def __init__(self, args):
self.cfg = update_config(args.cfg)
args.gpus = [int(i) for i in args.gpus.split(',')
] if torch.cuda.device_count() >= 1 else [-1]
args.device = torch.device(
"cuda:" + str(args.gpus[0]) if args.gpus[0] >= 0 else "cpu")
args.detbatch = args.detbatch * len(args.gpus)
args.posebatch = args.posebatch * len(args.gpus)
args.tracking = (args.detector == 'tracker')
self.mode, self.input_source = self.check_input(args)
# Load pose model
self.pose_model = builder.build_sppe(self.cfg.MODEL,
preset_cfg=self.cfg.DATA_PRESET)
print(f'Loading pose model from {args.checkpoint}...')
self.pose_model.load_state_dict(
torch.load(args.checkpoint, map_location=args.device))
if len(args.gpus) > 1:
self.pose_model = torch.nn.DataParallel(self.pose_model,
device_ids=args.gpus).to(
args.device)
else:
self.pose_model.to(args.device)
self.pose_model.eval()
self.args = args
def __init__(self):
self.device = try_gpu()
self.cfg = update_config(
'configs/coco/resnet/256x192_res50_lr1e-3_1x.yaml')
self.detector = get_detector({'detector': yolo})
self.detector.load_model()
self.pose_net = builder.build_sppe(self.cfg.MODEL,
preset_cfg=self.cfg.DATA_PRESET)
self.pose_net.load_state_dict(
torch.load('pretrained_models/fast_res50_256x192.pth',
map_location=self.device))
pose_model.to(self.device)
def get_args():
parser = argparse.ArgumentParser(description='AlphaPose Single-Image Demo')
parser.add_argument('--cfg', type=str, default="configs/coco/resnet/256x192_res50_lr1e-3_1x.yaml",
help='experiment configure file name')
parser.add_argument('--checkpoint', type=str, default="pretrained_models/fast_res50_256x192.pth",
help='checkpoint file name')
parser.add_argument('--detector', dest='detector',
help='detector name', default="yolo")
parser.add_argument('--image', dest='inputimg',
help='image-name', default="")
parser.add_argument('--save_img', default=False, action='store_true',
help='save result as image')
parser.add_argument('--vis', default=False, action='store_true',
help='visualize image')
parser.add_argument('--showbox', default=False, action='store_true',
help='visualize human bbox')
parser.add_argument('--profile', default=False, action='store_true',
help='add speed profiling at screen output')
parser.add_argument('--format', type=str,
help='save in the format of cmu or coco or openpose, option: coco/cmu/open')
parser.add_argument('--min_box_area', type=int, default=0,
help='min box area to filter out')
parser.add_argument('--eval', dest='eval', default=False, action='store_true',
help='save the result json as coco format, using image index(int) instead of image name(str)')
parser.add_argument('--gpus', type=str, dest='gpus', default="0",
help='choose which cuda device to use by index and input comma to use multi gpus, e.g. 0,1,2,3. (input -1 for cpu only)')
parser.add_argument('--flip', default=False, action='store_true',
help='enable flip testing')
parser.add_argument('--debug', default=False, action='store_true',
help='print detail information')
parser.add_argument('--vis_fast', dest='vis_fast',
help='use fast rendering', action='store_true', default=False)
"""----------------------------- Tracking options -----------------------------"""
parser.add_argument('--pose_flow', dest='pose_flow',
help='track humans in video with PoseFlow', action='store_true', default=False)
parser.add_argument('--pose_track', dest='pose_track',
help='track humans in video with reid', action='store_true', default=False)
args = parser.parse_args()
cfg = update_config(args.cfg)
args.gpus = [int(args.gpus[0])] if torch.cuda.device_count() >= 1 else [-1]
args.device = torch.device("cuda:" + str(args.gpus[0]) if args.gpus[0] >= 0 else "cpu")
