def __init__(self, root_dir, model_path, save_dir=None):
self.root_dir = root_dir
self.transform = transforms.Compose([Normalize(), ToTensor()])
self.model_path = model_path
self.model = model.GoNet()
if use_gpu:
self.model = self.model.cuda()
self.model.load_state_dict(torch.load(model_path))
frames = os.listdir(root_dir + '/img')
frames = [root_dir + "/img/" + frame for frame in frames]
self.len = len(frames) - 1
frames = np.array(frames)
frames.sort()
self.x = []
for i in xrange(self.len):
self.x.append([frames[i], frames[i + 1]])
self.x = np.array(self.x)
# uncomment to select rectangle manually
# init_bbox = bbox_coordinates(self.x[0][0])
f = open(root_dir + '/groundtruth_rect.txt')
lines = f.readlines()
init_bbox = lines[0].strip().split('\t')
init_bbox = [float(x) for x in init_bbox]
init_bbox = [
init_bbox[0], init_bbox[1], init_bbox[0] + init_bbox[2],
init_bbox[1] + init_bbox[3]
]
init_bbox = np.array(init_bbox)
print init_bbox
self.prev_rect = init_bbox
def main():
args = parser.parse_args()
print args
# load dataset
transform = transforms.Compose([Normalize(), ToTensor()])
alov = datasets.ALOVDataset('../data/alov300/imagedata++/',
'../data/alov300/alov300++_rectangleAnnotation_full/',
transform)
dataloader = DataLoader(alov, batch_size=args.batch_size, shuffle=True, num_workers=4)
# load model
net = model.GoNet()
loss_fn = torch.nn.L1Loss(size_average = False)
if use_gpu:
net = net.cuda()
loss_fn = loss_fn.cuda()
optimizer = optim.SGD(net.classifier.parameters(), lr=args.learning_rate, momentum=args.momentum)
if os.path.exists(args.save_directory):
print('Directory %s already exists' % (args.save_directory))
else:
os.makedirs(args.save_directory)
# start training
net = train_model(net, dataloader, loss_fn, optimizer, args.epochs, args.learning_rate, args.save_directory)
def main():
global args, batchSize, kSaveModel, bb_params
args = parser.parse_args()
print(args)
batchSize = args.batch_size
kSaveModel = args.save_freq
np.random.seed(args.manual_seed)
torch.manual_seed(args.manual_seed)
if cuda:
torch.cuda.manual_seed_all(args.manual_seed)
# load bounding box motion model params
bb_params['lambda_shift_frac'] = args.lambda_shift_frac
bb_params['lambda_scale_frac'] = args.lambda_scale_frac
bb_params['min_scale'] = args.min_scale
bb_params['max_scale'] = args.max_scale
# load datasets
alov = ALOVDataset(
os.path.join(args.data_directory, 'imagedata++/'),
os.path.join(args.data_directory,
'alov300++_rectangleAnnotation_full/'), transform,
input_size)
imagenet = ILSVRC2014_DET_Dataset(
os.path.join(args.data_directory, 'ILSVRC2014_DET_train/'),
os.path.join(args.data_directory, 'ILSVRC2014_DET_bbox_train/'),
bb_params, transform, input_size)
# list of datasets to train on
datasets = [alov, imagenet]
# load model
net = model.GoNet().to(device)
# summary(net, [(3, 224, 224), (3, 224, 224)])
loss_fn = torch.nn.L1Loss(size_average=False).to(device)
# initialize optimizer
optimizer = optim.SGD(net.classifier.parameters(),
lr=args.learning_rate,
momentum=args.momentum,
weight_decay=args.weight_decay)
if os.path.exists(args.save_directory):
print('Directory %s already exists' % (args.save_directory))
else:
os.makedirs(args.save_directory)
# start training
net = train_model(net, datasets, loss_fn, optimizer)
# save trained model
checkpoint = {'state_dict': net.state_dict()}
path = os.path.join(args.save_directory, 'pytorch_goturn.pth.tar')
torch.save(checkpoint, path)
def __init__(self, root_dir, model_path, save_dir=None):
self.root_dir = root_dir
self.transform = transforms.Compose([Normalize(), ToTensor()])
self.model_path = model_path
self.model = model.GoNet()
if use_gpu:
self.model = self.model.cuda()
self.model.load_state_dict(torch.load(model_path))
frames = os.listdir(root_dir)
self.len = len(frames) - 1
