[GroupScale(net.scale_size),
GroupCenterCrop(net.input_size)])
elif args.test_crops == 10:
cropping = torchvision.transforms.Compose(
[GroupOverSample(net.input_size, net.scale_size)])
else:
raise ValueError(
"Only 1 and 10 crops are supported while we got {}".format(
args.test_crops))
if not args.use_reference and not args.use_kinetics_reference:
checkpoint = torch.load(args.weights)
else:
model_url = get_reference_model_url(
args.dataset,
args.modality,
"ImageNet" if args.use_reference else "Kinetics",
args.arch,
)
checkpoint = model_zoo.load_url(model_url)
print(("using reference model: {}".format(model_url)))
print(("model epoch {} loss: {}".format(checkpoint["epoch"],
checkpoint["best_loss"])))
base_dict = {
".".join(k.split(".")[1:]): v
for k, v in list(checkpoint["state_dict"].items())
}
stats = checkpoint["reg_stats"].numpy()
dataset = SSNDataSet(
"",
if args.test_crops == 1:
cropping = torchvision.transforms.Compose([
GroupScale(net.scale_size),
GroupCenterCrop(net.input_size),
])
elif args.test_crops == 10:
cropping = torchvision.transforms.Compose([
GroupOverSample(net.input_size, net.scale_size)
])
else:
raise ValueError("Only 1 and 10 crops are supported while we got {}".format(args.test_crops))
if not args.use_reference and not args.use_kinetics_reference:
checkpoint = torch.load(args.weights)
else:
model_url = get_reference_model_url(args.dataset, args.modality,
'ImageNet' if args.use_reference else 'Kinetics', args.arch)
checkpoint = model_zoo.load_url(model_url)
print("using reference model: {}".format(model_url))
print("model epoch {} loss: {}".format(checkpoint['epoch'], checkpoint['best_loss']))
base_dict = {'.'.join(k.split('.')[1:]): v for k, v in list(checkpoint['state_dict'].items())}
stats = checkpoint['reg_stats'].numpy()
dataset = SSNDataSet("", test_prop_file,
new_length=data_length,
modality=args.modality,
aug_seg=2, body_seg=5,
image_tmpl="img_{:05d}.jpg" if args.modality in ["RGB",
"RGBDiff"] else args.flow_pref + "{}_{:05d}.jpg",
test_mode=True, test_interval=args.frame_interval,
transform=torchvision.transforms.Compose([
GroupScale(net.scale_size),
GroupCenterCrop(net.input_size),
])
elif args.test_crops == 10:
cropping = torchvision.transforms.Compose(
[GroupOverSample(net.input_size, net.scale_size)])
else:
raise ValueError(
"Only 1 and 10 crops are supported while we got {}".format(
args.test_crops))
if not args.use_reference and not args.use_kinetics_reference:
checkpoint = torch.load(args.weights)
else:
model_url = get_reference_model_url(
args.dataset, args.modality,
'ImageNet' if args.use_reference else 'Kinetics', args.arch)
checkpoint = model_zoo.load_url(model_url)
print("using reference model: {}".format(model_url))
print("model epoch {} loss: {}".format(checkpoint['epoch'],
checkpoint['best_loss']))
base_dict = {
'.'.join(k.split('.')[1:]): v
for k, v in list(checkpoint['state_dict'].items())
}
stats = checkpoint['reg_stats'].numpy()
dataset = SSNDataSet(
"",
test_prop_file,