      DISABLE_REL_COORDS: false
+      NUM_LAYERS: 3
+      USE_FP16: false
+    MASK_OUT_STRIDE: 4
+    MAX_PROPOSALS: -1
+  DEVICE: cuda
+  DLA:
+    CONV_BODY: DLA34
+    NORM: FrozenBN
+    OUT_FEATURES:
+    - stage2
+    - stage3
+    - stage4
+    - stage5
+  FCOS:
+    CENTER_SAMPLE: true
+    FPN_STRIDES:
+    - 8
+    - 16
+    - 32
+    - 64
+    - 128
+    INFERENCE_TH_TEST: 0.05
+    INFERENCE_TH_TRAIN: 0.05
+    IN_FEATURES:
+    - p3
+    - p4
+    - p5
+    - p6
+    - p7
+    LOC_LOSS_TYPE: giou
+    LOSS_ALPHA: 0.25
+    LOSS_GAMMA: 2.0
+    NMS_TH: 0.6
+    NORM: GN
+    NUM_BOX_CONVS: 4
+    NUM_CLASSES: 1
+    NUM_CLS_CONVS: 4
+    NUM_SHARE_CONVS: 0
+    POST_NMS_TOPK_TEST: 100
+    POST_NMS_TOPK_TRAIN: 100
+    POS_RADIUS: 1.5
+    PRE_NMS_TOPK_TEST: 1000
+    PRE_NMS_TOPK_TRAIN: 1000
+    PRIOR_PROB: 0.01
+    SIZES_OF_INTEREST:
+    - 64
+    - 128
+    - 256
+    - 512
+    THRESH_WITH_CTR: false
+    TOP_LEVELS: 2
+    USE_DEFORMABLE: false
+    USE_RELU: true
+    USE_SCALE: true
+    YIELD_PROPOSAL: false
+  FPN:
+    FUSE_TYPE: sum
+    IN_FEATURES:
+    - res2
+    - res3
+    - res4
+    - res5
+    NORM: ''
+    OUT_CHANNELS: 256
+  KEYPOINT_ON: false
+  LOAD_PROPOSALS: false
+  MASK_ON: true
+  MEInst:
+    AGNOSTIC: true
+    CENTER_SAMPLE: true
+    DIM_MASK: 60
+    FLAG_PARAMETERS: false
+    FPN_STRIDES:
+    - 8
+    - 16
+    - 32
+    - 64
+    - 128
+    GCN_KERNEL_SIZE: 9
+    INFERENCE_TH_TEST: 0.05
+    INFERENCE_TH_TRAIN: 0.05
+    IN_FEATURES:
+    - p3
+    - p4
+    - p5
+    - p6
+    - p7
+    IOU_LABELS:
+    - 0
+    - 1
+    IOU_THRESHOLDS:
+    - 0.5
+    LAST_DEFORMABLE: false
+    LOC_LOSS_TYPE: giou
+    LOSS_ALPHA: 0.25
+    LOSS_GAMMA: 2.0
+    LOSS_ON_MASK: false
+    MASK_LOSS_TYPE: mse
+    MASK_ON: true
+    MASK_SIZE: 28
+    NMS_TH: 0.6
+    NORM: GN
+    NUM_BOX_CONVS: 4
+    NUM_CLASSES: 1
+    NUM_CLS_CONVS: 4
+    NUM_MASK_CONVS: 4
+    NUM_SHARE_CONVS: 0
+    PATH_COMPONENTS: datasets/coco/components/coco_2017_train_class_agnosticTrue_whitenTrue_sigmoidTrue_60.npz
+    POST_NMS_TOPK_TEST: 100
+    POST_NMS_TOPK_TRAIN: 100
+    POS_RADIUS: 1.5
+    PRE_NMS_TOPK_TEST: 1000
+    PRE_NMS_TOPK_TRAIN: 1000
+    PRIOR_PROB: 0.01
+    SIGMOID: true
+    SIZES_OF_INTEREST:
+    - 64
+    - 128
+    - 256
+    - 512
+    THRESH_WITH_CTR: false
+    TOP_LEVELS: 2
+    TYPE_DEFORMABLE: DCNv1
+    USE_DEFORMABLE: false
+    USE_GCN_IN_MASK: false
+    USE_RELU: true
+    USE_SCALE: true
+    WHITEN: true
