def main(argv, common_opts):
args = parse_args(argv)
seed_all(12345)
init_algorithms(deterministic=True)
torch.set_grad_enabled(False)
device = common_opts['device']
if args.model:
# model = load_model(args.model).to(device).eval()
model = load_model(args.model).eval()
data_specs = model.data_specs
else:
model = None
data_specs = DataSpecs(
ImageSpecs(224,
mean=ImageSpecs.IMAGENET_MEAN,
stddev=ImageSpecs.IMAGENET_STDDEV),
JointsSpecs(CanonicalSkeletonDesc, n_dims=3),
)
dataset = get_dataset(args.dataset, data_specs, use_aug=False)
app = MainGUIApp(dataset, device, model)
app.mainloop()
def main(argv, common_opts):
args = parse_args(argv)
seed_all(12345)
init_algorithms(deterministic=True)
torch.set_grad_enabled(False)
device = common_opts['device']
model = load_model(args.model).to(device).eval()
dataset = get_dataset(args.dataset, model.data_specs, use_aug=False)
if args.multicrop:
dataset.multicrop = True
loader = make_unbatched_dataloader(dataset)
else:
loader = make_dataloader(dataset, batch_size=1)
if args.dataset.startswith('h36m-'):
known_depth = True
included_joints = list(range(CanonicalSkeletonDesc.n_joints))
else:
known_depth = False
included_joints = [
CanonicalSkeletonDesc.joint_names.index(joint_name)
for joint_name in VNect_Common_Skeleton
]
print('Use ground truth root joint depth? {}'.format(known_depth))
print('Number of joints in evaluation: {}'.format(len(included_joints)))
df = run_evaluation_3d(model,
device,
loader,
included_joints,
known_depth=known_depth,
print_progress=True)
print('### By sequence')
print()
print(
tabulate(df.drop(columns=['activity_id']).groupby('seq_id').mean(),
headers='keys',
tablefmt='pipe'))
print()
print('### By activity')
print()
print(
tabulate(df.drop(columns=['seq_id']).groupby('activity_id').mean(),
headers='keys',
tablefmt='pipe'))
print()
print('### Overall')
print()
print(
tabulate(
df.drop(columns=['activity_id', 'seq_id']).mean().to_frame().T,
headers='keys',
tablefmt='pipe'))
def _create_dataloader(dataset_names, data_specs, batch_size,
examples_per_epoch, use_aug):
datasets = [
get_dataset(name, data_specs, use_aug=use_aug)
for name in dataset_names
]
assert len(datasets) > 0, 'at least one dataset must be specified'
if len(datasets) == 1:
dataset = datasets[0]
else:
dataset = MixedPoseDataset(datasets)
return make_dataloader(
dataset,
sampler=dataset.sampler(examples_per_epoch=examples_per_epoch),
batch_size=batch_size,
drop_last=True,
num_workers=4,
)
