def run(config):
# Get loader
config['drop_last'] = False
loaders = utils.get_data_loaders(**config)
# Load inception net
net = inception_utils.load_inception_net(parallel=config['parallel'])
pool, logits, labels = [], [], []
device = 'cuda'
for i, (x, y) in enumerate(tqdm(loaders[0])):
x = x.to(device)
with torch.no_grad():
pool_val, logits_val = net(x)
pool += [np.asarray(pool_val.cpu())]
logits += [np.asarray(F.softmax(logits_val, 1).cpu())]
labels += [np.asarray(y.cpu())]
pool, logits, labels = [np.concatenate(item, 0) for item in [pool, logits, labels]]
# uncomment to save pool, logits, and labels to disk
# print('Saving pool, logits, and labels to disk...')
# np.savez(config['dataset']+'_inception_activations.npz',
# {'pool': pool, 'logits': logits, 'labels': labels})
# Calculate inception metrics and report them
print('Calculating inception metrics...')
IS_mean, IS_std = inception_utils.calculate_inception_score(logits)
print('Training data from dataset %s has IS of %5.5f +/- %5.5f' % (config['dataset'], IS_mean, IS_std))
# Prepare mu and sigma, save to disk. Remove "hdf5" by default
# (the FID code also knows to strip "hdf5")
print('Calculating means and covariances...')
mu, sigma = np.mean(pool, axis=0), np.cov(pool, rowvar=False)
print('Saving calculated means and covariances to disk...')
np.savez(config['dataset'].strip('_hdf5')+'_inception_moments.npz', **{'mu' : mu, 'sigma' : sigma})
def run(config):
logger = logging.getLogger('tl')
saved_inception_moments = global_cfg.saved_inception_moments.format(
config['dataset'])
# Get loader
config['drop_last'] = False
loaders = utils.get_data_loaders(use_data_root=True, **config)
# Load inception net
net = inception_utils.load_inception_net(parallel=config['parallel'])
net.eval()
# net.train()
pool, logits, labels = [], [], []
device = 'cuda'
pbar = tqdm(loaders[0], desc='accumulate pool and logits')
for i, (x, y) in enumerate(pbar):
x = x.to(device)
with torch.no_grad():
pool_val, logits_val = net(x)
pool += [np.asarray(pool_val.cpu())]
logits += [np.asarray(F.softmax(logits_val, 1).cpu())]
labels += [np.asarray(y.cpu())]
pool, logits, labels = [
np.concatenate(item, 0) for item in [pool, logits, labels]
]
# uncomment to save pool, logits, and labels to disk
# print('Saving pool, logits, and labels to disk...')
# np.savez(config['dataset']+'_inception_activations.npz',
# {'pool': pool, 'logits': logits, 'labels': labels})
# Calculate inception metrics and report them
logger.info('Calculating inception metrics...')
IS_mean, IS_std = inception_utils.calculate_inception_score(logits)
logger.info('Training data from dataset %s has IS of %5.5f +/- %5.5f' %
(config['dataset'], IS_mean, IS_std))
# Prepare mu and sigma, save to disk. Remove "hdf5" by default
# (the FID code also knows to strip "hdf5")
logger.info('Calculating means and covariances...')
mu, sigma = np.mean(pool, axis=0), np.cov(pool, rowvar=False)
logger.info('Saving calculated means and covariances to disk...')