+  META_ARCHITECTURE: SOLOv2
+  MOBILENET: false
+  PANOPTIC_FPN:
+    COMBINE:
+      ENABLED: true
+      INSTANCES_CONFIDENCE_THRESH: 0.5
+      OVERLAP_THRESH: 0.5
+      STUFF_AREA_LIMIT: 4096
+    INSTANCE_LOSS_WEIGHT: 1.0
+  PIXEL_MEAN:
+  - 103.53
+  - 116.28
+  - 123.675
+  PIXEL_STD:
+  - 1.0
+  - 1.0
+  - 1.0
+  PROPOSAL_GENERATOR:
+    MIN_SIZE: 0
+    NAME: RPN
+  RESNETS:
+    DEFORM_INTERVAL: 1
+    DEFORM_MODULATED: false
+    DEFORM_NUM_GROUPS: 1
+    DEFORM_ON_PER_STAGE:
+    - false
+    - false
+    - false
+    - false
+    DEPTH: 101
+    NORM: FrozenBN
+    NUM_GROUPS: 1
+    OUT_FEATURES:
+    - res2
+    - res3
+    - res4
+    - res5
+    RES2_OUT_CHANNELS: 256
+    RES5_DILATION: 1
+    STEM_OUT_CHANNELS: 64
+    STRIDE_IN_1X1: true
+    WIDTH_PER_GROUP: 64
+  RETINANET:
+    BBOX_REG_LOSS_TYPE: smooth_l1
+    BBOX_REG_WEIGHTS:
+    - 1.0
+    - 1.0
+    - 1.0
+    - 1.0
+    FOCAL_LOSS_ALPHA: 0.25
+    FOCAL_LOSS_GAMMA: 2.0
+    IN_FEATURES:
+    - p3
+    - p4
+    - p5
+    - p6
+    - p7
+    IOU_LABELS:
+    - 0
+    - -1
+    - 1
+    IOU_THRESHOLDS:
+    - 0.4
+    - 0.5
+    NMS_THRESH_TEST: 0.5
+    NORM: ''
+    NUM_CLASSES: 1
+    NUM_CONVS: 4
+    PRIOR_PROB: 0.01
+    SCORE_THRESH_TEST: 0.05
+    SMOOTH_L1_LOSS_BETA: 0.1
+    TOPK_CANDIDATES_TEST: 1000
+  ROI_BOX_CASCADE_HEAD:
+    BBOX_REG_WEIGHTS:
+    - - 10.0
+      - 10.0
+      - 5.0
+      - 5.0
+    - - 20.0
+      - 20.0
+      - 10.0
+      - 10.0
+    - - 30.0
+      - 30.0
+      - 15.0
+      - 15.0
+    IOUS:
+    - 0.5
+    - 0.6
+    - 0.7
+  ROI_BOX_HEAD:
+    BBOX_REG_LOSS_TYPE: smooth_l1
+    BBOX_REG_LOSS_WEIGHT: 1.0
+    BBOX_REG_WEIGHTS:
+    - 10.0
+    - 10.0
+    - 5.0
+    - 5.0
+    CLS_AGNOSTIC_BBOX_REG: false
+    CONV_DIM: 256
+    FC_DIM: 1024
+    NAME: ''
+    NORM: ''
+    NUM_CONV: 0
+    NUM_FC: 0
+    POOLER_RESOLUTION: 14
+    POOLER_SAMPLING_RATIO: 0
+    POOLER_TYPE: ROIAlignV2
+    SMOOTH_L1_BETA: 0.0
+    TRAIN_ON_PRED_BOXES: false
+  ROI_HEADS:
+    BATCH_SIZE_PER_IMAGE: 512
+    IN_FEATURES:
+    - res4
+    IOU_LABELS:
+    - 0
+    - 1
+    IOU_THRESHOLDS:
+    - 0.5
+    NAME: Res5ROIHeads
+    NMS_THRESH_TEST: 0.5
+    NUM_CLASSES: 1
+    POSITIVE_FRACTION: 0.25
+    PROPOSAL_APPEND_GT: true
+    SCORE_THRESH_TEST: 0.05
+  ROI_KEYPOINT_HEAD:
+    CONV_DIMS:
+    - 512
+    - 512
+    - 512
+    - 512
+    - 512
+    - 512
+    - 512
+    - 512
+    LOSS_WEIGHT: 1.0
+    MIN_KEYPOINTS_PER_IMAGE: 1
+    NAME: KRCNNConvDeconvUpsampleHead