args.tracking = args.pose_track or args.pose_flow or args.detector=='tracker'
return args, cfg
def __init__(self, video, kp_score_treshold=.7):
self.video = video
self.kp_score_treshold = kp_score_treshold
self.detector = "yolo"
self.outputpath = os.path.dirname(
self.video) + os.path.sep + "AlphaPose" + os.path.sep
self.vis = False
self.profile = False
self.format = None # coco/cmu/open
self.min_box_area = 0
self.detbatch = 1 # 5
self.posebatch = 10 # 80
self.eval = False
self.gpus = [0]
self.flip = False
self.qsize = 64 # 1024
self.debug = False
self.save_video = False
self.vis_fast = False
self.pose_flow = False
self.pose_track = True
self.sp = True
self.save_img = False
assert not (self.pose_flow
and self.pose_track), "Pick only PoseFlow or Pose Track"
self.device = torch.device("cuda:0")
self.detbatch = self.detbatch * len(self.gpus)
self.posebatch = self.posebatch * len(self.gpus)
self.tracking = (self.pose_track or self.pose_flow
or self.detector == 'tracker')
self.cfg = "configs/coco/resnet/256x192_res50_lr1e-3_2x-dcn.yaml"
self.checkpoint = "pretrained_models/fast_dcn_res50_256x192.pth"
self.cfg = update_config(self.cfg)
self.all_results = []
help='whether to save rendered video',
default=True,
action='store_true')
parser.add_argument('--vis_fast',
dest='vis_fast',
help='use fast rendering',
action='store_true',
default=False)
parser.add_argument('--pose_track',
dest='pose_track',
help='track humans in video',
action='store_true',
default=False)
args = parser.parse_args()
cfg = update_config(args.cfg)
if platform.system() == 'Windows':
args.sp = True
args.gpus = [int(i) for i in args.gpus.split(',')
] if torch.cuda.device_count() >= 1 else [-1]
args.device = torch.device("cuda:" +
str(args.gpus[0]) if args.gpus[0] >= 0 else "cpu")
args.detbatch = args.detbatch * len(args.gpus)
args.posebatch = args.posebatch * len(args.gpus)
args.tracking = (args.detector == 'tracker')
if not args.sp:
torch.multiprocessing.set_start_method('forkserver', force=True)
torch.multiprocessing.set_sharing_strategy('file_system')
required=True,
type=str)
parser.add_argument('--gpus', help='gpus', type=str)
parser.add_argument('--batch', help='validation batch size', type=int)
parser.add_argument('--flip-test',
default=False,
dest='flip_test',
help='flip test',
action='store_true')
parser.add_argument('--detector',
dest='detector',
help='detector name',
default="yolo")
opt = parser.parse_args()
cfg = update_config(opt.cfg)
gpus = [int(i) for i in opt.gpus.split(',')]
opt.gpus = [gpus[0]]
opt.device = torch.device("cuda:" +
str(opt.gpus[0]) if opt.gpus[0] >= 0 else "cpu")
def validate(m, heatmap_to_coord, batch_size=20):
det_dataset = builder.build_dataset(cfg.DATASET.TEST,
preset_cfg=cfg.DATA_PRESET,
train=False,
opt=opt)
eval_joints = det_dataset.EVAL_JOINTS
det_loader = torch.utils.data.DataLoader(det_dataset,
########################################
# Load in ReID Classification Parameter#
########################################
print('===> Start to constructing and loading ReID model',
['yellow', 'bold'])
if opt.ReIDCfg != "":
ReIDCfg.merge_from_file(opt.ReIDCfg)
ReIDCfg.freeze()
ReIDCfg_ = edict(ReIDCfg)
ReIDCfg__ = TransferEasyDictToDICT(ReIDCfg_)
writeyaml('./config/ReID/defaults.yaml', ReIDCfg__)
##########################
# Load in Poser Parameter#
##########################
Pose_opt = update_config(opt.Poser_cfg)
Pose_opt_ = edict(Pose_opt)
Pose_opt__ = TransferEasyDictToDICT(Pose_opt_)
writeyaml('./config/alphapose/defaults.yaml', Pose_opt__)
##################################
# Load in Number Predictor Number#
##################################
Num_Pred_opt = Config.fromfile(opt.SvhnCfg)
Num_Pred_opt_ = edict(Num_Pred_opt)