logger.info(f'Save to {saved_inception_moments}')
os.makedirs(os.path.dirname(saved_inception_moments), exist_ok=True)
np.savez(saved_inception_moments, **{'mu': mu, 'sigma': sigma})
pass
def run(config):
# Get loader
config['drop_last'] = False
if config["dataset"] == "FFHQ":
imsize = 256
root = os.path.join(os.environ["SSD"], "images256x256")
root_perm = os.path.join(os.environ["SSD"], "images256x256")
transform = transforms.Compose([
transforms.Scale(imsize),
transforms.CenterCrop(imsize),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5]),
])
batch_size = 100 #config['batch_size']
dataset = FFHQ(root=root, transform=transform, test_mode=False)
data_loader = DataLoader(dataset,
batch_size,
shuffle=True,
drop_last=True)
loaders = [data_loader]
elif config["dataset"] == "coco":
imsize = 128
batch_size = config['batch_size']
transform = transforms.Compose([
transforms.Resize(imsize),
transforms.CenterCrop(imsize),
#transforms.RandomHorizontalFlip(),
#transforms.ColorJitter(brightness=0.01, contrast=0.01, saturation=0.01, hue=0.01),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)),
])
classes = [
'bird', 'cat', 'dog', 'horse', 'sheep', 'cow', 'elephant',
'monkey', 'zebra', 'giraffe'
]
root = None
root_perm = None
dataset = CocoAnimals(root=root,
batch_size=batch_size,
classes=classes,
transform=transform,
masks=False,
return_all=True,
test_mode=False,
imsize=imsize)
data_loader = DataLoader(dataset,
batch_size,
drop_last=True,
num_workers=1,
shuffle=True) #,shuffle=False)
loaders = [data_loader]
else:
loaders = utils.get_data_loaders(**config)
# Load inception net
net = inception_utils.load_inception_net(parallel=config['parallel'])
pool, logits, labels = [], [], []
device = 'cuda'
used_samples = 0
for e in range(2):
for i, batch_data in enumerate(tqdm(loaders[0])):
x = batch_data[0]
y = batch_data[1]
x = x.to(device)
with torch.no_grad():
pool_val, logits_val = net(x)
pool += [np.asarray(pool_val.cpu())]
logits += [np.asarray(F.softmax(logits_val, 1).cpu())]
labels += [np.asarray(y.cpu())]
used_samples += x.size(0)
if used_samples >= 50000:
break
pool, logits, labels = [
np.concatenate(item, 0) for item in [pool, logits, labels]
]
# uncomment to save pool, logits, and labels to disk
# print('Saving pool, logits, and labels to disk...')
# np.savez(config['dataset']+'_inception_activations.npz',
# {'pool': pool, 'logits': logits, 'labels': labels})
# Calculate inception metrics and report them
print('Calculating inception metrics...')
IS_mean, IS_std = inception_utils.calculate_inception_score(logits)
print('Training data from dataset %s has IS of %5.5f +/- %5.5f' %
(config['dataset'], IS_mean, IS_std))
# Prepare mu and sigma, save to disk. Remove "hdf5" by default
# (the FID code also knows to strip "hdf5")
print('Calculating means and covariances...')
print(pool.shape)
mu, sigma = np.mean(pool, axis=0), np.cov(pool, rowvar=False)
print('Saving calculated means and covariances to disk...')
np.savez(config['dataset'].strip('_hdf5') + '_inception_moments.npz', **{
'mu': mu,
'sigma': sigma
})
def run(config):
# Get loader
config['drop_last'] = False
loaders = utils.get_data_loaders(**config)
# Load inception net
net = inception_utils.load_inception_net(parallel=config['parallel'])
pool, logits, labels = [], [], []
device = 'cuda'
init = 0
for i, (x, y) in enumerate(tqdm(loaders[0])):
x = x.to(device)
with torch.no_grad():
if torch.sum(y == (init + 1)) > 0:
init += 1
print(y[0], init)
pool_val, logits_val = net(x)
pool += [np.asarray(pool_val.cpu()[y == (init - 1)])]
logits += [
np.asarray(
F.softmax(logits_val[y == (init - 1)], 1).cpu())
]
labels += [np.asarray(y.cpu()[y == (init - 1)])]
pool, logits, labels = [
np.concatenate(item, 0) for item in [pool, logits, labels]
]
print('Calculating inception metrics...')
IS_mean, IS_std = inception_utils.calculate_inception_score(
logits)
print(
'Training data from dataset %s has IS of %5.5f +/- %5.5f' %
(config['dataset'], IS_mean, IS_std))
print('Calculating means and covariances...')
mu, sigma = np.mean(pool, axis=0), np.cov(pool, rowvar=False)
print('Saving calculated means and covariances to disk...')
np.savez(
'../inception_moment/' + str(init - 1) + '_' +
config['dataset'].strip('_hdf5') +
'_inception_moments.npz', **{
'mu': mu,
'sigma': sigma
})
pool, logits, labels = [], [], []
pool_val, logits_val = net(x)
pool += [np.asarray(pool_val.cpu()[y == (init)])]
logits += [
np.asarray(F.softmax(logits_val[y == (init)], 1).cpu())
]
labels += [np.asarray(y.cpu()[y == (init)])]
else:
pool_val, logits_val = net(x)
pool += [np.asarray(pool_val.cpu())]
logits += [np.asarray(F.softmax(logits_val, 1).cpu())]
labels += [np.asarray(y.cpu())]
pool, logits, labels = [
np.concatenate(item, 0) for item in [pool, logits, labels]
]
print('Calculating inception metrics...')
