Add application file

.gitignore

@@ -0,0 +1 @@
+*.pyc

Dockerfile

@@ -0,0 +1,14 @@
+# read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+# you will also find guides on how best to write your Dockerfile
+
+FROM python:3.9
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+COPY . .
+
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -1,10 +1,14 @@
 ---
-title: Viton Idm
-emoji: 😻
-colorFrom: blue
-colorTo: purple
-sdk: docker
+title: IDM VTON
+emoji: 👕👔👚
+colorFrom: yellow
+colorTo: red
+sdk: gradio
+sdk_version: 4.24.0
+app_file: app.py
 pinned: false
+license: cc-by-nc-sa-4.0
+short_description: High-fidelity Virtual Try-on
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app/main.py

@@ -0,0 +1,117 @@
+from flask import Flask, request, jsonify
+import torch
+from transformers import AutoTokenizer
+from src.tryon_pipeline import StableDiffusionXLInpaintPipeline as TryonPipeline
+from src.unet_hacked_garmnet import UNet2DConditionModel as UNet2DConditionModel_ref
+from src.unet_hacked_tryon import UNet2DConditionModel
+from PIL import Image
+import numpy as np
+import os
+
+app = Flask(__name__)
+
+# Load models and tokenizers
+unet = UNet2DConditionModel.from_pretrained(
+    'yisol/IDM-VTON',
+    subfolder="unet",
+    torch_dtype=torch.float16,
+)
+unet.requires_grad_(False)
+
+tokenizer_one = AutoTokenizer.from_pretrained(
+    'yisol/IDM-VTON',
+    subfolder="tokenizer",
+    revision=None,
+    use_fast=False,
+)
+tokenizer_two = AutoTokenizer.from_pretrained(
+    'yisol/IDM-VTON',
+    subfolder="tokenizer_2",
+    revision=None,
+    use_fast=False,
+)
+
+noise_scheduler = DDPMScheduler.from_pretrained('yisol/IDM-VTON', subfolder="scheduler")
+
+text_encoder_one = CLIPTextModel.from_pretrained(
+    'yisol/IDM-VTON',
+    subfolder="text_encoder",
+    torch_dtype=torch.float16,
+)
+text_encoder_two = CLIPTextModelWithProjection.from_pretrained(
+    'yisol/IDM-VTON',
+    subfolder="text_encoder_2",
+    torch_dtype=torch.float16,
+)
+image_encoder = CLIPVisionModelWithProjection.from_pretrained(
+    'yisol/IDM-VTON',
+    subfolder="image_encoder",
+    torch_dtype=torch.float16,
+)
+vae = AutoencoderKL.from_pretrained('yisol/IDM-VTON', subfolder="vae", torch_dtype=torch.float16,)
+
+UNet_Encoder = UNet2DConditionModel_ref.from_pretrained(
+    'yisol/IDM-VTON',
+    subfolder="unet_encoder",
+    torch_dtype=torch.float16,
+)
+UNet_Encoder.requires_grad_(False)
+
+parsing_model = Parsing(0)
+openpose_model = OpenPose(0)
+
+pipe = TryonPipeline.from_pretrained(
+    'yisol/IDM-VTON',
+    unet=unet,
+    vae=vae,
+    feature_extractor=CLIPImageProcessor(),
+    text_encoder=text_encoder_one,
+    text_encoder_2=text_encoder_two,
+    tokenizer=tokenizer_one,
+    tokenizer_2=tokenizer_two,
+    scheduler=noise_scheduler,
+    image_encoder=image_encoder,
+    torch_dtype=torch.float16,
+)
+pipe.unet_encoder = UNet_Encoder
+from fastapi import APIRouter, UploadFile, HTTPException
+from PIL import Image
+from io import BytesIO
+import numpy as np
+from service.core.schema.output import APIOutput
+
+tryon_router = APIRouter()
+
+@tryon_router.post("/tryon", response_model=APIOutput)
+async def tryon(human_img: UploadFile, garm_img: UploadFile, garment_des: str, is_checked: bool, is_checked_crop: bool, denoise_steps: int, seed: int):
+    # Check whether the uploaded files are images
+    if human_img.filename.split(".")[-1] not in ("jpg", "jpeg", "png"):
+        raise HTTPException(status_code=415, detail="Human image is not an image")
+    if garm_img.filename.split(".")[-1] not in ("jpg", "jpeg", "png"):
+        raise HTTPException(status_code=415, detail="Garment image is not an image")
+
+    # Open and process the images
+    human_image = Image.open(BytesIO(human_img.file.read()))
+    garm_image = Image.open(BytesIO(garm_img.file.read()))
+
+    # Run the try-on pipeline
+    output, masked_img = start_tryon(
+        dict({"background": human_image}),
+        garm_image,
+        garment_des,
+        is_checked,
+        is_checked_crop,
+        denoise_steps,
+        seed,
+    )
+
+    # Convert the output image to bytes
+    output_bytes = BytesIO()
+    output.save(output_bytes, format="PNG")
+    output_bytes.seek(0)
+
+    # Return the output image as a response
+    return {
+        "output_img": output_bytes.read(),
+        "masked_img": BytesIO(masked_img).read(),
+    }

