Spaces:
Running
on
Zero
Running
on
Zero
File size: 11,091 Bytes
938e515 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 |
#!/usr/bin/env python3
# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
import argparse
import glob
import logging
import os
import pickle
import sys
from typing import Any, ClassVar, Dict, List
import torch
from detectron2.config import get_cfg
from detectron2.data.detection_utils import read_image
from detectron2.engine.defaults import DefaultPredictor
from detectron2.structures.boxes import BoxMode
from detectron2.structures.instances import Instances
from detectron2.utils.logger import setup_logger
from densepose import add_densepose_config
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 import (
DensePoseResultsContourVisualizer,
DensePoseResultsFineSegmentationVisualizer,
DensePoseResultsUVisualizer,
DensePoseResultsVVisualizer,
)
from densepose.vis.extractor import CompoundExtractor, 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(object):
@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("input", metavar="<input>", help="Input data")
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):
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)
for file_name in file_list:
img = read_image(file_name, format="BGR") # predictor expects BGR image.
with torch.no_grad():
outputs = predictor(img)["instances"]
cls.execute_on_outputs(context, {"file_name": file_name, "image": img}, outputs)
cls.postexecute(context)
@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"):
boxes_XYWH = BoxMode.convert(
result["pred_boxes_XYXY"], BoxMode.XYXY_ABS, BoxMode.XYWH_ABS
)
result["pred_densepose"] = outputs.get("pred_densepose").to_result(boxes_XYWH)
context["results"].append(result)
@classmethod
def create_context(cls: type, args: argparse.Namespace):
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:
pickle.dump(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,
"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(
"--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)
entry_idx = context["entry_idx"] + 1
out_fname = cls._get_out_fname(entry_idx, 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)
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
@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) -> Dict[str, Any]:
vis_specs = args.visualizations.split(",")
visualizers = []
extractors = []
for vis_spec in vis_specs:
vis = cls.VISUALIZERS[vis_spec]()
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 = args.verbosity if hasattr(args, "verbosity") else None
global logger
logger = setup_logger(name=LOGGER_NAME)
logger.setLevel(verbosity_to_level(verbosity))
args.func(args)
if __name__ == "__main__":
main()
|