Upload 1459 files

app.py

@@ -0,0 +1,257 @@
+import spaces
+import gradio as gr
+import apply_net
+
+import os
+import sys
+import cv2
+
+sys.path.append('./')
+import numpy as np
+import argparse
+
+import torch
+import torchvision
+import pytorch_lightning
+from torch import autocast
+from torchvision import transforms
+from pytorch_lightning import seed_everything
+
+from einops import rearrange 
+from functools import partial
+from omegaconf import OmegaConf
+from PIL import Image
+from typing import List
+import matplotlib.pyplot as plt
+from torchvision.transforms.functional import to_pil_image
+from utils_mask import get_mask_location
+from preprocess.humanparsing.run_parsing import Parsing
+from preprocess.openpose.run_openpose import OpenPose
+from ldm.util import instantiate_from_config, get_obj_from_str
+from ldm.models.diffusion.ddim import DDIMSampler
+from detectron2.data.detection_utils import convert_PIL_to_numpy,_apply_exif_orientation
+
+
+
+if __name__ == "__main__":
+    
+    parser = argparse.ArgumentParser(description="Script for demo model")
+    parser.add_argument("-b", "--base", type=str, default=r"configs/test_vitonhd.yaml")
+    parser.add_argument("-c", "--ckpt", type=str, default=r"ckpt/hitonhd.ckpt")
+    parser.add_argument("-s", "--seed", type=str, default=42)
+    parser.add_argument("-d", "--ddim", type=str, default=16)
+    opt = parser.parse_args()
+    
+    seed_everything(opt.seed)
+    config = OmegaConf.load(f"{opt.base}")
+
+    device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
+
+    model = instantiate_from_config(config.model)
+    model.load_state_dict(torch.hub.load_state_dict_from_url("https://huggingface.co/basso4/hitonhd/resolve/main/hitonhd.ckpt")["state_dict"], strict=False)
+    model.cuda()
+    model.eval()
+    model = model.to(device)
+    sampler = DDIMSampler(model)
+
+    # model = instantiate_from_config(config.model)
+    # model.load_state_dict(torch.load(opt.ckpt, map_location="cpu")["state_dict"], strict=False)
+    # model.cuda()
+    # model.eval()
+    # device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
+    # model = model.to(device)
+    # sampler = DDIMSampler(model)
+    
+    precision_scope = autocast
+    
+    
+    @spaces.GPU
+    def start_tryon(dict_human,garm_img):
+        #load human image
+        human_img = dict_human['background'].convert("RGB").resize((768,1024))
+
+        #mask
+        tensor_transfrom = transforms.Compose(
+                [
+                    transforms.ToTensor(),
+                    transforms.Normalize([0.5], [0.5]),
+                ]
+        )
+    
+        parsing_model = Parsing(0)
+        openose_model = OpenPose(0)
+        openose_model.preprocessor.body_estimation.model.to(device)
+    
+        keypoints = openose_model(human_img.resize((384,512)))
+        model_parse, _ = parsing_model(human_img.resize((384,512)))
+        mask, mask_gray = get_mask_location('hd', "upper_body", model_parse, keypoints)
+        mask_cv = mask
+        mask = mask.resize((768, 1024))
+        mask_gray = (1-transforms.ToTensor()(mask)) * tensor_transfrom(human_img)
+        mask_gray = to_pil_image((mask_gray+1.0)/2.0)
+    
+        #densepose    
+        human_img_arg = _apply_exif_orientation(human_img.resize((384,512)))
+        human_img_arg = convert_PIL_to_numpy(human_img_arg, format="BGR")
+        args = apply_net.create_argument_parser().parse_args(('show', 
+                                                            './configs/configs_densepose/densepose_rcnn_R_50_FPN_s1x.yaml', 
+                                                            'https://dl.fbaipublicfiles.com/densepose/densepose_rcnn_R_50_FPN_s1x/165712039/model_final_162be9.pkl', 
+                                                            'dp_segm', '-v', 
+                                                            '--opts', 
+                                                            'MODEL.DEVICE', 
+                                                            'cuda'))
+        # verbosity = getattr(args, "verbosity", None)
+        pose_img = args.func(args,human_img_arg)    
+        pose_img = pose_img[:,:,::-1]    
+        pose_img = Image.fromarray(pose_img).resize((768,1024))
+    
+        #preprocessing image
+        human_img = human_img.convert("RGB").resize((512, 512))
+        human_img = torchvision.transforms.ToTensor()(human_img)
+    
+        garm_img = garm_img.convert("RGB").resize((224, 224))
+        garm_img = torchvision.transforms.ToTensor()(garm_img)
+    
+        mask = mask.convert("L").resize((512,512))
+        mask = torchvision.transforms.ToTensor()(mask)
+        mask = 1-mask
+    
+        pose_img = pose_img.convert("RGB").resize((512, 512))
+        pose_img = torchvision.transforms.ToTensor()(pose_img)
+    
+        #Normalize
+        human_img = torchvision.transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))(human_img)
+        garm_img = torchvision.transforms.Normalize((0.48145466, 0.4578275, 0.40821073),
+                                                    (0.26862954, 0.26130258, 0.27577711))(garm_img)
+        pose_img = torchvision.transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))(pose_img)
+    
+        #create inpaint & hint
+        inpaint = human_img * mask
+        hint = torchvision.transforms.Resize((512, 512))(garm_img)
+        hint = torch.cat((hint, pose_img), dim=0)