apply_net.py

@@ -0,0 +1,359 @@
+#!/usr/bin/env python3
+# Copyright (c) Facebook, Inc. and its affiliates.
+
+import argparse
+import glob
+import logging
+import os
+import sys
+from typing import Any, ClassVar, Dict, List
+import torch
+
+from detectron2.config import CfgNode, get_cfg
+from detectron2.data.detection_utils import read_image
+from detectron2.engine.defaults import DefaultPredictor
+from detectron2.structures.instances import Instances
+from detectron2.utils.logger import setup_logger
+
+from densepose import add_densepose_config
+from densepose.structures import DensePoseChartPredictorOutput, DensePoseEmbeddingPredictorOutput
+from densepose.utils.logger import verbosity_to_level
+from densepose.vis.base import CompoundVisualizer
+from densepose.vis.bounding_box import ScoredBoundingBoxVisualizer
+from densepose.vis.densepose_outputs_vertex import (
+    DensePoseOutputsTextureVisualizer,
+    DensePoseOutputsVertexVisualizer,
+    get_texture_atlases,
+)
+from densepose.vis.densepose_results import (
+    DensePoseResultsContourVisualizer,
+    DensePoseResultsFineSegmentationVisualizer,
+    DensePoseResultsUVisualizer,
+    DensePoseResultsVVisualizer,
+)
+from densepose.vis.densepose_results_textures import (
+    DensePoseResultsVisualizerWithTexture,
+    get_texture_atlas,
+)
+from densepose.vis.extractor import (
+    CompoundExtractor,
+    DensePoseOutputsExtractor,
+    DensePoseResultExtractor,
+    create_extractor,
+)
+
+DOC = """Apply Net - a tool to print / visualize DensePose results
+"""
+
+LOGGER_NAME = "apply_net"
+logger = logging.getLogger(LOGGER_NAME)
+
+_ACTION_REGISTRY: Dict[str, "Action"] = {}
+
+
+class Action:
+    @classmethod
+    def add_arguments(cls: type, parser: argparse.ArgumentParser):
+        parser.add_argument(
+            "-v",
+            "--verbosity",
+            action="count",
+            help="Verbose mode. Multiple -v options increase the verbosity.",
+        )
+
+
+def register_action(cls: type):
+    """
+    Decorator for action classes to automate action registration
+    """
+    global _ACTION_REGISTRY
+    _ACTION_REGISTRY[cls.COMMAND] = cls
+    return cls
+
+
+class InferenceAction(Action):
+    @classmethod
+    def add_arguments(cls: type, parser: argparse.ArgumentParser):
+        super(InferenceAction, cls).add_arguments(parser)
+        parser.add_argument("cfg", metavar="<config>", help="Config file")
+        parser.add_argument("model", metavar="<model>", help="Model file")
+        parser.add_argument(
+            "--opts",
+            help="Modify config options using the command-line 'KEY VALUE' pairs",
+            default=[],
+            nargs=argparse.REMAINDER,
+        )
+
+    @classmethod
+    def execute(cls: type, args: argparse.Namespace, human_img):
+        logger.info(f"Loading config from {args.cfg}")
+        opts = []
+        cfg = cls.setup_config(args.cfg, args.model, args, opts)
+        logger.info(f"Loading model from {args.model}")
+        predictor = DefaultPredictor(cfg)
+        # logger.info(f"Loading data from {args.input}")
+        # file_list = cls._get_input_file_list(args.input)
+        # if len(file_list) == 0:
+        #     logger.warning(f"No input images for {args.input}")
+        #     return
+        context = cls.create_context(args, cfg)
+        # for file_name in file_list:
+        #     img = read_image(file_name, format="BGR")  # predictor expects BGR image.
+        with torch.no_grad():
+            outputs = predictor(human_img)["instances"]
+            out_pose = cls.execute_on_outputs(context, {"image": human_img}, outputs)
+        cls.postexecute(context)
+        return out_pose
+
+    @classmethod
+    def setup_config(
+        cls: type, config_fpath: str, model_fpath: str, args: argparse.Namespace, opts: List[str]
+    ):
+        cfg = get_cfg()
+        add_densepose_config(cfg)
+        cfg.merge_from_file(config_fpath)
+        cfg.merge_from_list(args.opts)
+        if opts:
+            cfg.merge_from_list(opts)
+        cfg.MODEL.WEIGHTS = model_fpath
+        cfg.freeze()
+        return cfg
+
+    @classmethod
+    def _get_input_file_list(cls: type, input_spec: str):
+        if os.path.isdir(input_spec):
+            file_list = [
+                os.path.join(input_spec, fname)
+                for fname in os.listdir(input_spec)
+                if os.path.isfile(os.path.join(input_spec, fname))
+            ]
+        elif os.path.isfile(input_spec):
+            file_list = [input_spec]
+        else:
+            file_list = glob.glob(input_spec)
+        return file_list
+
+
+@register_action
+class DumpAction(InferenceAction):
+    """
+    Dump action that outputs results to a pickle file
+    """
+
+    COMMAND: ClassVar[str] = "dump"
+
+    @classmethod
+    def add_parser(cls: type, subparsers: argparse._SubParsersAction):
+        parser = subparsers.add_parser(cls.COMMAND, help="Dump model outputs to a file.")
+        cls.add_arguments(parser)
+        parser.set_defaults(func=cls.execute)
+
+    @classmethod
+    def add_arguments(cls: type, parser: argparse.ArgumentParser):
+        super(DumpAction, cls).add_arguments(parser)
+        parser.add_argument(
+            "--output",
+            metavar="<dump_file>",
+            default="results.pkl",
+            help="File name to save dump to",
+        )
+
+    @classmethod
+    def execute_on_outputs(
+        cls: type, context: Dict[str, Any], entry: Dict[str, Any], outputs: Instances
+    ):
+        image_fpath = entry["file_name"]
+        logger.info(f"Processing {image_fpath}")
+        result = {"file_name": image_fpath}
+        if outputs.has("scores"):
+            result["scores"] = outputs.get("scores").cpu()
+        if outputs.has("pred_boxes"):
+            result["pred_boxes_XYXY"] = outputs.get("pred_boxes").tensor.cpu()
+            if outputs.has("pred_densepose"):
+                if isinstance(outputs.pred_densepose, DensePoseChartPredictorOutput):
+                    extractor = DensePoseResultExtractor()
+                elif isinstance(outputs.pred_densepose, DensePoseEmbeddingPredictorOutput):
+                    extractor = DensePoseOutputsExtractor()
+                result["pred_densepose"] = extractor(outputs)[0]
+        context["results"].append(result)
+
+    @classmethod
+    def create_context(cls: type, args: argparse.Namespace, cfg: CfgNode):
+        context = {"results": [], "out_fname": args.output}
+        return context
+
+    @classmethod
+    def postexecute(cls: type, context: Dict[str, Any]):
+        out_fname = context["out_fname"]
+        out_dir = os.path.dirname(out_fname)
