Upload 2 files

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

utils_mask.py

@@ -0,0 +1,181 @@
+import numpy as np
+import cv2
+from PIL import Image, ImageDraw
+
+label_map = {
+    "background": 0,
+    "hat": 1,
+    "hair": 2,
+    "sunglasses": 3,
+    "upper_clothes": 4,
+    "skirt": 5,
+    "pants": 6,
+    "dress": 7,
+    "belt": 8,
+    "left_shoe": 9,
+    "right_shoe": 10,
+    "head": 11,
+    "left_leg": 12,
+    "right_leg": 13,
+    "left_arm": 14,
+    "right_arm": 15,
+    "bag": 16,
+    "scarf": 17,
+}
+
+def extend_arm_mask(wrist, elbow, scale):
+  wrist = elbow + scale * (wrist - elbow)
+  return wrist
+
+def hole_fill(img):
+    img = np.pad(img[1:-1, 1:-1], pad_width = 1, mode = 'constant', constant_values=0)
+    img_copy = img.copy()
+    mask = np.zeros((img.shape[0] + 2, img.shape[1] + 2), dtype=np.uint8)
+
+    cv2.floodFill(img, mask, (0, 0), 255)
+    img_inverse = cv2.bitwise_not(img)
+    dst = cv2.bitwise_or(img_copy, img_inverse)
+    return dst
+
+def refine_mask(mask):
+    contours, hierarchy = cv2.findContours(mask.astype(np.uint8),
+                                           cv2.RETR_CCOMP, cv2.CHAIN_APPROX_TC89_L1)
+    area = []
+    for j in range(len(contours)):
+        a_d = cv2.contourArea(contours[j], True)
+        area.append(abs(a_d))
+    refine_mask = np.zeros_like(mask).astype(np.uint8)
+    if len(area) != 0:
+        i = area.index(max(area))
+        cv2.drawContours(refine_mask, contours, i, color=255, thickness=-1)
+
+    return refine_mask
+
+def get_mask_location(model_type, category, model_parse: Image.Image, keypoint: dict, width=384,height=512):
+    im_parse = model_parse.resize((width, height), Image.NEAREST)
+    parse_array = np.array(im_parse)
+
+    if model_type == 'hd':
+        arm_width = 60
+    elif model_type == 'dc':
+        arm_width = 45
+    else:
+        raise ValueError("model_type must be \'hd\' or \'dc\'!")
+
+    parse_head = (parse_array == 1).astype(np.float32) + \
+                 (parse_array == 3).astype(np.float32) + \
+                 (parse_array == 11).astype(np.float32)
+
+    parser_mask_fixed = (parse_array == label_map["left_shoe"]).astype(np.float32) + \
+                        (parse_array == label_map["right_shoe"]).astype(np.float32) + \
+                        (parse_array == label_map["hat"]).astype(np.float32) + \
+                        (parse_array == label_map["sunglasses"]).astype(np.float32) + \
+                        (parse_array == label_map["bag"]).astype(np.float32)
+
+    parser_mask_changeable = (parse_array == label_map["background"]).astype(np.float32)
+
+    arms_left = (parse_array == 14).astype(np.float32)
+    arms_right = (parse_array == 15).astype(np.float32)
+
+    if category == 'dresses':
+        parse_mask = (parse_array == 7).astype(np.float32) + \
+                     (parse_array == 4).astype(np.float32) + \
+                     (parse_array == 5).astype(np.float32) + \
+                     (parse_array == 6).astype(np.float32)
+
+        parser_mask_changeable += np.logical_and(parse_array, np.logical_not(parser_mask_fixed))
+
+    elif category == 'upper_body':
+        parse_mask = (parse_array == 4).astype(np.float32) + (parse_array == 7).astype(np.float32)
+        parser_mask_fixed_lower_cloth = (parse_array == label_map["skirt"]).astype(np.float32) + \
+                                        (parse_array == label_map["pants"]).astype(np.float32)
+        parser_mask_fixed += parser_mask_fixed_lower_cloth
+        parser_mask_changeable += np.logical_and(parse_array, np.logical_not(parser_mask_fixed))
+    elif category == 'lower_body':
+        parse_mask = (parse_array == 6).astype(np.float32) + \
+                     (parse_array == 12).astype(np.float32) + \
+                     (parse_array == 13).astype(np.float32) + \
+                     (parse_array == 5).astype(np.float32)
+        parser_mask_fixed += (parse_array == label_map["upper_clothes"]).astype(np.float32) + \
+                             (parse_array == 14).astype(np.float32) + \
+                             (parse_array == 15).astype(np.float32)
+        parser_mask_changeable += np.logical_and(parse_array, np.logical_not(parser_mask_fixed))