Num_Pred_opt__ = TransferEasyDictToDICT(Num_Pred_opt_)
writeyaml('./config/SVHN/defaults.yaml', Num_Pred_opt__)
'''
def saveONNX(model, filepath, c, h, w):
#输入数据形状
dummy_input = torch.zeros(1, c, h, w, device='cuda')
dynamic_ax = {'input': {0: 'batch_size'}, 'output': {0: 'batch_size'}}
torch.onnx.export(model,
dummy_input,
filepath,
opset_version=10,
input_names=["input"],
output_names=["output"],
dynamic_axes=dynamic_ax)
cfg = update_config("configs/coco/resnet/256x192_res50_lr1e-3_1x.yaml")
print(cfg)
pose_model = builder.build_sppe(cfg.MODEL, preset_cfg=cfg.DATA_PRESET)
pose_model.load_state_dict(
torch.load("pretrained_models/fast_res50_256x192.pth"))
pose_model.eval()
print(pose_model)
pose_model = pose_model.cuda()
saveONNX(pose_model,
filepath="onnxfile/fastpose_ret50_dynamic.onnx",
c=3,
h=256,
w=192)
def __init__(self, args=None):
if args is None:
args = Namespace(
# Pose config
pose_cfg='configs/coco/resnet/256x192_res50_lr1e-3_1x.yaml',
# Pose checkpoint
pose_checkpoint='pretrained_models/fast_res50_256x192.pth',
# GPUS
gpus='0',
# Detection thresh
det_thresh=0.5,
# Detection config
det_cfg='mmDetection/gfl_x101_611.py',
# Detection checkpoint
det_checkpoint='mmDetection/weights.pth',
# Show clothe color
clothe_color=True,
# show bboxes
showbox=True
)
self.pose_cfg = update_config(args.pose_cfg)
# Device configuration
args.gpus = [int(i) for i in args.gpus.split(',')] if torch.cuda.device_count() >= 1 else [-1]
args.device = torch.device("cuda:" + str(args.gpus[0]) if args.gpus[0] >= 0 else "cpu")
args.tracking = False
args.pose_track = False
# Copy args
self.args = args
# Preprocess transformation
pose_dataset = builder.retrieve_dataset(self.pose_cfg.DATASET.TRAIN)
self.transformation = SimpleTransform(
pose_dataset, scale_factor=0,
input_size=self.pose_cfg.DATA_PRESET.IMAGE_SIZE,
output_size=self.pose_cfg.DATA_PRESET.HEATMAP_SIZE,
rot=0, sigma=self.pose_cfg.DATA_PRESET.SIGMA,
train=False, add_dpg=False, gpu_device=args.device)
self.norm_type = self.pose_cfg.LOSS.get('NORM_TYPE', None)
# Post process
self.heatmap_to_coord = get_func_heatmap_to_coord(self.pose_cfg)
# Load Detector Model
self.det_model = init_detector(args.det_cfg, checkpoint=args.det_checkpoint, device=args.device)
# Load pose model
self.pose_model = builder.build_sppe(self.pose_cfg.MODEL, preset_cfg=self.pose_cfg.DATA_PRESET)
print(f'Loading pose model from {args.pose_checkpoint}...')
self.pose_model.load_state_dict(torch.load(args.pose_checkpoint, map_location=args.device))
self.pose_model.to(args.device)
self.pose_model.eval()
import numpy as np
import torch
from alphapose.models import builder
from alphapose.utils.config import update_config
cfg_path = 'scripts/256x192_res50_lr1e-3_1x.yaml'
weight = 'scripts/fast_res50_256x192.pth'
model_path = 'alpha_pose_res50_256x192.pth'
onnx_model_name = 'alphapose.onnx'
if __name__ == "__main__":
cfg = update_config(cfg_path)
input_npz = np.load('pose.npz')
input = input_npz['input']
input = torch.from_numpy(input)
device = torch.device('cpu')
pose_model = builder.build_sppe(cfg.MODEL, preset_cfg=cfg.DATA_PRESET)
pose_model.load_state_dict(torch.load(weight, map_location=device))
torch.onnx.export(
pose_model, # model being run
input, # model input (or a tuple for multiple inputs)
onnx_model_name, # where to save the model (can be a file or file-like object)
export_params=
True, # store the trained parameter weights inside the model file
opset_version=10, # the ONNX version to export the model to
do_constant_folding=
True, # whether to execute constant folding for optimization
input_names=['input'], # the model's input names
output_names=['output'], # the model's output names
)
print("Finish!")