+    
+        # {"human_img": human_img,     # [3, 512, 512]
+        # "inpaint_image": inpaint,   # [3, 512, 512]
+        # "inpaint_mask": mask,       # [1, 512, 512]
+        # "garm_img": garm_img,       # [3, 224, 224]
+        # "hint": hint,               # [6, 512, 512]
+        # }
+    
+    
+        with torch.no_grad():
+            with precision_scope("cuda"):
+                #loading data
+                inpaint = inpaint.unsqueeze(0).to(torch.float16).to(device)
+                reference = garm_img.unsqueeze(0).to(torch.float16).to(device)
+                mask = mask.unsqueeze(0).to(torch.float16).to(device)
+                hint = hint.unsqueeze(0).to(torch.float16).to(device)
+                truth = human_img.unsqueeze(0).to(torch.float16).to(device)
+    
+                #data preprocessing
+                encoder_posterior_inpaint = model.first_stage_model.encode(inpaint)
+                z_inpaint = model.scale_factor * (encoder_posterior_inpaint.sample()).detach()
+                mask_resize = torchvision.transforms.Resize([z_inpaint.shape[-2],z_inpaint.shape[-1]])(mask)
+                test_model_kwargs = {}
+                test_model_kwargs['inpaint_image'] = z_inpaint
+                test_model_kwargs['inpaint_mask'] = mask_resize
+                shape = (model.channels, model.image_size, model.image_size)
+    
+                #predict
+                samples, _ = sampler.sample(S=opt.ddim,
+                                                 batch_size=1,
+                                                 shape=shape,
+                                                 pose=hint,
+                                                 conditioning=reference,
+                                                 verbose=False,
+                                                 eta=0,
+                                                 test_model_kwargs=test_model_kwargs)
+                samples = 1. / model.scale_factor * samples
+                x_samples = model.first_stage_model.decode(samples[:,:4,:,:])
+    
+                x_samples_ddim = torch.clamp((x_samples + 1.0) / 2.0, min=0.0, max=1.0)
+                x_samples_ddim = x_samples_ddim.cpu().permute(0, 2, 3, 1).numpy()
+                x_checked_image=x_samples_ddim
+                x_checked_image_torch = torch.from_numpy(x_checked_image).permute(0, 3, 1, 2)
+                
+                x_checked_image_torch = torch.nn.functional.interpolate(x_checked_image_torch.float(), size=[512,384])
+
+                #apply seamlessClone technique here
+                #img_base
+                dict_human = dict_human.convert("RGB").resize((384, 512))
+                dict_human = np.array(dict_human)
+                dict_human = cv2.cvtColor(dict_human, cv2.COLOR_RGB2BGR)
+
+                #img_output
+                img_cv = rearrange(x_checked_image_torch[0], 'c h w -> h w c').cpu().numpy()
+                img_cv = (img_cv * 255).astype(np.uint8)
+                img_cv = cv2.cvtColor(img_cv, cv2.COLOR_RGB2BGR)
+                
+                #mask
+                mask_cv = mask_cv.convert("L").resize((384,512))
+                mask_cv = np.array(mask_cv)
+                mask_cv = 255-mask_cv
+    
+                img_C = cv2.seamlessClone(dict_human, img_cv, mask_cv, (192,256), cv2.NORMAL_CLONE)
+    
+                
+                return img_C, mask_gray
+
+
+example_path = os.path.join(os.path.dirname(__file__), 'example')
+
+garm_list = os.listdir(os.path.join(example_path,"cloth"))
+garm_list_path = [os.path.join(example_path,"cloth",garm) for garm in garm_list]
+
+human_list = os.listdir(os.path.join(example_path,"human"))
+human_list_path = [os.path.join(example_path,"human",human) for human in human_list]
+
+human_ex_list = []
+for ex_human in human_list_path:
+    ex_dict= {}
+    ex_dict['background'] = ex_human
+    ex_dict['layers'] = None
+    ex_dict['composite'] = None
+    human_ex_list.append(ex_dict)
+
+##default human
+
+
+image_blocks = gr.Blocks().queue()
+with image_blocks as demo:
+    gr.Markdown("## FPT_VTON 👕👔👚")
+    gr.Markdown("Virtual Try-on with your image and garment image")
+    with gr.Row():
+        with gr.Column():
+            imgs = gr.ImageEditor(sources='upload', type="pil", label='Human Picture or use Examples below', interactive=True)
+
+            example = gr.Examples(
+                inputs=imgs,
+                examples_per_page=10,
+                examples=human_list_path
+            )
+        
+        with gr.Column():
+            garm_img = gr.Image(label="Garment", sources='upload', type="pil")
+
+            example = gr.Examples(
+                inputs=garm_img,
+                examples_per_page=8,
+                examples=garm_list_path
+            )
+        
+        with gr.Column():
+            image_out_c = gr.Image(label="Output", elem_id="output-img",show_download_button=True)
+            try_button = gr.Button(value="Try-on")
+
+        # with gr.Column():
+        #     image_out_c = gr.Image(label="Output", elem_id="output-img",show_download_button=False)
+
+        with gr.Column():
+            masked_img = gr.Image(label="Masked image output", elem_id="masked_img", show_download_button=True)
+
+
+    try_button.click(fn=start_tryon, inputs=[imgs,garm_img], outputs=[image_out_c,masked_img], api_name='tryon')
+
+
+
+image_blocks.launch()