+        if len(out_dir) > 0 and not os.path.exists(out_dir):
+            os.makedirs(out_dir)
+        with open(out_fname, "wb") as hFile:
+            torch.save(context["results"], hFile)
+            logger.info(f"Output saved to {out_fname}")
+
+
+@register_action
+class ShowAction(InferenceAction):
+    """
+    Show action that visualizes selected entries on an image
+    """
+
+    COMMAND: ClassVar[str] = "show"
+    VISUALIZERS: ClassVar[Dict[str, object]] = {
+        "dp_contour": DensePoseResultsContourVisualizer,
+        "dp_segm": DensePoseResultsFineSegmentationVisualizer,
+        "dp_u": DensePoseResultsUVisualizer,
+        "dp_v": DensePoseResultsVVisualizer,
+        "dp_iuv_texture": DensePoseResultsVisualizerWithTexture,
+        "dp_cse_texture": DensePoseOutputsTextureVisualizer,
+        "dp_vertex": DensePoseOutputsVertexVisualizer,
+        "bbox": ScoredBoundingBoxVisualizer,
+    }
+
+    @classmethod
+    def add_parser(cls: type, subparsers: argparse._SubParsersAction):
+        parser = subparsers.add_parser(cls.COMMAND, help="Visualize selected entries")
+        cls.add_arguments(parser)
+        parser.set_defaults(func=cls.execute)
+
+    @classmethod
+    def add_arguments(cls: type, parser: argparse.ArgumentParser):
+        super(ShowAction, cls).add_arguments(parser)
+        parser.add_argument(
+            "visualizations",
+            metavar="<visualizations>",
+            help="Comma separated list of visualizations, possible values: "
+            "[{}]".format(",".join(sorted(cls.VISUALIZERS.keys()))),
+        )
+        parser.add_argument(
+            "--min_score",
+            metavar="<score>",
+            default=0.8,
+            type=float,
+            help="Minimum detection score to visualize",
+        )
+        parser.add_argument(
+            "--nms_thresh", metavar="<threshold>", default=None, type=float, help="NMS threshold"
+        )
+        parser.add_argument(
+            "--texture_atlas",
+            metavar="<texture_atlas>",
+            default=None,
+            help="Texture atlas file (for IUV texture transfer)",
+        )
+        parser.add_argument(
+            "--texture_atlases_map",
+            metavar="<texture_atlases_map>",
+            default=None,
+            help="JSON string of a dict containing texture atlas files for each mesh",
+        )
+        parser.add_argument(
+            "--output",
+            metavar="<image_file>",
+            default="outputres.png",
+            help="File name to save output to",
+        )
+
+    @classmethod
+    def setup_config(
+        cls: type, config_fpath: str, model_fpath: str, args: argparse.Namespace, opts: List[str]
+    ):
+        opts.append("MODEL.ROI_HEADS.SCORE_THRESH_TEST")
+        opts.append(str(args.min_score))
+        if args.nms_thresh is not None:
+            opts.append("MODEL.ROI_HEADS.NMS_THRESH_TEST")
+            opts.append(str(args.nms_thresh))
+        cfg = super(ShowAction, cls).setup_config(config_fpath, model_fpath, args, opts)
+        return cfg
+
+    @classmethod
+    def execute_on_outputs(
+        cls: type, context: Dict[str, Any], entry: Dict[str, Any], outputs: Instances
+    ):
+        import cv2
+        import numpy as np
+        visualizer = context["visualizer"]
+        extractor = context["extractor"]
+        # image_fpath = entry["file_name"]
+        # logger.info(f"Processing {image_fpath}")
+        image = cv2.cvtColor(entry["image"], cv2.COLOR_BGR2GRAY)
+        image = np.tile(image[:, :, np.newaxis], [1, 1, 3])
+        data = extractor(outputs)
+        image_vis = visualizer.visualize(image, data)
+
+        return image_vis
+        entry_idx = context["entry_idx"] + 1
+        out_fname = './image-densepose/' + image_fpath.split('/')[-1]
+        out_dir = './image-densepose'
+        out_dir = os.path.dirname(out_fname)
+        if len(out_dir) > 0 and not os.path.exists(out_dir):
+            os.makedirs(out_dir)
+        cv2.imwrite(out_fname, image_vis)
+        logger.info(f"Output saved to {out_fname}")
+        context["entry_idx"] += 1
+
+    @classmethod
+    def postexecute(cls: type, context: Dict[str, Any]):
+        pass
+# python ./apply_net.py show ./configs/densepose_rcnn_R_50_FPN_s1x.yaml https://dl.fbaipublicfiles.com/densepose/densepose_rcnn_R_50_FPN_s1x/165712039/model_final_162be9.pkl /home/alin0222/DressCode/upper_body/images dp_segm -v --opts MODEL.DEVICE cpu
+
+    @classmethod
+    def _get_out_fname(cls: type, entry_idx: int, fname_base: str):
+        base, ext = os.path.splitext(fname_base)
+        return base + ".{0:04d}".format(entry_idx) + ext
+
+    @classmethod
+    def create_context(cls: type, args: argparse.Namespace, cfg: CfgNode) -> Dict[str, Any]:
+        vis_specs = args.visualizations.split(",")
+        visualizers = []
+        extractors = []
+        for vis_spec in vis_specs:
+            texture_atlas = get_texture_atlas(args.texture_atlas)
+            texture_atlases_dict = get_texture_atlases(args.texture_atlases_map)
+            vis = cls.VISUALIZERS[vis_spec](
+                cfg=cfg,
+                texture_atlas=texture_atlas,
+                texture_atlases_dict=texture_atlases_dict,
+            )
+            visualizers.append(vis)
+            extractor = create_extractor(vis)
+            extractors.append(extractor)
+        visualizer = CompoundVisualizer(visualizers)
+        extractor = CompoundExtractor(extractors)
+        context = {
+            "extractor": extractor,
+            "visualizer": visualizer,
+            "out_fname": args.output,
+            "entry_idx": 0,
+        }
+        return context
+
+
+def create_argument_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(
+        description=DOC,
+        formatter_class=lambda prog: argparse.HelpFormatter(prog, max_help_position=120),
+    )
+    parser.set_defaults(func=lambda _: parser.print_help(sys.stdout))
+    subparsers = parser.add_subparsers(title="Actions")
+    for _, action in _ACTION_REGISTRY.items():
+        action.add_parser(subparsers)
+    return parser
+
+
+def main():
+    parser = create_argument_parser()
+    args = parser.parse_args()
+    verbosity = getattr(args, "verbosity", None)
+    global logger
+    logger = setup_logger(name=LOGGER_NAME)
+    logger.setLevel(verbosity_to_level(verbosity))
+    args.func(args)
+
+
+if __name__ == "__main__":
+    main()
+
+
+# python ./apply_net.py show ./configs/densepose_rcnn_R_50_FPN_s1x.yaml https://dl.fbaipublicfiles.com/densepose/densepose_rcnn_R_50_FPN_s1x/165712039/model_final_162be9.pkl /home/alin0222/Dresscode/dresses/humanonly dp_segm -v --opts MODEL.DEVICE cuda

