def main(args):
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
if os.path.isfile(args.config):
config.merge_from_file(args.config)
config.freeze()
model = build_tracker(config.MODEL)
if os.path.isfile(args.model):
model.load_state_dict(torch.load(args.model, map_location='cpu'))
model.cuda().eval()
h, w = [int(s) for s in args.insize.split('x')]
tracker = JDETracker()
if os.path.isfile(args.img_path):
dataloader = dataset.VideoLoader(args.img_path, (h,w,3))
else:
dataloader = dataset.ImagesLoader(args.img_path, (h,w,3), formats=['*.jpg', '*.png'])
strs = re.split(r'[\\, /]', args.img_path)
imgpath = os.path.join(args.workspace, 'result', strs[-3], 'img')
mkdir(imgpath)
traj_path = os.path.join(args.workspace, 'result', '{}.txt'.format(strs[-3]))
os.system('rm -f {}'.format(os.path.join(imgpath, '*')))
for i, (path, im, lb_im) in enumerate(dataloader):
input = torch.from_numpy(lb_im).unsqueeze(0).to(device)
with torch.no_grad():
outputs = model(input)
print('{} {} {} {}'.format(path, im.shape, lb_im.shape, outputs.size()), end=' ')
outputs = nonmax_suppression(outputs, args.score_thresh, args.iou_thresh)[0]
if outputs is None:
print('no object detected!')
segments = re.split(r'[\\, /]', path)
cv2.imwrite(os.path.join(imgpath, segments[-1]), im)
continue
print('{}'.format(outputs.size()), end=' ')
outputs[:, :4] = ltrb_net2img(outputs[:, :4], (h,w), im.shape[:2])
if not args.only_detect:
trajectories = tracker.update(outputs.numpy())
print('{}'.format(len(trajectories)))
result = overlap_trajectory(trajectories, im)
save_trajectories(traj_path, trajectories, i + 1)
else:
print('')
result = overlap(outputs, im)
segments = re.split(r'[\\, /]', path)
cv2.imwrite(os.path.join(imgpath, segments[-1]), result)
os.system('ffmpeg -f image2 -i {} {}.mp4 -y'.format(os.path.join(imgpath, '%06d.jpg'),
os.path.join(args.workspace, 'result', strs[-3])))
def main(args):
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
# if args.backbone == 'darknet':
# model = darknet.DarkNet(np.random.randint(0, 100, (12, 2))).to(device)
# elif args.backbone == 'shufflenetv2':
# model = shufflenetv2.ShuffleNetV2(np.random.randint(0, 100, (12, 2)),
# model_size=args.thin).to(device)
# else:
# print('unknown backbone architecture!')
# sys.exit(0)
#
# # load state dict except the classifier layer
# model_dict = model.state_dict()
# trained_model_dict = torch.load(os.path.join(args.model), map_location='cpu')
# trained_model_dict = {k : v for (k, v) in trained_model_dict.items() if k in model_dict}
# trained_model_dict = collections.OrderedDict(trained_model_dict)
# model_dict.update(trained_model_dict)
# model.load_state_dict(model_dict)
#
# model.eval()
if os.path.isfile(args.config):
config.merge_from_file(args.config)
config.freeze()
model = build_tracker(config.MODEL)
if os.path.isfile(args.model):
model.load_state_dict(torch.load(args.model, map_location='cpu'))
model.cuda().eval()
# if '320x576' in args.insize:
# anchors = ((6,16), (8,23), (11,32), (16,45),
# (21,64), (30,90), (43,128), (60,180),
# (85,255), (120,360), (170,420), (340,320))
# elif '480x864' in args.insize:
# anchors = ((6,19), (9,27), (13,38), (18,54),
# (25,76), (36,107), (51,152), (71,215),
# (102,305), (143,429), (203,508), (407,508))
# elif '608x1088' in args.insize:
# anchors = ((8,24), (11,34), (16,48), (23,68),
# (32,96), (45,135), (64,192), (90,271),
# (128,384), (180,540), (256,640), (512,640))
h, w = [int(s) for s in args.insize.split('x')]
# decoder = jde.JDEcoder((h, w), embd_dim=args.embedding)
tracker = JDETracker()
if os.path.isfile(args.img_path):
dataloader = dataset.VideoLoader(args.img_path, (h, w, 3))
else:
dataloader = dataset.ImagesLoader(args.img_path, (h, w, 3),
formats=['*.jpg', '*.png'])
strs = re.split(r'[\\, /]', args.img_path)
imgpath = os.path.join(args.workspace, 'result', strs[-3], 'img')
mkdir(imgpath)
traj_path = os.path.join(args.workspace, 'result',
'{}.txt'.format(strs[-3]))
os.system('rm -f {}'.format(os.path.join(imgpath, '*')))
for i, (path, im, lb_im) in enumerate(dataloader):
input = torch.from_numpy(lb_im).unsqueeze(0).to(device)
with torch.no_grad():
outputs = model(input)
# outputs = decoder(outputs)
print('{} {} {} {}'.format(path, im.shape, lb_im.shape,
outputs.size()),
end=' ')
outputs = nonmax_suppression(outputs, args.score_thresh,
args.iou_thresh)[0]
if outputs is None:
print('no object detected!')