+    else:
+        raise NotImplementedError
+
+    # Load pose points
+    pose_data = keypoint["pose_keypoints_2d"]
+    pose_data = np.array(pose_data)
+    pose_data = pose_data.reshape((-1, 2))
+
+    im_arms_left = Image.new('L', (width, height))
+    im_arms_right = Image.new('L', (width, height))
+    arms_draw_left = ImageDraw.Draw(im_arms_left)
+    arms_draw_right = ImageDraw.Draw(im_arms_right)
+    if category == 'dresses' or category == 'upper_body':
+        shoulder_right = np.multiply(tuple(pose_data[2][:2]), height / 512.0)
+        shoulder_left = np.multiply(tuple(pose_data[5][:2]), height / 512.0)
+        elbow_right = np.multiply(tuple(pose_data[3][:2]), height / 512.0)
+        elbow_left = np.multiply(tuple(pose_data[6][:2]), height / 512.0)
+        wrist_right = np.multiply(tuple(pose_data[4][:2]), height / 512.0)
+        wrist_left = np.multiply(tuple(pose_data[7][:2]), height / 512.0)
+        ARM_LINE_WIDTH = int(arm_width / 512 * height)
+        size_left = [shoulder_left[0] - ARM_LINE_WIDTH // 2, shoulder_left[1] - ARM_LINE_WIDTH // 2, shoulder_left[0] + ARM_LINE_WIDTH // 2, shoulder_left[1] + ARM_LINE_WIDTH // 2]
+        size_right = [shoulder_right[0] - ARM_LINE_WIDTH // 2, shoulder_right[1] - ARM_LINE_WIDTH // 2, shoulder_right[0] + ARM_LINE_WIDTH // 2,
+                      shoulder_right[1] + ARM_LINE_WIDTH // 2]
+        
+
+        if wrist_right[0] <= 1. and wrist_right[1] <= 1.:
+            im_arms_right = arms_right
+        else:
+            wrist_right = extend_arm_mask(wrist_right, elbow_right, 1.2)
+            arms_draw_right.line(np.concatenate((shoulder_right, elbow_right, wrist_right)).astype(np.uint16).tolist(), 'white', ARM_LINE_WIDTH, 'curve')
+            arms_draw_right.arc(size_right, 0, 360, 'white', ARM_LINE_WIDTH // 2)
+
+        if wrist_left[0] <= 1. and wrist_left[1] <= 1.:
+            im_arms_left = arms_left
+        else:
+            wrist_left = extend_arm_mask(wrist_left, elbow_left, 1.2)
+            arms_draw_left.line(np.concatenate((wrist_left, elbow_left, shoulder_left)).astype(np.uint16).tolist(), 'white', ARM_LINE_WIDTH, 'curve')
+            arms_draw_left.arc(size_left, 0, 360, 'white', ARM_LINE_WIDTH // 2)
+
+        hands_left = np.logical_and(np.logical_not(im_arms_left), arms_left)
+        hands_right = np.logical_and(np.logical_not(im_arms_right), arms_right)
+        parser_mask_fixed += hands_left + hands_right
+
+    parser_mask_fixed = np.logical_or(parser_mask_fixed, parse_head)
+    parse_mask = cv2.dilate(parse_mask, np.ones((5, 5), np.uint16), iterations=5)
+    if category == 'dresses' or category == 'upper_body':
+        neck_mask = (parse_array == 18).astype(np.float32)
+        neck_mask = cv2.dilate(neck_mask, np.ones((5, 5), np.uint16), iterations=1)
+        neck_mask = np.logical_and(neck_mask, np.logical_not(parse_head))
+        parse_mask = np.logical_or(parse_mask, neck_mask)
+        arm_mask = cv2.dilate(np.logical_or(im_arms_left, im_arms_right).astype('float32'), np.ones((5, 5), np.uint16), iterations=4)
+        parse_mask += np.logical_or(parse_mask, arm_mask)
+
+    parse_mask = np.logical_and(parser_mask_changeable, np.logical_not(parse_mask))
+
+    parse_mask_total = np.logical_or(parse_mask, parser_mask_fixed)
+    inpaint_mask = 1 - parse_mask_total
+    img = np.where(inpaint_mask, 255, 0)
+    dst = hole_fill(img.astype(np.uint8))
+    dst = refine_mask(dst)
+    inpaint_mask = dst / 255 * 1
+    mask = Image.fromarray(inpaint_mask.astype(np.uint8) * 255)
+    mask_gray = Image.fromarray(inpaint_mask.astype(np.uint8) * 127)
+
+    return mask, mask_gray
+
+
+def pil_to_binary_mask(pil_image, threshold=0):
+    np_image = np.array(pil_image)
+    grayscale_image = Image.fromarray(np_image).convert("L")
+    binary_mask = np.array(grayscale_image) > threshold
+    mask = np.zeros(binary_mask.shape, dtype=np.uint8)
+    for i in range(binary_mask.shape[0]):
+        for j in range(binary_mask.shape[1]):
+            if binary_mask[i,j] == True :
+                mask[i,j] = 1
+    mask = (mask*255).astype(np.uint8)
+    output_mask = Image.fromarray(mask)
+    return output_mask