configs/Base-DensePose-RCNN-FPN.yaml

@@ -0,0 +1,48 @@
+VERSION: 2
+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
+
+  DENSEPOSE_ON: True
+  ROI_HEADS:
+    NAME: "DensePoseROIHeads"
+    IN_FEATURES: ["p2", "p3", "p4", "p5"]
+    NUM_CLASSES: 1
+  ROI_BOX_HEAD:
+    NAME: "FastRCNNConvFCHead"
+    NUM_FC: 2
+    POOLER_RESOLUTION: 7
+    POOLER_SAMPLING_RATIO: 2
+    POOLER_TYPE: "ROIAlign"
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    POOLER_TYPE: "ROIAlign"
+    NUM_COARSE_SEGM_CHANNELS: 2
+DATASETS:
+  TRAIN: ("densepose_coco_2014_train", "densepose_coco_2014_valminusminival")
+  TEST: ("densepose_coco_2014_minival",)
+SOLVER:
+  IMS_PER_BATCH: 16
+  BASE_LR: 0.01
+  STEPS: (60000, 80000)
+  MAX_ITER: 90000
+  WARMUP_FACTOR: 0.1
+INPUT:
+  MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)

configs/HRNet/densepose_rcnn_HRFPN_HRNet_w32_s1x.yaml

@@ -0,0 +1,16 @@
+_BASE_: "../Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "https://1drv.ms/u/s!Aus8VCZ_C_33dYBMemi9xOUFR0w"
+  BACKBONE:
+    NAME: "build_hrfpn_backbone"
+  RPN:
+    IN_FEATURES: ['p1', 'p2', 'p3', 'p4', 'p5']
+  ROI_HEADS:
+    IN_FEATURES: ['p1', 'p2', 'p3', 'p4', 'p5']
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)
+  CLIP_GRADIENTS:
+    ENABLED: True
+    CLIP_TYPE: "norm"
+  BASE_LR: 0.03

configs/HRNet/densepose_rcnn_HRFPN_HRNet_w40_s1x.yaml

@@ -0,0 +1,23 @@
+_BASE_: "../Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "https://1drv.ms/u/s!Aus8VCZ_C_33ck0gvo5jfoWBOPo"
+  BACKBONE:
+    NAME: "build_hrfpn_backbone"
+  RPN:
+    IN_FEATURES: ['p1', 'p2', 'p3', 'p4', 'p5']
+  ROI_HEADS:
+    IN_FEATURES: ['p1', 'p2', 'p3', 'p4', 'p5']
+  HRNET:
+    STAGE2:
+      NUM_CHANNELS: [40, 80]
+    STAGE3:
+      NUM_CHANNELS: [40, 80, 160]
+    STAGE4:
+      NUM_CHANNELS: [40, 80, 160, 320]
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)
+  CLIP_GRADIENTS:
+    ENABLED: True
+    CLIP_TYPE: "norm"
+  BASE_LR: 0.03

configs/HRNet/densepose_rcnn_HRFPN_HRNet_w48_s1x.yaml

@@ -0,0 +1,23 @@
+_BASE_: "../Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "https://1drv.ms/u/s!Aus8VCZ_C_33dKvqI6pBZlifgJk"
+  BACKBONE:
+    NAME: "build_hrfpn_backbone"
+  RPN:
+    IN_FEATURES: ['p1', 'p2', 'p3', 'p4', 'p5']
+  ROI_HEADS:
+    IN_FEATURES: ['p1', 'p2', 'p3', 'p4', 'p5']
+  HRNET:
+    STAGE2:
+      NUM_CHANNELS: [48, 96]
+    STAGE3:
+      NUM_CHANNELS: [48, 96, 192]
+    STAGE4:
+      NUM_CHANNELS: [48, 96, 192, 384]
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)
+  CLIP_GRADIENTS:
+    ENABLED: True
+    CLIP_TYPE: "norm"
+  BASE_LR: 0.03

configs/cse/Base-DensePose-RCNN-FPN-Human.yaml

@@ -0,0 +1,20 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  ROI_DENSEPOSE_HEAD:
+    CSE:
+      EMBEDDERS:
+        "smpl_27554":
+          TYPE: vertex_feature
+          NUM_VERTICES: 27554
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_smpl_27554_256.pkl"
+DATASETS:
+  TRAIN:
+    - "densepose_coco_2014_train_cse"
+    - "densepose_coco_2014_valminusminival_cse"
+  TEST:
+    - "densepose_coco_2014_minival_cse"
+  CLASS_TO_MESH_NAME_MAPPING:
+    "0": "smpl_27554"

configs/cse/Base-DensePose-RCNN-FPN.yaml

@@ -0,0 +1,60 @@
+VERSION: 2
+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
+
+  DENSEPOSE_ON: True
+  ROI_HEADS:
+    NAME: "DensePoseROIHeads"
+    IN_FEATURES: ["p2", "p3", "p4", "p5"]
+    NUM_CLASSES: 1
+  ROI_BOX_HEAD:
+    NAME: "FastRCNNConvFCHead"
+    NUM_FC: 2
+    POOLER_RESOLUTION: 7
+    POOLER_SAMPLING_RATIO: 2
+    POOLER_TYPE: "ROIAlign"
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    POOLER_TYPE: "ROIAlign"
+    NUM_COARSE_SEGM_CHANNELS: 2
+    PREDICTOR_NAME: "DensePoseEmbeddingPredictor"
+    LOSS_NAME: "DensePoseCseLoss"
+    CSE:
+      # embedding loss, possible values:
+      # - "EmbeddingLoss"
+      # - "SoftEmbeddingLoss"
+      EMBED_LOSS_NAME: "EmbeddingLoss"
+SOLVER:
+  IMS_PER_BATCH: 16
+  BASE_LR: 0.01
+  STEPS: (60000, 80000)
+  MAX_ITER: 90000
+  WARMUP_FACTOR: 0.1
+  CLIP_GRADIENTS:
+    CLIP_TYPE: norm
+    CLIP_VALUE: 1.0
+    ENABLED: true
+    NORM_TYPE: 2.0
+INPUT:
+  MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
+DENSEPOSE_EVALUATION:
+  TYPE: cse
+  STORAGE: file

configs/cse/densepose_rcnn_R_101_FPN_DL_s1x.yaml

@@ -0,0 +1,12 @@
+_BASE_: "Base-DensePose-RCNN-FPN-Human.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    CSE:
+      EMBED_LOSS_NAME: "EmbeddingLoss"
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/cse/densepose_rcnn_R_101_FPN_DL_soft_s1x.yaml

@@ -0,0 +1,12 @@
+_BASE_: "Base-DensePose-RCNN-FPN-Human.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    CSE:
+      EMBED_LOSS_NAME: "SoftEmbeddingLoss"
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/cse/densepose_rcnn_R_101_FPN_s1x.yaml

@@ -0,0 +1,12 @@
+_BASE_: "Base-DensePose-RCNN-FPN-Human.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    CSE:
+      EMBED_LOSS_NAME: "EmbeddingLoss"
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/cse/densepose_rcnn_R_101_FPN_soft_s1x.yaml

@@ -0,0 +1,12 @@
+_BASE_: "Base-DensePose-RCNN-FPN-Human.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    CSE:
+      EMBED_LOSS_NAME: "SoftEmbeddingLoss"
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/cse/densepose_rcnn_R_50_FPN_DL_s1x.yaml

@@ -0,0 +1,12 @@
+_BASE_: "Base-DensePose-RCNN-FPN-Human.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    CSE:
+      EMBED_LOSS_NAME: "EmbeddingLoss"
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/cse/densepose_rcnn_R_50_FPN_DL_soft_s1x.yaml

@@ -0,0 +1,12 @@
+_BASE_: "Base-DensePose-RCNN-FPN-Human.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    CSE:
+      EMBED_LOSS_NAME: "SoftEmbeddingLoss"
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/cse/densepose_rcnn_R_50_FPN_s1x.yaml

@@ -0,0 +1,12 @@
+_BASE_: "Base-DensePose-RCNN-FPN-Human.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    CSE:
+      EMBED_LOSS_NAME: "EmbeddingLoss"
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/cse/densepose_rcnn_R_50_FPN_soft_animals_CA_finetune_16k.yaml