def start(self):
parser = argparse.ArgumentParser(description='AlphaPose Demo')
parser.add_argument(
'--cfg',
type=str,
required=False,
help='experiment configure file name',
default=
"./AlphaPose/configs/coco/resnet/256x192_res50_lr1e-3_1x.yaml")
parser.add_argument(
'--checkpoint',
type=str,
required=False,
help='checkpoint file name',
default="./AlphaPose/pretrained_models/fast_res50_256x192.pth")
parser.add_argument('--sp',
default=False,
action='store_true',
help='Use single process for pytorch')
parser.add_argument('--detector',
dest='detector',
help='detector name',
default="yolo")
parser.add_argument('--detfile',
dest='detfile',
help='detection result file',
default="")
parser.add_argument('--indir',
dest='inputpath',
help='image-directory',
default="./media/img")
parser.add_argument('--list',
dest='inputlist',
help='image-list',
default="")
parser.add_argument('--image',
dest='inputimg',
help='image-name',
default="")
parser.add_argument('--outdir',
dest='outputpath',
help='output-directory',
default="./output")
parser.add_argument('--save_img',
default=True,
action='store_true',
help='save result as image')
parser.add_argument('--vis',
default=False,
action='store_true',
help='visualize image')
parser.add_argument('--showbox',
default=False,
action='store_true',
help='visualize human bbox')
parser.add_argument('--profile',
default=False,
action='store_true',
help='add speed profiling at screen output')
parser.add_argument(
'--format',
type=str,
help=
'save in the format of cmu or coco or openpose, option: coco/cmu/open',
default="open")
parser.add_argument('--min_box_area',
type=int,
default=0,
help='min box area to filter out')
parser.add_argument('--detbatch',
type=int,
default=1,
help='detection batch size PER GPU')
parser.add_argument('--posebatch',
type=int,
default=30,
help='pose estimation maximum batch size PER GPU')
parser.add_argument(
'--eval',
dest='eval',
default=False,
action='store_true',
help=
'save the result json as coco format, using image index(int) instead of image name(str)'
)
parser.add_argument(
'--gpus',
type=str,
dest='gpus',
default="0",
help=
'choose which cuda device to use by index and input comma to use multi gpus, e.g. 0,1,2,3. (input -1 for cpu only)'
)
parser.add_argument(
'--qsize',
type=int,
dest='qsize',
default=1024,
help=
'the length of result buffer, where reducing it will lower requirement of cpu memory'
)
parser.add_argument('--flip',
default=False,
action='store_true',
help='enable flip testing')
parser.add_argument('--debug',
default=False,
action='store_true',
help='print detail information')
"""----------------------------- Video options -----------------------------"""
parser.add_argument('--video',
dest='video',
help='video-name',
default="")
parser.add_argument('--webcam',
dest='webcam',
type=int,
help='webcam number',
default=-1)
parser.add_argument('--save_video',
dest='save_video',
help='whether to save rendered video',
default=False,
action='store_true')
parser.add_argument('--vis_fast',
dest='vis_fast',
help='use fast rendering',
action='store_true',
default=False)
"""----------------------------- Tracking options -----------------------------"""
parser.add_argument('--pose_flow',
dest='pose_flow',
help='track humans in video with PoseFlow',
action='store_true',
default=False)
parser.add_argument('--pose_track',
dest='pose_track',
help='track humans in video with reid',
action='store_true',
default=True)
args = parser.parse_args()
cfg = update_config(args.cfg)
if platform.system() == 'Windows':
args.sp = True
args.gpus = [int(i) for i in args.gpus.split(',')
] if torch.cuda.device_count() >= 1 else [-1]
args.device = torch.device(
"cuda:" + str(args.gpus[0]) if args.gpus[0] >= 0 else "cpu")
args.detbatch = args.detbatch * len(args.gpus)
args.posebatch = args.posebatch * len(args.gpus)
args.tracking = args.pose_track or args.pose_flow or args.detector == 'tracker'
if not args.sp:
torch.multiprocessing.set_start_method('forkserver', force=True)
torch.multiprocessing.set_sharing_strategy('file_system')
def check_input():
# for wecam
if args.webcam != -1:
args.detbatch = 1
return 'webcam', int(args.webcam)
# for video
if len(args.video):
if os.path.isfile(args.video):
videofile = args.video
return 'video', videofile
else:
raise IOError(
'Error: --video must refer to a video file, not directory.'