+    NORMALIZE_LOSS_BY_VISIBLE_KEYPOINTS: true
+    NUM_KEYPOINTS: 17
+    POOLER_RESOLUTION: 14
+    POOLER_SAMPLING_RATIO: 0
+    POOLER_TYPE: ROIAlignV2
+  ROI_MASK_HEAD:
+    CLS_AGNOSTIC_MASK: false
+    CONV_DIM: 256
+    NAME: MaskRCNNConvUpsampleHead
+    NORM: ''
+    NUM_CONV: 0
+    POOLER_RESOLUTION: 14
+    POOLER_SAMPLING_RATIO: 0
+    POOLER_TYPE: ROIAlignV2
+  RPN:
+    BATCH_SIZE_PER_IMAGE: 256
+    BBOX_REG_LOSS_TYPE: smooth_l1
+    BBOX_REG_LOSS_WEIGHT: 1.0
+    BBOX_REG_WEIGHTS:
+    - 1.0
+    - 1.0
+    - 1.0
+    - 1.0
+    BOUNDARY_THRESH: -1
+    HEAD_NAME: StandardRPNHead
+    IN_FEATURES:
+    - res4
+    IOU_LABELS:
+    - 0
+    - -1
+    - 1
+    IOU_THRESHOLDS:
+    - 0.3
+    - 0.7
+    LOSS_WEIGHT: 1.0
+    NMS_THRESH: 0.7
+    POSITIVE_FRACTION: 0.5
+    POST_NMS_TOPK_TEST: 1000
+    POST_NMS_TOPK_TRAIN: 2000
+    PRE_NMS_TOPK_TEST: 6000
+    PRE_NMS_TOPK_TRAIN: 12000
+    SMOOTH_L1_BETA: 0.0
+  SEM_SEG_HEAD:
+    COMMON_STRIDE: 4
+    CONVS_DIM: 128
+    IGNORE_VALUE: 255
+    IN_FEATURES:
+    - p2
+    - p3
+    - p4
+    - p5
+    LOSS_WEIGHT: 1.0
+    NAME: SemSegFPNHead
+    NORM: GN
+    NUM_CLASSES: 1
+  SOLOV2:
+    FPN_INSTANCE_STRIDES:
+    - 8
+    - 8
+    - 16
+    - 32
+    - 32
+    FPN_SCALE_RANGES:
+    - - 1
+      - 96
+    - - 48
+      - 192
+    - - 96
+      - 384
+    - - 192
+      - 768
+    - - 384
+      - 2048
+    INSTANCE_CHANNELS: 512
+    INSTANCE_IN_CHANNELS: 256
+    INSTANCE_IN_FEATURES:
+    - p2
+    - p3
+    - p4
+    - p5
+    - p6
+    LOSS:
+      DICE_WEIGHT: 3.0
+      FOCAL_ALPHA: 0.25
+      FOCAL_GAMMA: 2.0
+      FOCAL_USE_SIGMOID: true
+      FOCAL_WEIGHT: 1.0
+    MASK_CHANNELS: 128
+    MASK_IN_CHANNELS: 256
+    MASK_IN_FEATURES:
+    - p2
+    - p3
+    - p4
+    - p5
+    MASK_THR: 0.5
+    MAX_PER_IMG: 100
+    NMS_KERNEL: gaussian
+    NMS_PRE: 500
+    NMS_SIGMA: 2
+    NMS_TYPE: mask
+    NORM: GN
+    NUM_CLASSES: 1
+    NUM_GRIDS:
+    - 40
+    - 36
+    - 24
+    - 16
+    - 12
+    NUM_INSTANCE_CONVS: 4
+    NUM_KERNELS: 256
+    NUM_MASKS: 256
+    PRIOR_PROB: 0.01
+    SCORE_THR: 0.1
+    SIGMA: 0.2
+    TYPE_DCN: DCN
+    UPDATE_THR: 0.05
+    USE_COORD_CONV: true
+    USE_DCN_IN_INSTANCE: false
+  TOP_MODULE:
+    DIM: 16
+    NAME: conv
+  VOVNET:
+    BACKBONE_OUT_CHANNELS: 256
+    CONV_BODY: V-39-eSE
+    NORM: FrozenBN
+    OUT_CHANNELS: 256
+    OUT_FEATURES:
+    - stage2
+    - stage3
+    - stage4
+    - stage5
+  WEIGHTS: SOLOv2.pth
+VERSION: 2