@@ -0,0 +1,133 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/cse/densepose_rcnn_R_50_FPN_soft_s1x/250533982/model_final_2c4512.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_HEADS:
+    NUM_CLASSES: 1
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    COARSE_SEGM_TRAINED_BY_MASKS: True
+    CSE:
+      EMBED_LOSS_NAME: "SoftEmbeddingLoss"
+      EMBEDDING_DIST_GAUSS_SIGMA: 0.1
+      GEODESIC_DIST_GAUSS_SIGMA: 0.1
+      EMBEDDERS:
+        "cat_7466":
+          TYPE: vertex_feature
+          NUM_VERTICES: 7466
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cat_7466_256.pkl"
+        "dog_7466":
+          TYPE: vertex_feature
+          NUM_VERTICES: 7466
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_dog_7466_256.pkl"
+        "sheep_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_sheep_5004_256.pkl"
+        "horse_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_horse_5004_256.pkl"
+        "zebra_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_zebra_5002_256.pkl"
+        "giraffe_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_giraffe_5002_256.pkl"
+        "elephant_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_elephant_5002_256.pkl"
+        "cow_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cow_5002_256.pkl"
+        "bear_4936":
+          TYPE: vertex_feature
+          NUM_VERTICES: 4936
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_bear_4936_256.pkl"
+DATASETS:
+  TRAIN:
+    - "densepose_lvis_v1_ds2_train_v1"
+  TEST:
+    - "densepose_lvis_v1_ds2_val_v1"
+  WHITELISTED_CATEGORIES:
+    "densepose_lvis_v1_ds2_train_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+    "densepose_lvis_v1_ds2_val_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+  CATEGORY_MAPS:
+    "densepose_lvis_v1_ds2_train_v1":
+      "1202": 943 # zebra -> sheep
+      "569": 943  # horse -> sheep
+      "496": 943  # giraffe -> sheep
+      "422": 943  # elephant -> sheep
+      "80": 943   # cow -> sheep
+      "76": 943   # bear -> sheep
+      "225": 943  # cat -> sheep
+      "378": 943  # dog -> sheep
+    "densepose_lvis_v1_ds2_val_v1":
+      "1202": 943 # zebra -> sheep
+      "569": 943  # horse -> sheep
+      "496": 943  # giraffe -> sheep
+      "422": 943  # elephant -> sheep
+      "80": 943   # cow -> sheep
+      "76": 943   # bear -> sheep
+      "225": 943  # cat -> sheep
+      "378": 943  # dog -> sheep
+  CLASS_TO_MESH_NAME_MAPPING:
+    # Note: different classes are mapped to a single class
+    # mesh is chosen based on GT data, so this is just some
+    # value which has no particular meaning
+    "0": "sheep_5004"
+SOLVER:
+  MAX_ITER: 16000
+  STEPS: (12000, 14000)
+DENSEPOSE_EVALUATION:
+  EVALUATE_MESH_ALIGNMENT: True

configs/cse/densepose_rcnn_R_50_FPN_soft_animals_CA_finetune_4k.yaml

@@ -0,0 +1,133 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/cse/densepose_rcnn_R_50_FPN_soft_s1x/250533982/model_final_2c4512.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_HEADS:
+    NUM_CLASSES: 1
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    COARSE_SEGM_TRAINED_BY_MASKS: True
+    CSE:
+      EMBED_LOSS_NAME: "SoftEmbeddingLoss"
+      EMBEDDING_DIST_GAUSS_SIGMA: 0.1
+      GEODESIC_DIST_GAUSS_SIGMA: 0.1
+      EMBEDDERS:
+        "cat_5001":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5001
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cat_5001_256.pkl"
+        "dog_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_dog_5002_256.pkl"
+        "sheep_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_sheep_5004_256.pkl"
+        "horse_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_horse_5004_256.pkl"
+        "zebra_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_zebra_5002_256.pkl"
+        "giraffe_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_giraffe_5002_256.pkl"
+        "elephant_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_elephant_5002_256.pkl"
+        "cow_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cow_5002_256.pkl"
+        "bear_4936":
+          TYPE: vertex_feature
+          NUM_VERTICES: 4936
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_bear_4936_256.pkl"
+DATASETS:
+  TRAIN:
+    - "densepose_lvis_v1_ds1_train_v1"
+  TEST:
+    - "densepose_lvis_v1_ds1_val_v1"
+  WHITELISTED_CATEGORIES:
+    "densepose_lvis_v1_ds1_train_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+    "densepose_lvis_v1_ds1_val_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+  CATEGORY_MAPS:
+    "densepose_lvis_v1_ds1_train_v1":
+      "1202": 943 # zebra -> sheep
+      "569": 943  # horse -> sheep
+      "496": 943  # giraffe -> sheep
+      "422": 943  # elephant -> sheep
+      "80": 943   # cow -> sheep
+      "76": 943   # bear -> sheep
+      "225": 943  # cat -> sheep
+      "378": 943  # dog -> sheep
+    "densepose_lvis_v1_ds1_val_v1":
+      "1202": 943 # zebra -> sheep
+      "569": 943  # horse -> sheep
+      "496": 943  # giraffe -> sheep
+      "422": 943  # elephant -> sheep
+      "80": 943   # cow -> sheep
+      "76": 943   # bear -> sheep
+      "225": 943  # cat -> sheep
+      "378": 943  # dog -> sheep
+  CLASS_TO_MESH_NAME_MAPPING:
+    # Note: different classes are mapped to a single class
+    # mesh is chosen based on GT data, so this is just some
+    # value which has no particular meaning
+    "0": "sheep_5004"
+SOLVER:
+  MAX_ITER: 4000
+  STEPS: (3000, 3500)
+DENSEPOSE_EVALUATION:
+  EVALUATE_MESH_ALIGNMENT: True

