def _get_model_config(config_file):
cfg = get_cfg()
add_densepose_config(cfg)
cfg.merge_from_file(config_file)
if not torch.cuda.is_available():
cfg.MODEL_DEVICE = "cpu"
return cfg
def setup(args):
# Regist own dataset.
from detectron2.data.datasets import register_coco_instances
folder_data = "/root/detectron2/MADS_data_train_test/80_20_tonghop"
# train_data
name = "mads_train"
json_file = os.path.join(folder_data, "train.json")
image_root = os.path.join(folder_data, "train", "images")
# test data
name_val = "mads_val"
json_file_val = os.path.join(folder_data, "val.json")
image_root_val = os.path.join(folder_data, "val", "images")
# registr
register_coco_instances(name, {}, json_file, image_root)
register_coco_instances(name_val, {}, json_file_val, image_root_val)
cfg = get_cfg()
add_densepose_config(cfg)
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
default_setup(cfg, args)
# Setup logger for "densepose" module
setup_logger(output=cfg.OUTPUT_DIR,
distributed_rank=comm.get_rank(),
name="densepose")
return cfg
def __init__(self, config_path, model_path):
cfg = get_cfg()
add_densepose_config(cfg)
cfg.merge_from_file(config_path)
cfg.MODEL.WEIGHTS = model_path
cfg.MODEL.DEVICE = 'cpu'
cfg.freeze()
super().__init__(cfg)
def setup_config(config_fpath: str, model_fpath: str, args: dict):
cfg = get_cfg()
add_densepose_config(cfg)
cfg.merge_from_file(config_fpath)
cfg.merge_from_list(args['opts'])
cfg.MODEL.WEIGHTS = model_fpath
cfg.freeze()
return cfg
def setup(args):
cfg = get_cfg()
add_densepose_config(cfg)
add_efficientnet_config(cfg)
add_roi_shared_config(cfg)
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
return cfg
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)
if opts:
cfg.merge_from_list(opts)
cfg.MODEL.WEIGHTS = model_fpath
cfg.freeze()
return cfg
def setup_config():
cfg = get_cfg()
add_densepose_config(cfg)
cfg.merge_from_file(config_fpath)
if opts:
cfg.merge_from_list(opts)
cfg.MODEL.WEIGHTS = model_fpath
cfg.MODEL.DEVICE = 'cpu'
cfg.freeze()
return cfg
def setup(args):
cfg = get_cfg()
add_densepose_config(cfg)
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
default_setup(cfg, args)
# Setup logger for "densepose" module
setup_logger(output=cfg.OUTPUT_DIR, distributed_rank=comm.get_rank(), name="densepose")
return cfg
def get_model_config(config_file):
"""
Load and return the configuration from the specified file (relative to the base configuration
directory)
"""
cfg = get_cfg()
add_densepose_config(cfg)
path = os.path.join(_get_base_config_dir(), config_file)
cfg.merge_from_file(path)
if not torch.cuda.is_available():
cfg.MODEL_DEVICE = "cpu"
return cfg
def setup_config(config_fpath: str, model_fpath: str, opts: List[str]):
opts.append("MODEL.ROI_HEADS.SCORE_THRESH_TEST")
opts.append(0.8) # Min score
cfg = get_cfg()
add_densepose_config(cfg)
add_hrnet_config(cfg)
cfg.merge_from_file(config_fpath)
if opts:
cfg.merge_from_list(opts)
cfg.MODEL.WEIGHTS = model_fpath
cfg.freeze()
return cfg
def setup(args):
cfg = get_cfg()
add_densepose_config(cfg)
add_efficientnet_config(cfg)
add_roi_shared_config(cfg)
cfg.merge_from_file(args.config_file)
cfg.SOLVER.BASE_LR = 0.001 # Avoid NaNs. Not useful in this script anyway.
cfg.merge_from_list(args.opts)
cfg.freeze()
setup_logger(distributed_rank=comm.get_rank())
return cfg
def prepare_predictor(threshold=0.5):
print('prepare predictor...')
