def __init__(self,
dataset_csv_path,
dataset_csv_file,
dataset_image_path,
dataset_size=0,
output_size=(240, 240),
transform=None,
random_crop=False,
random_affine=False):
self.random_crop = random_crop
if random_affine:
self.random_affine = torchvision.transforms.RandomAffine(
40,
translate=None,
scale=(1, 1.5),
shear=40,
resample=PIL.Image.BILINEAR)
else:
self.random_affine = None
self.out_h, self.out_w = output_size
self.train_data = pd.read_csv(
os.path.join(dataset_csv_path, dataset_csv_file))
if dataset_size is not None and dataset_size != 0:
dataset_size = min((dataset_size, len(self.train_data)))
self.train_data = self.train_data.iloc[0:dataset_size, :]
self.img_A_names = self.train_data.iloc[:, 0]
self.img_B_names = self.train_data.iloc[:, 1]
self.set = self.train_data.iloc[:, 2].to_numpy()
self.flip = self.train_data.iloc[:, 3].to_numpy().astype('int')
self.dataset_image_path = dataset_image_path
self.transform = transform
# no cuda as dataset is called from CPU threads in dataloader and produces confilct
self.affineTnf = AffineTnf(out_h=self.out_h,
out_w=self.out_w,
use_cuda=False)
def __init__(self,
csv_file,
dataset_path,
output_size=(240, 240),
transform=None,
category=None,
pck_procedure='pf'):
self.category_names = [
'aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car',
'cat', 'chair', 'cow', 'diningtable', 'dog', 'horse', 'motorbike',
'person', 'pottedplant', 'sheep', 'sofa', 'train', 'tvmonitor'
]
self.out_h, self.out_w = output_size
self.pairs = pd.read_csv(csv_file)
self.category = self.pairs.iloc[:, 2].as_matrix().astype('float')
if category is not None:
cat_idx = np.nonzero(self.category == category)[0]
self.category = self.category[cat_idx]
self.pairs = self.pairs.iloc[cat_idx, :]
self.img_A_names = self.pairs.iloc[:, 0]
self.img_B_names = self.pairs.iloc[:, 1]
self.point_A_coords = self.pairs.iloc[:, 3:5]
self.point_B_coords = self.pairs.iloc[:, 5:]
self.dataset_path = dataset_path
self.transform = transform
# no cuda as dataset is called from CPU threads in dataloader and produces confilct
self.affineTnf = AffineTnf(out_h=self.out_h,
out_w=self.out_w,
use_cuda=False)
self.pck_procedure = pck_procedure
def __init__(self,
dataset_csv_path,
dataset_csv_file,
dataset_image_path,
dataset_size=0,
output_size=(240, 240),
transform=None,
random_crop=False):
self.random_crop = random_crop
self.out_h, self.out_w = output_size
self.train_data = pd.read_csv(
os.path.join(dataset_csv_path, dataset_csv_file))
if dataset_size is not None and dataset_size != 0:
dataset_size = min((dataset_size, len(self.train_data)))
self.train_data = self.train_data.iloc[0:dataset_size, :]
self.img_A_names = self.train_data.iloc[:, 0]
self.img_B_names = self.train_data.iloc[:, 1]
self.set = self.train_data.iloc[:, 2].values
self.flip = self.train_data.iloc[:, 3].values.astype('int')
self.dataset_image_path = dataset_image_path
self.transform = transform
# no cuda as dataset is called from CPU threads in dataloader and produces confilct
self.affineTnf = AffineTnf(out_h=self.out_h,
out_w=self.out_w,
use_cuda=False)
def __init__(
self,
csv_file,
dataset_path,
output_size=(240, 240),
transform=None,
category=None,
pck_procedure="pf",
):
self.category_names = [
"aeroplane",
"bicycle",
"bird",
"boat",
"bottle",
"bus",
"car",
"cat",
"chair",
"cow",
"diningtable",
"dog",
"horse",
"motorbike",
"person",
"pottedplant",
"sheep",
"sofa",
"train",
"tvmonitor",
]
self.out_h, self.out_w = output_size
self.pairs = pd.read_csv(csv_file)
self.category = np.array(self.pairs.iloc[:, 2]).astype("float")
if category is not None:
cat_idx = np.nonzero(self.category == category)[0]
self.category = self.category[cat_idx]
self.pairs = self.pairs.iloc[cat_idx, :]
self.img_A_names = self.pairs.iloc[:, 0]
self.img_B_names = self.pairs.iloc[:, 1]
self.point_A_coords = self.pairs.iloc[:, 3:5]
self.point_B_coords = self.pairs.iloc[:, 5:]
self.dataset_path = dataset_path
self.transform = transform
# no cuda as dataset is called from CPU threads in dataloader and produces confilct
self.affineTnf = AffineTnf(out_h=self.out_h,
out_w=self.out_w,
use_cuda=False)
self.pck_procedure = pck_procedure