configs/cse/densepose_rcnn_R_50_FPN_soft_animals_I0_finetune_16k.yaml

@@ -0,0 +1,119 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/cse/densepose_rcnn_R_50_FPN_soft_animals_finetune_maskonly_24k/270668502/model_final_21b1d2.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_HEADS:
+    NUM_CLASSES: 9
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    COARSE_SEGM_TRAINED_BY_MASKS: True
+    CSE:
+      EMBED_LOSS_NAME: "SoftEmbeddingLoss"
+      EMBEDDING_DIST_GAUSS_SIGMA: 0.1
+      GEODESIC_DIST_GAUSS_SIGMA: 0.1
+      EMBEDDERS:
+        "cat_7466":
+          TYPE: vertex_feature
+          NUM_VERTICES: 7466
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cat_7466_256.pkl"
+        "dog_7466":
+          TYPE: vertex_feature
+          NUM_VERTICES: 7466
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_dog_7466_256.pkl"
+        "sheep_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_sheep_5004_256.pkl"
+        "horse_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_horse_5004_256.pkl"
+        "zebra_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_zebra_5002_256.pkl"
+        "giraffe_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_giraffe_5002_256.pkl"
+        "elephant_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_elephant_5002_256.pkl"
+        "cow_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cow_5002_256.pkl"
+        "bear_4936":
+          TYPE: vertex_feature
+          NUM_VERTICES: 4936
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_bear_4936_256.pkl"
+DATASETS:
+  TRAIN:
+    - "densepose_lvis_v1_ds2_train_v1"
+  TEST:
+    - "densepose_lvis_v1_ds2_val_v1"
+  WHITELISTED_CATEGORIES:
+    "densepose_lvis_v1_ds2_train_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+    "densepose_lvis_v1_ds2_val_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+  CLASS_TO_MESH_NAME_MAPPING:
+    "0": "bear_4936"
+    "1": "cow_5002"
+    "2": "cat_7466"
+    "3": "dog_7466"
+    "4": "elephant_5002"
+    "5": "giraffe_5002"
+    "6": "horse_5004"
+    "7": "sheep_5004"
+    "8": "zebra_5002"
+SOLVER:
+  MAX_ITER: 16000
+  STEPS: (12000, 14000)
+DENSEPOSE_EVALUATION:
+  EVALUATE_MESH_ALIGNMENT: True

configs/cse/densepose_rcnn_R_50_FPN_soft_animals_I0_finetune_i2m_16k.yaml

@@ -0,0 +1,121 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/cse/densepose_rcnn_R_50_FPN_soft_animals_finetune_maskonly_24k/270668502/model_final_21b1d2.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_HEADS:
+    NUM_CLASSES: 9
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    COARSE_SEGM_TRAINED_BY_MASKS: True
+    CSE:
+      EMBED_LOSS_NAME: "SoftEmbeddingLoss"
+      EMBEDDING_DIST_GAUSS_SIGMA: 0.1
+      GEODESIC_DIST_GAUSS_SIGMA: 0.1
+      PIX_TO_SHAPE_CYCLE_LOSS:
+        ENABLED: True
+      EMBEDDERS:
+        "cat_7466":
+          TYPE: vertex_feature
+          NUM_VERTICES: 7466
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cat_7466_256.pkl"
+        "dog_7466":
+          TYPE: vertex_feature
+          NUM_VERTICES: 7466
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_dog_7466_256.pkl"
+        "sheep_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_sheep_5004_256.pkl"
+        "horse_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_horse_5004_256.pkl"
+        "zebra_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_zebra_5002_256.pkl"
+        "giraffe_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_giraffe_5002_256.pkl"
+        "elephant_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_elephant_5002_256.pkl"
+        "cow_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cow_5002_256.pkl"
+        "bear_4936":
+          TYPE: vertex_feature
+          NUM_VERTICES: 4936
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_bear_4936_256.pkl"
+DATASETS:
+  TRAIN:
+    - "densepose_lvis_v1_ds2_train_v1"
+  TEST:
+    - "densepose_lvis_v1_ds2_val_v1"
+  WHITELISTED_CATEGORIES:
+    "densepose_lvis_v1_ds2_train_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+    "densepose_lvis_v1_ds2_val_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+  CLASS_TO_MESH_NAME_MAPPING:
+    "0": "bear_4936"
+    "1": "cow_5002"
+    "2": "cat_7466"
+    "3": "dog_7466"
+    "4": "elephant_5002"
+    "5": "giraffe_5002"
+    "6": "horse_5004"
+    "7": "sheep_5004"
+    "8": "zebra_5002"
+SOLVER:
+  MAX_ITER: 16000
+  STEPS: (12000, 14000)
+DENSEPOSE_EVALUATION:
+  EVALUATE_MESH_ALIGNMENT: True

configs/cse/densepose_rcnn_R_50_FPN_soft_animals_I0_finetune_m2m_16k.yaml

@@ -0,0 +1,138 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/cse/densepose_rcnn_R_50_FPN_soft_animals_finetune_maskonly_24k/267687159/model_final_354e61.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_HEADS:
+    NUM_CLASSES: 9
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    COARSE_SEGM_TRAINED_BY_MASKS: True
+    CSE:
+      EMBED_LOSS_NAME: "SoftEmbeddingLoss"
+      EMBEDDING_DIST_GAUSS_SIGMA: 0.1
+      GEODESIC_DIST_GAUSS_SIGMA: 0.1
+      SHAPE_TO_SHAPE_CYCLE_LOSS:
+        ENABLED: True
+      EMBEDDERS:
+        "cat_7466":
+          TYPE: vertex_feature
+          NUM_VERTICES: 7466
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cat_7466_256.pkl"
+        "dog_7466":
+          TYPE: vertex_feature
+          NUM_VERTICES: 7466
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_dog_7466_256.pkl"
+        "sheep_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_sheep_5004_256.pkl"
+        "horse_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_horse_5004_256.pkl"
+        "zebra_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_zebra_5002_256.pkl"
+        "giraffe_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_giraffe_5002_256.pkl"
+        "elephant_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_elephant_5002_256.pkl"
+        "cow_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cow_5002_256.pkl"
+        "bear_4936":
+          TYPE: vertex_feature
+          NUM_VERTICES: 4936
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_bear_4936_256.pkl"
+        "smpl_27554":
+          TYPE: vertex_feature
+          NUM_VERTICES: 27554
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_smpl_27554_256.pkl"
+DATASETS:
+  TRAIN:
+    - "densepose_lvis_v1_ds2_train_v1"
+  TEST:
+    - "densepose_lvis_v1_ds2_val_v1"
+  WHITELISTED_CATEGORIES:
+    "densepose_lvis_v1_ds2_train_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+    "densepose_lvis_v1_ds2_val_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+  CLASS_TO_MESH_NAME_MAPPING:
+    "0": "bear_4936"
+    "1": "cow_5002"
+    "2": "cat_7466"
+    "3": "dog_7466"
+    "4": "elephant_5002"
+    "5": "giraffe_5002"
+    "6": "horse_5004"
+    "7": "sheep_5004"
+    "8": "zebra_5002"
+SOLVER:
+  MAX_ITER: 16000
+  STEPS: (12000, 14000)
+DENSEPOSE_EVALUATION:
+  EVALUATE_MESH_ALIGNMENT: True
+  MESH_ALIGNMENT_MESH_NAMES:
+    - bear_4936
+    - cow_5002
+    - cat_7466
+    - dog_7466
+    - elephant_5002
+    - giraffe_5002
+    - horse_5004
+    - sheep_5004
+    - zebra_5002