segments = re.split(r'[\\, /]', path)
cv2.imwrite(os.path.join(imgpath, segments[-1]), im)
continue
print('{}'.format(outputs.size()), end=' ')
outputs[:, :4] = ltrb_net2img(outputs[:, :4], (h, w), im.shape[:2])
if not args.only_detect:
trajectories = tracker.update(outputs.numpy())
print('{}'.format(len(trajectories)))
result = overlap_trajectory(trajectories, im)
save_trajectories(traj_path, trajectories, i + 1)
else:
print('')
result = overlap(outputs, im)
segments = re.split(r'[\\, /]', path)
cv2.imwrite(os.path.join(imgpath, segments[-1]), result)
os.system('ffmpeg -f image2 -i {} {}.mp4 -y'.format(
os.path.join(imgpath, '%06d.jpg'),
os.path.join(args.workspace, 'result', strs[-3])))
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = shufflenetv2.ShuffleNetV2().to(device)
model_dict = model.state_dict()
trained_model_dict = torch.load(args.model, map_location='cpu')
trained_model_dict = {k : v for (k, v) in trained_model_dict.items() if k in model_dict}
trained_model_dict = collections.OrderedDict(trained_model_dict)
model_dict.update(trained_model_dict)
model.load_state_dict(model_dict)
model.eval()
h, w = args.in_size
decoder = jde.JDEcoder(args.in_size, embd_dim=args.embedding)
dataloader = dataset.VideoLoader(args.video, (h, w, 3))
mkdir(os.path.join(args.save_path, 'images'))
mkdir(os.path.join(args.save_path, 'labels_with_ids'))
for i, (path, im, lb_im) in enumerate(dataloader):
input = torch.from_numpy(lb_im).unsqueeze(0).to(device)
with torch.no_grad():
outputs = model(input)
outputs = decoder(outputs)
outputs = tracker.nonmax_suppression(outputs, args.score_thresh, args.iou_thresh)[0]
if outputs is not None:
segments = re.split(r'[\\, /]', path)
outdir = os.path.join(args.save_path, 'images', segments[-1])
cv2.imwrite(outdir, im)
outdir = outdir.replace('images', 'labels_with_ids').replace('jpg', 'txt')
with open(outdir, 'w') as file:
if param.requires_grad:
params_to_update.append(param)
print("\t", name)
return torch.optim.SGD(params_to_update, lr=0.01, momentum=0.9)
if __name__ == "__main__":
train_mode = False
# setup dataset
from preprocess import Preprocess
directory = '/home/ds/Data/academic/dataset_v2'
transform = Preprocess.get_transform(224)
loader = dataset.VideoLoader(directory, transform)
train_loader = loader.get_train_loader(batch_size=1)
val_loader = loader.get_val_loader(batch_size=1)
test_loader = loader.get_test_loader(batch_size=1)
# setup model
model, buffer = initialize_model("result2.pth")
# setup trainer
criterion = torch.nn.CrossEntropyLoss()
optimizer = create_optimizer(model)
# setup logger
logging.basicConfig(level=logging.INFO, filename='training_log1.txt')
model = model.to(device)