src.train.data namespace

Submodules

src.train.data.dataloader module

src.train.data.dataloader.get_train_loader(batch_size, data_root, griding_num, use_aux, distributed, num_lanes, train_gt)

src.train.data.dataset module

class src.train.data.dataset.LaneClsDataset(path, list_path, img_transform=None, target_transform=None, simu_transform=None, griding_num=50, load_name=False, row_anchor=None, use_aux=False, segment_transform=None, num_lanes=4)

Bases: torch.utils.data.dataset.Dataset

src.train.data.dataset.loader_func(path)

src.train.data.mytransforms module

class src.train.data.mytransforms.Compose2(transforms)

Bases: object

class src.train.data.mytransforms.DeNormalize(mean, std)

Bases: object

class src.train.data.mytransforms.FreeScale(size)

Bases: object

class src.train.data.mytransforms.FreeScaleMask(size)

Bases: object

class src.train.data.mytransforms.MaskToTensor

Bases: object

class src.train.data.mytransforms.RandomLROffsetLABEL(max_offset)

Bases: object

class src.train.data.mytransforms.RandomRotate(angle)

Bases: object

Crops the given PIL.Image at a random location to have a region of the given size. size can be a tuple (target_height, target_width) or an integer, in which case the target will be of a square shape (size, size)

class src.train.data.mytransforms.RandomUDoffsetLABEL(max_offset)

Bases: object

class src.train.data.mytransforms.Scale(size)

Bases: object

src.train.data.mytransforms.find_start_pos(row_sample, start_line)