configs/cse/densepose_rcnn_R_50_FPN_soft_animals_finetune_16k.yaml

@@ -0,0 +1,119 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/cse/densepose_rcnn_R_50_FPN_soft_s1x/250533982/model_final_2c4512.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_HEADS:
+    NUM_CLASSES: 9
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    COARSE_SEGM_TRAINED_BY_MASKS: True
+    CSE:
+      EMBED_LOSS_NAME: "SoftEmbeddingLoss"
+      EMBEDDING_DIST_GAUSS_SIGMA: 0.1
+      GEODESIC_DIST_GAUSS_SIGMA: 0.1
+      EMBEDDERS:
+        "cat_7466":
+          TYPE: vertex_feature
+          NUM_VERTICES: 7466
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cat_7466_256.pkl"
+        "dog_7466":
+          TYPE: vertex_feature
+          NUM_VERTICES: 7466
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_dog_7466_256.pkl"
+        "sheep_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_sheep_5004_256.pkl"
+        "horse_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_horse_5004_256.pkl"
+        "zebra_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_zebra_5002_256.pkl"
+        "giraffe_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_giraffe_5002_256.pkl"
+        "elephant_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_elephant_5002_256.pkl"
+        "cow_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cow_5002_256.pkl"
+        "bear_4936":
+          TYPE: vertex_feature
+          NUM_VERTICES: 4936
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_bear_4936_256.pkl"
+DATASETS:
+  TRAIN:
+    - "densepose_lvis_v1_ds2_train_v1"
+  TEST:
+    - "densepose_lvis_v1_ds2_val_v1"
+  WHITELISTED_CATEGORIES:
+    "densepose_lvis_v1_ds2_train_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+    "densepose_lvis_v1_ds2_val_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+  CLASS_TO_MESH_NAME_MAPPING:
+    "0": "bear_4936"
+    "1": "cow_5002"
+    "2": "cat_7466"
+    "3": "dog_7466"
+    "4": "elephant_5002"
+    "5": "giraffe_5002"
+    "6": "horse_5004"
+    "7": "sheep_5004"
+    "8": "zebra_5002"
+SOLVER:
+  MAX_ITER: 16000
+  STEPS: (12000, 14000)
+DENSEPOSE_EVALUATION:
+  EVALUATE_MESH_ALIGNMENT: True

configs/cse/densepose_rcnn_R_50_FPN_soft_animals_finetune_4k.yaml

@@ -0,0 +1,119 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/cse/densepose_rcnn_R_50_FPN_soft_s1x/250533982/model_final_2c4512.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_HEADS:
+    NUM_CLASSES: 9
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    COARSE_SEGM_TRAINED_BY_MASKS: True
+    CSE:
+      EMBED_LOSS_NAME: "SoftEmbeddingLoss"
+      EMBEDDING_DIST_GAUSS_SIGMA: 0.1
+      GEODESIC_DIST_GAUSS_SIGMA: 0.1
+      EMBEDDERS:
+        "cat_5001":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5001
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cat_5001_256.pkl"
+        "dog_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_dog_5002_256.pkl"
+        "sheep_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_sheep_5004_256.pkl"
+        "horse_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_horse_5004_256.pkl"
+        "zebra_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_zebra_5002_256.pkl"
+        "giraffe_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_giraffe_5002_256.pkl"
+        "elephant_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_elephant_5002_256.pkl"
+        "cow_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cow_5002_256.pkl"
+        "bear_4936":
+          TYPE: vertex_feature
+          NUM_VERTICES: 4936
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_bear_4936_256.pkl"
+DATASETS:
+  TRAIN:
+    - "densepose_lvis_v1_ds1_train_v1"
+  TEST:
+    - "densepose_lvis_v1_ds1_val_v1"
+  WHITELISTED_CATEGORIES:
+    "densepose_lvis_v1_ds1_train_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+    "densepose_lvis_v1_ds1_val_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+  CLASS_TO_MESH_NAME_MAPPING:
+    "0": "bear_4936"
+    "1": "cow_5002"
+    "2": "cat_5001"
+    "3": "dog_5002"
+    "4": "elephant_5002"
+    "5": "giraffe_5002"
+    "6": "horse_5004"
+    "7": "sheep_5004"
+    "8": "zebra_5002"
+SOLVER:
+  MAX_ITER: 4000
+  STEPS: (3000, 3500)
+DENSEPOSE_EVALUATION:
+  EVALUATE_MESH_ALIGNMENT: True

configs/cse/densepose_rcnn_R_50_FPN_soft_animals_finetune_maskonly_24k.yaml

@@ -0,0 +1,118 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/cse/densepose_rcnn_R_50_FPN_soft_s1x/250533982/model_final_2c4512.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_HEADS:
+    NUM_CLASSES: 9
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    COARSE_SEGM_TRAINED_BY_MASKS: True
+    CSE:
+      EMBED_LOSS_NAME: "SoftEmbeddingLoss"
+      EMBED_LOSS_WEIGHT: 0.0
+      EMBEDDING_DIST_GAUSS_SIGMA: 0.1
+      GEODESIC_DIST_GAUSS_SIGMA: 0.1
+      EMBEDDERS:
+        "cat_7466":
+          TYPE: vertex_feature
+          NUM_VERTICES: 7466
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cat_7466_256.pkl"
+        "dog_7466":
+          TYPE: vertex_feature
+          NUM_VERTICES: 7466
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_dog_7466_256.pkl"
+        "sheep_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_sheep_5004_256.pkl"
+        "horse_5004":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5004
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_horse_5004_256.pkl"
+        "zebra_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_zebra_5002_256.pkl"
+        "giraffe_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_giraffe_5002_256.pkl"
+        "elephant_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_elephant_5002_256.pkl"
+        "cow_5002":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5002
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_cow_5002_256.pkl"
+        "bear_4936":
+          TYPE: vertex_feature
+          NUM_VERTICES: 4936
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_bear_4936_256.pkl"
+DATASETS:
+  TRAIN:
+    - "densepose_lvis_v1_ds2_train_v1"
+  TEST:
+    - "densepose_lvis_v1_ds2_val_v1"
+  WHITELISTED_CATEGORIES:
+    "densepose_lvis_v1_ds2_train_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+    "densepose_lvis_v1_ds2_val_v1":
+      - 943  # sheep
+      - 1202 # zebra
+      - 569  # horse
+      - 496  # giraffe
+      - 422  # elephant
+      - 80   # cow
+      - 76   # bear
+      - 225  # cat
+      - 378  # dog
+  CLASS_TO_MESH_NAME_MAPPING:
+    "0": "bear_4936"
+    "1": "cow_5002"
+    "2": "cat_7466"
+    "3": "dog_7466"
+    "4": "elephant_5002"
+    "5": "giraffe_5002"
+    "6": "horse_5004"
+    "7": "sheep_5004"
+    "8": "zebra_5002"
+SOLVER:
+  MAX_ITER: 24000
+  STEPS: (20000, 22000)

