SEQ CUB200 RS#
Implements the Sequential CUB200 Dataset, as used in Transfer without Forgetting (Version with ResNet50 as backbone).
Classes#
- class datasets.seq_cub200_rs.MyCUB200RS(root, train=True, transform=None, target_transform=None, download=True)[source]#
Bases:
MyCUB200- MEAN = (0.4856, 0.4994, 0.4324)#
- STD = (0.2272, 0.2226, 0.2613)#
- TEST_TRANSFORM = Compose( Resize(size=224, interpolation=bilinear, max_size=None, antialias=True) ToTensor() Normalize(mean=(0.4856, 0.4994, 0.4324), std=(0.2272, 0.2226, 0.2613)) )#
- class datasets.seq_cub200_rs.SequentialCUB200RS(args)[source]#
Bases:
SequentialCUB200Sequential CUB200 Dataset. Version with ResNet50 (as in Transfer without Forgetting)
- Parameters:
NAME (str) – name of the dataset.
SETTING (str) – setting of the dataset.
N_CLASSES_PER_TASK (int) – number of classes per task.
N_TASKS (int) – number of tasks.
SIZE (tuple) – size of the images.
MEAN (tuple) – mean of the dataset.
STD (tuple) – standard deviation of the dataset.
TRANSFORM (torchvision.transforms) – transformation to apply to the data.
TEST_TRANSFORM (torchvision.transforms) – transformation to apply to the test data.
- MEAN = (0.4856, 0.4994, 0.4324)#
- STD = (0.2272, 0.2226, 0.2613)#
- TEST_TRANSFORM = Compose( Resize(size=224, interpolation=bilinear, max_size=None, antialias=True) ToTensor() Normalize(mean=(0.4856, 0.4994, 0.4324), std=(0.2272, 0.2226, 0.2613)) )#
- TRANSFORM = Compose( Resize(size=224, interpolation=bilinear, max_size=None, antialias=True) RandomCrop(size=(224, 224), padding=4) RandomHorizontalFlip(p=0.5) ToTensor() Normalize(mean=(0.4856, 0.4994, 0.4324), std=(0.2272, 0.2226, 0.2613)) )#