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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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/configs_densepose/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

configs/configs_densepose/densepose_rcnn_R_50_FPN_s1x.yaml

@@ -0,0 +1,8 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+SOLVER:
+  MAX_ITER: 130000
+  STEPS: (100000, 120000)

configs/configs_densepose/densepose_rcnn_R_50_FPN_s1x_legacy.yaml

@@ -0,0 +1,17 @@
+_BASE_: "Base-DensePose-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+  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/configs_densepose/evolution/Base-RCNN-FPN-Atop10P_CA.yaml

@@ -0,0 +1,91 @@
+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"]
+    NUM_CLASSES: 1
+  ROI_BOX_HEAD:
+    NAME: "FastRCNNConvFCHead"
+    NUM_FC: 2
+    POOLER_RESOLUTION: 7
+  ROI_MASK_HEAD:
+    NAME: "MaskRCNNConvUpsampleHead"
+    NUM_CONV: 4
+    POOLER_RESOLUTION: 14
+DATASETS:
+  TRAIN: ("base_coco_2017_train", "densepose_coco_2014_train")
+  TEST: ("densepose_chimps",)
+  CATEGORY_MAPS:
+    "base_coco_2017_train":
+      "16": 1 # bird -> person
+      "17": 1 # cat -> person
+      "18": 1 # dog -> person
+      "19": 1 # horse -> person
+      "20": 1 # sheep -> person
+      "21": 1 # cow -> person
+      "22": 1 # elephant -> person
+      "23": 1 # bear -> person
+      "24": 1 # zebra -> person
+      "25": 1 # girafe -> person
+    "base_coco_2017_val":
+      "16": 1 # bird -> person
+      "17": 1 # cat -> person
+      "18": 1 # dog -> person
+      "19": 1 # horse -> person
+      "20": 1 # sheep -> person
+      "21": 1 # cow -> person
+      "22": 1 # elephant -> person
+      "23": 1 # bear -> person
+      "24": 1 # zebra -> person
+      "25": 1 # girafe -> person
+  WHITELISTED_CATEGORIES:
+    "base_coco_2017_train":
+      - 1  # person
+      - 16 # bird
+      - 17 # cat
+      - 18 # dog
+      - 19 # horse
+      - 20 # sheep
+      - 21 # cow
+      - 22 # elephant
+      - 23 # bear
+      - 24 # zebra
+      - 25 # girafe
+    "base_coco_2017_val":
+      - 1  # person
+      - 16 # bird
+      - 17 # cat
+      - 18 # dog
+      - 19 # horse
+      - 20 # sheep
+      - 21 # cow
+      - 22 # elephant
+      - 23 # bear
+      - 24 # zebra
+      - 25 # girafe
+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