frames = [root_dir + "/" + frame for frame in frames]
frames = np.array(frames)
frames.sort()
self.x = []
for i in xrange(self.len):
self.x.append([frames[i], frames[i + 1]])
self.x = np.array(self.x)
# code for previous rectange
init_bbox = bbox_coordinates(self.x[0][0])
print init_bbox
self.prev_rect = init_bbox
def main():
global args
args = parser.parse_args()
print(args)
np.random.seed(args.manual_seed)
torch.manual_seed(args.manual_seed)
if use_gpu:
torch.cuda.manual_seed(args.manual_seed)
# load datasets
alov = ALOVDataset('../data/alov300/imagedata++/',
'../data/alov300/alov300++_rectangleAnnotation_full/',
transform)
imagenet = ILSVRC2014_DET_Dataset('../data/imagenet_img/',
'../data/imagenet_bbox/', transform,
args.lambda_shift_frac,
args.lambda_scale_frac, args.min_scale,
args.max_scale)
# list of datasets to train on
datasets = [alov, imagenet]
# load model
net = model.GoNet()
loss_fn = torch.nn.L1Loss(size_average=False)
if use_gpu:
net = net.cuda()
loss_fn = loss_fn.cuda()
# initialize optimizer
optimizer = optim.SGD(net.classifier.parameters(),
lr=args.learning_rate,
weight_decay=0.0005)
if os.path.exists(args.save_directory):
print('Directory %s already exists' % (args.save_directory))
else:
os.makedirs(args.save_directory)
# start training
net = train_model(net, datasets, loss_fn, optimizer)
# cv2.rectangle(srch,(x1_sc,y1_sc),(x2_sc,y2_sc),(255,0,0),3)
# cv2.rectangle(srch,(srch_xc-x_len,srch_yc-y_len),(srch_xc+x_len,srch_yc+y_len),(0,255,0),3)
# cv2.rectangle(image_srch,(x1+x1_sc,y1+y1_sc),(x1+x2_sc,y1+y2_sc),(255,0,0),3)
# cv2.rectangle(image_srch,(loc_srch[0],loc_srch[1]),(loc_srch[2],loc_srch[3]),(0,255,0),3)
# cv2.imwrite("srch.jpg", srch)
# cv2.imwrite("full_srch.jpg", image_srch)
return pd,x1,y1
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
m = nn.DataParallel(model.GoNet())
if os.path.exists("go_turn.pth"):
m.load_state_dict(torch.load("go_turn.pth")['state_dict'])
print("pretrained model loaded")
else:
print("Couldnot find trained model. Exitting")
sys.exit()
m.to(device)
m.eval()
op_summary =""
acc = mm.MOTAccumulator(auto_id=True)
folders = [700,800,900]
for fldr in folders:
if not os.path.exists("/ssd_scratch/cvit/bsr/"):
op = subprocess.run(["mkdir","/ssd_scratch/cvit/bsr"])
if not os.path.exists("/ssd_scratch/cvit/bsr/"+fldr):
def main():
global args
args = parser.parse_args()
print(args)
np.random.seed(args.manual_seed)
torch.manual_seed(args.manual_seed)
if use_gpu:
torch.cuda.manual_seed(args.manual_seed)
# load datasets
alov = ALOVDataset('../data/alov300/imagedata++/',
'../data/alov300/alov300++_rectangleAnnotation_full/',
transform)
imagenet = ILSVRC2014_DET_Dataset('../data/imagenet_img/',
'../data/imagenet_bbox/', transform,
args.lambda_shift_frac,
args.lambda_scale_frac, args.min_scale,
args.max_scale)
# list of datasets to train on
datasets = [alov, imagenet]
# load model
net = model.GoNet()
loss_fn = torch.nn.L1Loss(size_average=False)
if use_gpu:
net = net.cuda()
loss_fn = loss_fn.cuda()
# initialize optimizer
trainable_weights = []
trainable_bias = []
for name, param in net.classifier.named_parameters():
if 'weight' in name:
trainable_weights.append(param)
elif 'bias' in name:
trainable_bias.append(param)
optimizer = optim.SGD([{
'params': trainable_weights,
'lr': args.learning_rate * 10
}, {
'params': trainable_bias,
'lr': args.learning_rate * 20
}],
lr=args.learning_rate,
momentum=args.momentum,
weight_decay=args.weight_decay)
if os.path.exists(args.save_directory):
print('Directory %s already exists' % (args.save_directory))
else:
os.makedirs(args.save_directory)
# start training
net = train_model(net, datasets, loss_fn, optimizer)
# save trained model
path = os.path.join(args.save_directory, 'final_model.pth')
torch.save(net.state_dict(), path)