IS_mean, IS_std = inception_utils.calculate_inception_score(logits)
print('Training data from dataset %s has IS of %5.5f +/- %5.5f' %
(config['dataset'], IS_mean, IS_std))
print('Calculating means and covariances...')
mu, sigma = np.mean(pool, axis=0), np.cov(pool, rowvar=False)
print('Saving calculated means and covariances to disk...')
np.savez(
'../inception_moment/' + str(init - 1) + '_' +
config['dataset'].strip('_hdf5') + '_inception_moments.npz', **{
'mu': mu,
'sigma': sigma
})
def run(config):
unique_id = datetime.datetime.now().strftime('%Y%m-%d%H-%M%S-')
tensorboard_path = os.path.join(config['logs_root'], 'tensorboard_logs',
unique_id)
os.makedirs(tensorboard_path)
writer = SummaryWriter(log_dir=tensorboard_path)
# Get loader
config['drop_last'] = False
frame_size = utils.imsize_dict[config['dataset']] #112
print('Dataset:', config['dataset'], 'Frame size:', frame_size)
loaders = utils.get_video_data_loaders(num_epochs=1,
frame_size=frame_size,
**config)
# Load inception net
net = inception_utils.load_r2plus1d_18_net(parallel=config['parallel'])
pool, logits, labels = [], [], []
device = 'cuda'
accu_correct, accu_total = 0, 0
# norm_mean = [-0.43216/0.22803, -0.394666/0.22145, -0.37645/0.216989]
# norm_std = [1/0.22803, 1/0.22145, 1/0.216989]
# norm_mean = torch.tensor([0.43216, 0.394666, 0.37645]).to(device)
# norm_std = torch.tensor([0.22803, 0.22145, 0.216989]).to(device)
norm_mean = torch.tensor([0.5, 0.5, 0.5]).to(device)
norm_std = torch.tensor([0.5, 0.5, 0.5]).to(device)
transform_tensorboard = dset.VideoNormalize(norm_mean, norm_std)
for i, (x, y) in enumerate(tqdm(loaders[0])):
x = x.to(device) #[B,T,C,H,W]
# print('x shape',x.shape)
if i % 100 == 0:
# t_x = transform_tensorboard(x[0].permute(1,0,2,3).contiguous()).permute(1,0,2,3).unsqueeze(0)
t_x = x * norm_std[None, None, :, None,
None] + norm_mean[None, None, :, None, None]
print('Range:', t_x.min(), t_x.max())
writer.add_video('Loaded Data', t_x, i)
with torch.no_grad():
pool_val, logits_val = net(x)
pool += [np.asarray(pool_val.cpu())]
logits += [np.asarray(F.softmax(logits_val, 1).cpu())]
labels += [np.asarray(y.cpu())]
accu_correct += int(
sum(
F.softmax(logits_val, 1).cpu().argmax(1).squeeze() ==
y.cpu().squeeze()))
accu_total += len(np.asarray(y.cpu()).squeeze())
if i % 10 == 0:
print(F.softmax(logits_val, 1).cpu()[0])
print('Accumulated coorect predictions:', accu_correct)
print('Accumulated total number of samples:', accu_total)
print('Accumulated prediction accuracy is:',
accu_correct / accu_total)
pool, logits, labels = [
np.concatenate(item, 0) for item in [pool, logits, labels]
]
# uncomment to save pool, logits, and labels to disk
# print('Saving pool, logits, and labels to disk...')
# np.savez(config['dataset']+'_inception_activations.npz',
# {'pool': pool, 'logits': logits, 'labels': labels})
# Calculate inception metrics and report them
print('Calculating inception metrics...')
IS_mean, IS_std = inception_utils.calculate_inception_score(logits)
print('Training data from dataset %s has IS of %5.5f +/- %5.5f' %
(config['dataset'], IS_mean, IS_std))
# Prepare mu and sigma, save to disk. Remove "hdf5" by default
# (the FID code also knows to strip "hdf5")
print('Calculating means and covariances...')
mu, sigma = np.mean(pool, axis=0), np.cov(pool, rowvar=False)
print('Saving calculated means and covariances to disk...')
np.savez(config['dataset'].strip('_hdf5') + '_inception_moments.npz', **{
'mu': mu,
'sigma': sigma
})