configs/configs_densepose/evolution/densepose_R_50_FPN_DL_WC1M_3x_Atop10P_CA.yaml

@@ -0,0 +1,28 @@
+_BASE_: "Base-RCNN-FPN-Atop10P_CA.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+  DENSEPOSE_ON: True
+  ROI_HEADS:
+    NAME: "DensePoseROIHeads"
+    IN_FEATURES: ["p2", "p3", "p4", "p5"]
+    NUM_CLASSES: 1
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "iid_iso"
+    SEGM_CONFIDENCE:
+      ENABLED: True
+    POINT_REGRESSION_WEIGHTS: 0.0005
+    POOLER_TYPE: "ROIAlign"
+    NUM_COARSE_SEGM_CHANNELS: 2
+    COARSE_SEGM_TRAINED_BY_MASKS: True
+    INDEX_WEIGHTS: 1.0
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  WARMUP_FACTOR: 0.025
+  MAX_ITER: 270000
+  STEPS: (210000, 250000)

configs/configs_densepose/evolution/densepose_R_50_FPN_DL_WC1M_3x_Atop10P_CA_B_coarsesegm.yaml

@@ -0,0 +1,56 @@
+_BASE_: "Base-RCNN-FPN-Atop10P_CA.yaml"
+MODEL:
+  WEIGHTS: https://dl.fbaipublicfiles.com/densepose/evolution/densepose_R_50_FPN_DL_WC1M_3x_Atop10P_CA/217578784/model_final_9fe1cc.pkl
+  RESNETS:
+    DEPTH: 50
+  DENSEPOSE_ON: True
+  ROI_HEADS:
+    NAME: "DensePoseROIHeads"
+    IN_FEATURES: ["p2", "p3", "p4", "p5"]
+    NUM_CLASSES: 1
+  ROI_DENSEPOSE_HEAD:
+    NAME: "DensePoseDeepLabHead"
+    UV_CONFIDENCE:
+      ENABLED: True
+      TYPE: "iid_iso"
+    SEGM_CONFIDENCE:
+      ENABLED: True
+    POINT_REGRESSION_WEIGHTS: 0.0005
+    POOLER_TYPE: "ROIAlign"
+    NUM_COARSE_SEGM_CHANNELS: 2
+    COARSE_SEGM_TRAINED_BY_MASKS: True
+BOOTSTRAP_DATASETS:
+  - DATASET: "chimpnsee"
+    RATIO: 1.0
+    IMAGE_LOADER:
+      TYPE: "video_keyframe"
+      SELECT:
+        STRATEGY: "random_k"
+        NUM_IMAGES: 4
+      TRANSFORM:
+        TYPE: "resize"
+        MIN_SIZE: 800
+        MAX_SIZE: 1333
+      BATCH_SIZE: 8
+      NUM_WORKERS: 1
+    INFERENCE:
+      INPUT_BATCH_SIZE: 1
+      OUTPUT_BATCH_SIZE: 1
+    DATA_SAMPLER:
+      # supported types:
+      #   densepose_uniform
+      #   densepose_UV_confidence
+      #   densepose_fine_segm_confidence
+      #   densepose_coarse_segm_confidence
+      TYPE: "densepose_coarse_segm_confidence"
+      COUNT_PER_CLASS: 8
+    FILTER:
+      TYPE: "detection_score"
+      MIN_VALUE: 0.8
+BOOTSTRAP_MODEL:
+  WEIGHTS: https://dl.fbaipublicfiles.com/densepose/evolution/densepose_R_50_FPN_DL_WC1M_3x_Atop10P_CA/217578784/model_final_9fe1cc.pkl
+SOLVER:
+  CLIP_GRADIENTS:
+    ENABLED: True
+  MAX_ITER: 270000
+  STEPS: (210000, 250000)