def __init__(self, **kwargs):
default_tf = {
'first': (tf.Resize((224, 224)),),
'rgb': (tf.ToTensor(),),
'depth': (tf.ToTensor(), tf.DepthTransform())
}
pruning = kwargs.pop('pruning', 0.9)
sparse_pruning = kwargs.pop('sparse_pruning', False)
Base.__init__(self,
transform=kwargs.pop('transform', default_tf),
**kwargs)
self.folders = list()
with open(self.root_path + 'TrainSplit.txt', 'r') as f:
for line in f:
fold = 'seq-{:02d}/'.format(int(re.search('(?<=sequence)\d', line).group(0)))
self.folders.append(self.root_path + fold)
self.load_data()
if sparse_pruning:
step = round(1 / (1-pruning))
logger.info('Computed step for pruning: {}'.format(step))
self.data = [dat for i, dat in enumerate(self.data) if i % step == 0]
else:
self.data = self.data[round(len(self.data)*pruning):]
def __init__(self, **kwargs):
default_tf = {
'first': (tf.Resize((224, 224)),),
'rgb': (tf.ToTensor(),),
'depth': (tf.ToTensor(), tf.DepthTransform())
}
pruning = kwargs.pop('pruning', 0.9)
sparse_pruning = kwargs.pop('sparse_pruning', False)
Base.__init__(self,
transform=kwargs.pop('transform', default_tf),
**kwargs)
data_file_name = self.root_path + 'dataset_train.txt'
self.data = pd.read_csv(data_file_name, header=1, sep=' ').values
if sparse_pruning:
step = round(1 / (1-pruning))
logger.info('Computed step for pruning: {}'.format(step))
indexor = np.zeros(len(self.data))
for i in range(len(self.data)):
if i % step == 0:
indexor[i] = 1
self.data = self.data[indexor]
else:
self.data = self.data[round(len(self.data)*pruning):]
def __init__(self, root, file, modalities, **kwargs):
self.root = root
self.transform = kwargs.pop('transform', 'default')
self.bearing = kwargs.pop('bearing', True)
self.panorama_split = kwargs.pop('panorama_split', {
'v_split': 3,
'h_split': 2,
'offset': 0
})
if kwargs:
raise TypeError('Unexpected **kwargs: %r' % kwargs)
if self.transform == 'default':
self.transform = {'first': (tf.Resize((224, 224)), tf.ToTensor())}
self.data = pd.read_csv(self.root + file, skiprows=2, sep=';')
self.modalities = modalities
self.used_mod = self.modalities
def __init__(self, **kwargs):
default_tf = {
'first': (tf.Resize((224, 224)),),
'rgb': (tf.ToTensor(),),
'depth': (tf.ToTensor(), tf.DepthTransform())
}
light = kwargs.pop('light', False)
Base.__init__(self,
transform=kwargs.pop('transform', default_tf),
**kwargs)
self.folders = list()
with open(self.root_path + 'TestSplit.txt', 'r') as f:
for line in f:
fold = 'seq-{:02d}/'.format(int(re.search('(?<=sequence)\d', line).group(0)))
self.folders.append(self.root_path + fold)
self.load_data()
if light:
step = 10
self.data = [dat for i, dat in enumerate(self.data) if i % step == 0]
def __init__(self, **kwargs):
default_tf = {
'first': (tf.Resize((224, 224)),),
'rgb': (tf.ToTensor(),),
'depth': (tf.ToTensor(), tf.DepthTransform())
}
light = kwargs.pop('light', False)
Base.__init__(self,
transform=kwargs.pop('transform', default_tf),
**kwargs)
data_file_name = self.root_path + 'dataset_test.txt'
self.data = pd.read_csv(data_file_name, header=1, sep=' ').values
if light:
step = 10
indexor = np.zeros(len(self.data))
for i in range(len(self.data)):
if i % step == 0:
indexor[i] = 1
self.data = self.data[indexor.astype(bool)]
for l in b['pose']['T'].squeeze(0).numpy():
for num in l:
f.write("%16.7e\t" % num)
f.write('\n')
if __name__ == '__main__':
import datasets.SevenScene as SevenS
aug_tf = {
'first': (tf.CenterCrop(480),),
'rgb': (tf.ToTensor(), ),
'depth': (tf.ToTensor(), tf.DepthTransform())
}
std_tf = {
'first': (tf.Resize(256), tf.RandomCrop(224),),
'rgb': (tf.ColorJitter(brightness=0.5, contrast=0.5, saturation=0.5, hue=0.05),
tf.ToTensor(),
tf.Normalize(mean=[0.4684, 0.4624, 0.4690], std=[0.2680, 0.2659, 0.2549])),
'depth': (tf.Resize(56), tf.ToTensor(), tf.DepthTransform())
}
for room in ['pumpkin/', 'chess/', 'red_kitchen/']:
print(room)
root = os.environ['SEVENSCENES'] + room