cfg = get_cfg()
add_densepose_config(cfg)
model_file = './projects/DensePose/configs/densepose_rcnn_R_101_FPN_DL_s1x.yaml'
model_weights = 'https://dl.fbaipublicfiles.com/densepose/densepose_rcnn_R_101_FPN_DL_s1x/165712116/model_final_844d15.pkl'
cfg.merge_from_file(model_file)
cfg.MODEL.WEIGHTS = model_weights
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = threshold
cfg.freeze()
predictor = DefaultPredictor(cfg)
# print(cfg.dump())
return predictor
def __init__(self, configFile, poseModelFile, accuracyThreshold,numberGpus):
cfg = get_cfg()
add_densepose_config(cfg)
cfg.merge_from_file(configFile)
cfg.MODEL.WEIGHTS = poseModelFile
cfg.freeze()
self.cfg = cfg
self.accuracyThreshold = accuracyThreshold
mp.set_start_method("spawn", force=True)
smp = mp.get_context("spawn")
self.queues = [smp.Manager().list(), smp.Manager().list()]
self.procs = []
for i in range(numberGpus):
cfgProc = cfg.clone()
cfgProc.defrost()
cfgProc.MODEL.DEVICE = "cuda:" + str(i)
self.procs.append(PosePredictorMultiGPU.PredictWorker(cfgProc, self.queues[i], i, self.accuracyThreshold))
def _test_setup(self, config_file):
cfg = get_cfg()
add_densepose_config(cfg)
cfg.merge_from_file(config_file)
cfg.freeze()
default_setup(cfg, {})
edges_x.append(i)
edges_y.append(j)
left = min(edges_x) #左边界
right = max(edges_x) #右边界
width = right - left #宽度
bottom = min(edges_y) #底部
top = max(edges_y) #顶部
height = top - bottom #高度
pre1_picture = img[left:left + width, bottom:bottom + height] #图片截取
return pre1_picture #返回图片数据
cfg = get_cfg()
add_densepose_config(cfg)
cfg.merge_from_file(
"~/detectron2-master/projects/Densepose/configs/densepose_rcnn_R_50_FPN_s1x.yaml"
)
cfg.MODEL.WEIGHTS = "~/detectron2-master/projects/Densepose/model_final_162be9.pkl"
cfg.freeze()
predictor = DefaultPredictor(cfg)
img = cv2.imread("~/signLanguageAssesment/data/1.jpg")
print(img.shape)
outputs = predictor(img)["instances"]
def __init__(
self,
model=MODELS["chimps"],
model_cache_dir: Path = Path(".zamba_cache"),
download_region=RegionEnum("us"),
):
"""Create a DensePoseManager object.
Parameters
----------
model : dict, optional (default MODELS['chimps'])
A dictionary with the densepose model defintion like those defined in MODELS.
"""
if not DENSEPOSE_AVAILABLE:
raise ImportError(
"Densepose not installed. See: https://zamba.drivendata.org/docs/stable/models/densepose/#installation"
)
# setup configuration for densepose
self.cfg = get_cfg()
add_densepose_config(self.cfg)
self.cfg.merge_from_file(model["config"])
if not (model_cache_dir / model["weights"]).exists():
model_cache_dir.mkdir(parents=True, exist_ok=True)
self.cfg.MODEL.WEIGHTS = download_weights(model["weights"],
model_cache_dir,
download_region)
# automatically use CPU if no cuda available
if not torch.cuda.is_available():
self.cfg.MODEL.DEVICE = "cpu"
self.cfg.freeze()
logging.getLogger("fvcore").setLevel(
"CRITICAL") # silence noisy detectron2 logging
# set up predictor with the configuration
self.predictor = DefaultPredictor(self.cfg)
# we have a specific texture atlas for chimps with relevant regions
# labeled that we can use instead of the default segmentation
self.visualizer = model["viz_class"](
self.cfg,
device=self.cfg.MODEL.DEVICE,
**model.get("viz_class_kwargs", {}),
)
# set up utilities for use with visualizer
self.vis_extractor = create_extractor(self.visualizer)
self.vis_embedder = build_densepose_embedder(self.cfg)
self.vis_class_to_mesh_name = get_class_to_mesh_name_mapping(self.cfg)
self.vis_mesh_vertex_embeddings = {
mesh_name: self.vis_embedder(mesh_name).to(self.cfg.MODEL.DEVICE)
for mesh_name in self.vis_class_to_mesh_name.values()
if self.vis_embedder.has_embeddings(mesh_name)
}
if "anatomy_color_mapping" in model:
self.anatomy_color_mapping = pd.read_csv(
model["anatomy_color_mapping"], index_col=0)
else:
self.anatomy_color_mapping = None
