def load_model(opt, pretrained_path):
seed = int(time.time())
use_cuda = True
gpus = '0'
torch.manual_seed(seed)
if use_cuda:
os.environ['CUDA_VISIBLE_DEVICES'] = gpus
torch.cuda.manual_seed(seed)
# Create model
model = YOWO(opt)
model = model.cuda()
# model = nn.DataParallel(model, device_ids=None) # in multi-gpu case
model.seen = 0
checkpoint = torch.load(pretrained_path)
epoch = checkpoint['epoch']
fscore = checkpoint['fscore']
model.load_state_dict(checkpoint['state_dict'], strict=False)
return model, epoch, fscore
use_cuda = True
kwargs = {'num_workers': 0, 'pin_memory': True} if use_cuda else {}
# Create model
model = YOWO(opt)
model = model.cuda()
model = nn.DataParallel(model, device_ids=None) # in multi-gpu case
print(model)
# Load resume path
if opt.resume_path:
print("===================================================================")
print('loading checkpoint {}'.format(opt.resume_path))
checkpoint = torch.load(opt.resume_path)
model.load_state_dict(checkpoint['state_dict'])
model.eval()
print("===================================================================")
def get_clip(root, imgpath, train_dur, dataset):
im_split = imgpath.split('/')
num_parts = len(im_split)
class_name = im_split[-3]
file_name = im_split[-2]
im_ind = int(im_split[num_parts - 1][0:5])
if dataset == 'ucf101-24':
img_name = os.path.join(class_name, file_name, '{:05d}.jpg'.format(im_ind))
elif dataset == 'jhmdb-21':
img_name = os.path.join(class_name, file_name, '{:05d}.png'.format(im_ind))
if opt.resume_path:
print(
"===================================================================")
print('loading checkpoint {}'.format(opt.resume_path))
checkpoint = torch.load(opt.resume_path)
opt.begin_epoch = checkpoint['epoch']
best_fscore = checkpoint['fscore']
pretrained_dict = checkpoint['state_dict']
model_dict = model.state_dict()
pretrained_dict = {
k: v
for k, v in pretrained_dict.items()
if k in model_dict and k != 'module.cfam.conv_bn_relu1.0.weight'
}
model_dict.update(pretrained_dict)
model.load_state_dict(model_dict)
# model.load_state_dict(checkpoint['state_dict'])
#optimizer.load_state_dict(checkpoint['optimizer'])
model.seen = checkpoint['epoch'] * nsamples
print("Loaded model fscore: ", checkpoint['fscore'])
print(
"===================================================================")
region_loss.seen = model.seen
processed_batches = model.seen // batch_size
init_width = int(net_options['width'])
init_height = int(net_options['height'])
init_epoch = model.seen // nsamples