train_aug_dataset = SevenS.AugmentedTrain(root=root,
transform=aug_tf,
final_depth_size=256,
reduce_fact=1.85,
zoom_percentage=0.15)
spamwriter.writerow(list(zip(id, ranked[i])))
return ranked
if __name__ == '__main__':
logger.setLevel('INFO')
modtouse = {'rgb': 'dataset.txt', 'depth': 'mono_depth_dataset.txt'}
transform = {
'first': (tf.RandomResizedCrop(224), ),
'rgb': (tf.ToTensor(), ),
'depth': (tf.ToTensor(), )
}
transform_eval = {
'first': (
tf.Resize((224, 224)),
tf.ToTensor(),
),
}
query_data = Robotcar.VBLDataset(root=os.environ['ROBOTCAR'] +
'Robotcar_D1/Query/',
modalities={'rgb': 'query.txt'},
coord_file='coordxIm.txt',
transform=transform_eval,
bearing=False)
data = Robotcar.VBLDataset(root=os.environ['ROBOTCAR'] +
'Robotcar_D1/Dataset/',
modalities={'rgb': 'dataset.txt'},
coord_file='coordxIm.txt',
transform=transform_eval,
#q2[1:] *= -1 # Inverse computation
w3 = np.abs(np.dot(q1, q2))
if w3 > 1:
logger.warning('Unproper quaternion q1 = {}, q2 = {}'.format(
q1, q2))
w3 = 0.5
angle = 2 * np.arccos(w3)
return np.rad2deg(angle)
if __name__ == '__main__':
test_tf = {
'first': (
tf.Resize(240),
tf.RandomResizedCrop(224),
),
'rgb': (tf.ColorJitter(), tf.ToTensor())
}
val_tf = {'first': (tf.Resize((224, 224)), ), 'rgb': (tf.ToTensor(), )}
root = os.environ['SEVENSCENES'] + 'heads/'
train_dataset = SevenScene.Train(root=root,
transform=test_tf,
used_mod=('rgb', ))
val_dataset = SevenScene.Val(root=root,
transform=val_tf,
used_mod=('rgb', ))
grid = torchvis.utils.make_grid(torch.cat([batched['rgb'] for batched in sample_batched]), nrow=2)
plt.imshow(grid.numpy().transpose((1, 2, 0)))
def show_batch_mono(sample_batched, n_row=4):
"""Show image with landmarks for a batch of samples."""
depth = sample_batched['depth'] # /torch.max(sample_batched['depth'])
grid = torchvis.utils.make_grid(depth, nrow=n_row)
plt.imshow(grid.numpy().transpose((1, 2, 0)))
if __name__ == '__main__':
logger.setLevel('INFO')
test_tf = {
'first': (tf.Resize(256), tf.CenterCrop(256), ),
'rgb': (tf.ToTensor(), ),
'depth': (tf.ToTensor(), tf.DepthTransform())
}
test_tf_wo_tf = {
'first': (tf.Resize(240),),
'rgb': (tf.ToTensor(),),
}
root = os.environ['SEVENSCENES'] + 'heads/'
'''
train_dataset = Train(root=root,
transform=test_tf)
train_dataset_wo_tf = Train(root=root,
transform=test_tf_wo_tf,
used_mod=('rgb',))
grid = torchvis.utils.make_grid(torch.cat([batched['rgb'] for batched in sample_batched]), nrow=2)
plt.imshow(grid.numpy().transpose((1, 2, 0)))
def show_batch_mono(sample_batched, n_row=4):
"""Show image with landmarks for a batch of samples."""
depth = sample_batched['depth'] # /torch.max(sample_batched['depth'])
grid = torchvis.utils.make_grid(depth, nrow=n_row)
plt.imshow(grid.numpy().transpose((1, 2, 0)))
if __name__ == '__main__':
logger.setLevel('INFO')
test_tf = {
'first': (tf.Resize(140), tf.RandomCrop((112, 224))),
'rgb': (tf.ToTensor(), ),
}
test_tf_wo_tf = {
'first': (tf.Resize(240),),
'rgb': (tf.ToTensor(),),
}
root = os.environ['CAMBRIDGE']
train_dataset = TrainSequence(root=root, folders='Street/',
transform=test_tf, spacing=1, num_samples=8, random=False)
print(len(train_dataset))
dataloader = data.DataLoader(train_dataset, batch_size=1, shuffle=False, num_workers=2)
plt.figure(1)
images_batch = torch.cat(buffer, 0)
grid = torchvis.utils.make_grid(images_batch, nrow=4)
plt.imshow(grid.numpy().transpose((1, 2, 0)))
if __name__ == '__main__':
#root_to_folders = os.environ['PLATINUM'] + 'data/'
root_to_folders = '/private/anakim/data/mboussaha/data/imori/session_575/section_3/'
modtouse = [
'rgb',
]
transform = {
'first': (tf.Resize((224)), ),
'rgb': (
tf.RandomVerticalFlip(p=1),
tf.ToTensor(),
),
'depth': (tf.ToTensor(), ),
'sem': (tf.ToTensor(), )
}
dataset = Platinum(
root=root_to_folders,
file='session-575-3.csv',
modalities=modtouse,
transform=transform,
panorama_split=None) #{'v_split': 3, 'h_split': 2, 'offset': 0})