configs/cse/densepose_rcnn_R_50_FPN_soft_chimps_finetune_4k.yaml

@@ -0,0 +1,29 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "https://dl.fbaipublicfiles.com/densepose/cse/densepose_rcnn_R_50_FPN_soft_s1x/250533982/model_final_2c4512.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    CSE:
+      EMBED_LOSS_NAME: "SoftEmbeddingLoss"
+      EMBEDDING_DIST_GAUSS_SIGMA: 0.1
+      GEODESIC_DIST_GAUSS_SIGMA: 0.1
+      EMBEDDERS:
+        "chimp_5029":
+          TYPE: vertex_feature
+          NUM_VERTICES: 5029
+          FEATURE_DIM: 256
+          FEATURES_TRAINABLE: False
+          IS_TRAINABLE: True
+          INIT_FILE: "https://dl.fbaipublicfiles.com/densepose/data/cse/lbo/phi_chimp_5029_256.pkl"
+DATASETS:
+  TRAIN:
+    - "densepose_chimps_cse_train"
+  TEST:
+    - "densepose_chimps_cse_val"
+  CLASS_TO_MESH_NAME_MAPPING:
+    "0": "chimp_5029"
+SOLVER:
+  MAX_ITER: 4000
+  STEPS: (3000, 3500)

configs/cse/densepose_rcnn_R_50_FPN_soft_s1x.yaml

@@ -0,0 +1,12 @@
+_BASE_: "Base-DensePose-RCNN-FPN-Human.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseV1ConvXHead"
+    CSE:
+      EMBED_LOSS_NAME: "SoftEmbeddingLoss"
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/densepose_rcnn_R_101_FPN_DL_WC1M_s1x.yaml

@@ -0,0 +1,18 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "iid_iso"
+    SEGM_CONFIDENCE:
+      ENABLED: True
+    POINT_REGRESSION_WEIGHTS: 0.0005
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/densepose_rcnn_R_101_FPN_DL_WC1_s1x.yaml

@@ -0,0 +1,16 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "iid_iso"
+    POINT_REGRESSION_WEIGHTS: 0.0005
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/densepose_rcnn_R_101_FPN_DL_WC2M_s1x.yaml

@@ -0,0 +1,18 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "indep_aniso"
+    SEGM_CONFIDENCE:
+      ENABLED: True
+    POINT_REGRESSION_WEIGHTS: 0.0005
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/densepose_rcnn_R_101_FPN_DL_WC2_s1x.yaml

@@ -0,0 +1,16 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "indep_aniso"
+    POINT_REGRESSION_WEIGHTS: 0.0005
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/densepose_rcnn_R_101_FPN_DL_s1x.yaml

@@ -0,0 +1,10 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/densepose_rcnn_R_101_FPN_WC1M_s1x.yaml

@@ -0,0 +1,18 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+  ROI_DENSEPOSE_HEAD:
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "iid_iso"
+    SEGM_CONFIDENCE:
+      ENABLED: True
+    POINT_REGRESSION_WEIGHTS: 0.0005
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)
+  WARMUP_FACTOR: 0.025

configs/densepose_rcnn_R_101_FPN_WC1_s1x.yaml

@@ -0,0 +1,16 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+  ROI_DENSEPOSE_HEAD:
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "iid_iso"
+    POINT_REGRESSION_WEIGHTS: 0.0005
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)
+  WARMUP_FACTOR: 0.025

configs/densepose_rcnn_R_101_FPN_WC2M_s1x.yaml

@@ -0,0 +1,18 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+  ROI_DENSEPOSE_HEAD:
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "indep_aniso"
+    SEGM_CONFIDENCE:
+      ENABLED: True
+    POINT_REGRESSION_WEIGHTS: 0.0005
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)
+  WARMUP_FACTOR: 0.025

configs/densepose_rcnn_R_101_FPN_WC2_s1x.yaml

@@ -0,0 +1,16 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+  ROI_DENSEPOSE_HEAD:
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "indep_aniso"
+    POINT_REGRESSION_WEIGHTS: 0.0005
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)
+  WARMUP_FACTOR: 0.025

configs/densepose_rcnn_R_101_FPN_s1x.yaml

@@ -0,0 +1,8 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/densepose_rcnn_R_101_FPN_s1x_legacy.yaml

@@ -0,0 +1,17 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+  ROI_DENSEPOSE_HEAD:
+    NUM_COARSE_SEGM_CHANNELS: 15
+    POOLER_RESOLUTION: 14
+    HEATMAP_SIZE: 56
+    INDEX_WEIGHTS: 2.0
+    PART_WEIGHTS: 0.3
+    POINT_REGRESSION_WEIGHTS: 0.1
+    DECODER_ON: False
+SOLVER:
+  BASE_LR: 0.002
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/densepose_rcnn_R_50_FPN_DL_WC1M_s1x.yaml

@@ -0,0 +1,18 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "iid_iso"
+    SEGM_CONFIDENCE:
+      ENABLED: True
+    POINT_REGRESSION_WEIGHTS: 0.0005
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/densepose_rcnn_R_50_FPN_DL_WC1_s1x.yaml

@@ -0,0 +1,16 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "iid_iso"
+    POINT_REGRESSION_WEIGHTS: 0.0005
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/densepose_rcnn_R_50_FPN_DL_WC2M_s1x.yaml

@@ -0,0 +1,18 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "indep_aniso"
+    SEGM_CONFIDENCE:
+      ENABLED: True
+    POINT_REGRESSION_WEIGHTS: 0.0005
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/densepose_rcnn_R_50_FPN_DL_WC2_s1x.yaml

@@ -0,0 +1,16 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "indep_aniso"
+    POINT_REGRESSION_WEIGHTS: 0.0005
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/densepose_rcnn_R_50_FPN_DL_s1x.yaml

@@ -0,0 +1,10 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/densepose_rcnn_R_50_FPN_WC1M_s1x.yaml

@@ -0,0 +1,20 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_DENSEPOSE_HEAD:
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "iid_iso"
+    SEGM_CONFIDENCE:
+      ENABLED: True
+    POINT_REGRESSION_WEIGHTS: 0.0005
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+    CLIP_TYPE: norm
+    CLIP_VALUE: 100.0
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)
+  WARMUP_FACTOR: 0.025

configs/densepose_rcnn_R_50_FPN_WC1_s1x.yaml

@@ -0,0 +1,16 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_DENSEPOSE_HEAD:
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "iid_iso"
+    POINT_REGRESSION_WEIGHTS: 0.0005
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)
+  WARMUP_FACTOR: 0.025

configs/densepose_rcnn_R_50_FPN_WC2M_s1x.yaml

@@ -0,0 +1,18 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_DENSEPOSE_HEAD:
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "indep_aniso"
+    SEGM_CONFIDENCE:
+      ENABLED: True
+    POINT_REGRESSION_WEIGHTS: 0.0005
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)
+  WARMUP_FACTOR: 0.025

configs/densepose_rcnn_R_50_FPN_WC2_s1x.yaml

@@ -0,0 +1,16 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+  ROI_DENSEPOSE_HEAD:
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "indep_aniso"
+    POINT_REGRESSION_WEIGHTS: 0.0005
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)
+  WARMUP_FACTOR: 0.025