)
# for detection results
if len(args.detfile):
if os.path.isfile(args.detfile):
detfile = args.detfile
return 'detfile', detfile
else:
raise IOError(
'Error: --detfile must refer to a detection json file, not directory.'
)
# for images
if len(args.inputpath) or len(args.inputlist) or len(
args.inputimg):
inputpath = args.inputpath
inputlist = args.inputlist
inputimg = args.inputimg
if len(inputlist):
im_names = open(inputlist, 'r').readlines()
elif len(inputpath) and inputpath != '/':
for root, dirs, files in os.walk(inputpath):
im_names = files
im_names = natsort.natsorted(im_names)
elif len(inputimg):
args.inputpath = os.path.split(inputimg)[0]
im_names = [os.path.split(inputimg)[1]]
return 'image', im_names
else:
raise NotImplementedError
def print_finish_info():
print('===========================> Finish Model Running.')
if (args.save_img or args.save_video) and not args.vis_fast:
print(
'===========================> Rendering remaining images in the queue...'
)
print(
'===========================> If this step takes too long, you can enable the --vis_fast flag to use fast rendering (real-time).'
)
def loop():
n = 0
while True:
yield n
n += 1
# dirList = os.listdir(args.inputpath)
# inDir = args.inputpath
# outDir = args.outputpath
# for i in dirList :
mode, input_source = check_input()
if not os.path.exists(args.outputpath):
os.makedirs(args.outputpath)
# Load detection loader
if mode == 'webcam':
det_loader = WebCamDetectionLoader(input_source,
get_detector(args), cfg, args)
det_worker = det_loader.start()
elif mode == 'detfile':
det_loader = FileDetectionLoader(input_source, cfg, args)
det_worker = det_loader.start()
else:
det_loader = DetectionLoader(input_source,
get_detector(args),
cfg,
args,
batchSize=args.detbatch,
mode=mode,
queueSize=args.qsize)
det_worker = det_loader.start()
# Load pose model
pose_model = builder.build_sppe(cfg.MODEL, preset_cfg=cfg.DATA_PRESET)
print(f'Loading pose model from {args.checkpoint}...')
pose_model.load_state_dict(
torch.load(args.checkpoint, map_location=args.device))
pose_dataset = builder.retrieve_dataset(cfg.DATASET.TRAIN)
if args.pose_track:
tracker = Tracker(tcfg, args)
if len(args.gpus) > 1:
pose_model = torch.nn.DataParallel(pose_model,
device_ids=args.gpus).to(
args.device)
else:
pose_model.to(args.device)
pose_model.eval()
runtime_profile = {'dt': [], 'pt': [], 'pn': []}
# Init data writer
queueSize = 2 if mode == 'webcam' else args.qsize
if args.save_video and mode != 'image':
from alphapose.utils.writer import DEFAULT_VIDEO_SAVE_OPT as video_save_opt
if mode == 'video':
video_save_opt['savepath'] = os.path.join(
args.outputpath,
'AlphaPose_' + os.path.basename(input_source))
else:
video_save_opt['savepath'] = os.path.join(
args.outputpath,
'AlphaPose_webcam' + str(input_source) + '.mp4')
video_save_opt.update(det_loader.videoinfo)
writer = DataWriter(cfg,
args,
save_video=True,
video_save_opt=video_save_opt,
queueSize=queueSize).start()
else:
writer = DataWriter(cfg,
args,
save_video=False,
queueSize=queueSize).start()
if mode == 'webcam':
print('Starting webcam demo, press Ctrl + C to terminate...')
sys.stdout.flush()
im_names_desc = tqdm(loop())
else:
data_len = det_loader.length
im_names_desc = tqdm(range(data_len), dynamic_ncols=True)
batchSize = args.posebatch
if args.flip:
batchSize = int(batchSize / 2)
try:
self.percentage[2] = '관절정보 분석중'
for i in range(len(im_names_desc)):
start_time = getTime()
# print(start_time)
self.percentage[0] += 1
#
with torch.no_grad():
(inps, orig_img, im_name, boxes, scores, ids,
cropped_boxes) = det_loader.read()
if orig_img is None:
break
if boxes is None or boxes.nelement() == 0:
writer.save(None, None, None, None, None, orig_img,
im_name)
continue
if args.profile:
ckpt_time, det_time = getTime(start_time)
runtime_profile['dt'].append(det_time)
# Pose Estimation
inps = inps.to(args.device)
datalen = inps.size(0)
leftover = 0
if (datalen) % batchSize:
leftover = 1
num_batches = datalen // batchSize + leftover
hm = []
for j in range(num_batches):
inps_j = inps[j * batchSize:min((j + 1) *
batchSize, datalen)]
if args.flip:
inps_j = torch.cat((inps_j, flip(inps_j)))
hm_j = pose_model(inps_j)
if args.flip:
hm_j_flip = flip_heatmap(hm_j[int(len(hm_j) / 2):],
pose_dataset.joint_pairs,
shift=True)
hm_j = (hm_j[0:int(len(hm_j) / 2)] + hm_j_flip) / 2
hm.append(hm_j)
hm = torch.cat(hm)
if args.profile:
ckpt_time, pose_time = getTime(ckpt_time)
runtime_profile['pt'].append(pose_time)
if args.pose_track:
boxes, scores, ids, hm, cropped_boxes = track(
tracker, args, orig_img, inps, boxes, hm,
cropped_boxes, im_name, scores)
hm = hm.cpu()
writer.save(boxes, scores, ids, hm, cropped_boxes,
orig_img, im_name)
if args.profile:
ckpt_time, post_time = getTime(ckpt_time)
runtime_profile['pn'].append(post_time)
if args.profile:
# TQDM
im_names_desc.set_description(
'det time: {dt:.4f} | pose time: {pt:.4f} | post processing: {pn:.4f}'
.format(dt=np.mean(runtime_profile['dt']),
pt=np.mean(runtime_profile['pt']),
pn=np.mean(runtime_profile['pn'])))
print_finish_info()
print("마무리 작업중...")
while (writer.running()):
time.sleep(1)
print('===========================> Rendering remaining ' +
str(writer.count()) + ' images in the queue...')
writer.stop()
det_loader.stop()
print("작업종료")
except Exception as e:
print(repr(e))
print(
'An error as above occurs when processing the images, please check it'
)
pass
except KeyboardInterrupt:
print_finish_info()
# Thread won't be killed when press Ctrl+C
if args.sp:
det_loader.terminate()
while (writer.running()):
time.sleep(1)
print('===========================> Rendering remaining ' +
str(writer.count()) + ' images in the queue...')
writer.stop()
else:
# subprocesses are killed, manually clear queues
det_loader.terminate()
writer.terminate()
writer.clear_queues()
det_loader.clear_queues()
if name.split('.')[-1] == 'jpg':
img = cv2.imread(os.path.join(dir,name))
imgs.append(img)
for index in range(1000):
C_T_output_queue.put(True, (index, imgs, []))
if __name__ == '__main__':
import torch.multiprocessing as mp
from SoftWare_main import Pose_Estimate
# 追踪器的参数
from opt import opt
Pose_opt = update_config(opt.Poser_cfg)
queueSize = 1024
cfg_file = '/datanew/hwb/FairMOT-master/alphapose/configs/coco/resnet/256x192_res50_lr1e-3_1x-simple.yaml'
cfg = update_config(cfg_file)
C_T_output_queue = mp.Queue(queueSize) # C_T : coordinate transfer.
# 基于追踪数据，将追踪数据转换到其他的视角，并且生成相应的截图何ReID Features
C_transfer = mp.Process(target=generate_img_sequences, args=(opt, C_T_output_queue))
C_transfer.daemon = True
C_transfer.start()
Pose_output_queue = mp.Queue(queueSize)
# 基于追踪数据，将追踪数据转换到其他的视角，并且生成相应的截图何ReID Features
P_estimate = mp.Process(target=Pose_Estimate, args=(opt, Pose_opt, C_T_output_queue, Pose_output_queue))
P_estimate.daemon = True
P_estimate.start()