A DataLoader library for Continual Learning in PyTorch.
Project description
Continual Loader (CLLoader)
A library for PyTorch's loading of datasets in the field of Continual Learning
Aka Continual Learning, Lifelong-Learning, Incremental Learning, etc.
Example:
from torch.utils.data import DataLoader
from clloader import CLLoader
from clloader.datasets import MNIST
clloader = CLLoader(
MNIST("my/data/path", download=True),
increment=1,
initial_increment=5
)
print(f"Number of classes: {clloader.nb_classes}.")
print(f"Number of tasks: {clloader.nb_tasks}.")
for task_id, (train_dataset, test_dataset) in enumerate(clloader):
train_loader = DataLoader(train_dataset)
test_loader = DataLoader(test_dataset)
# Do your cool stuff here
Supported Scenarios
Name | Acronym | Supported |
---|---|---|
New Instances | NI | :x: |
New Classes | NC | :white_check_mark: |
New Instances & Classes | NIC | :x: |
Supported Datasets:
Note that the task sizes are fully customizable.
Name | Nb classes | Image Size | Automatic Download |
---|---|---|---|
MNIST | 10 | 28x28x1 | :white_check_mark: |
Fashion MNIST | 10 | 28x28x1 | :white_check_mark: |
KMNIST | 10 | 28x28x1 | :white_check_mark: |
EMNIST | 10 | 28x28x1 | :white_check_mark: |
QMNIST | 10 | 28x28x1 | :white_check_mark: |
MNIST Fellowship | 30 | 28x28x1 | :white_check_mark: |
CIFAR10 | 10 | 32x32x3 | :white_check_mark: |
CIFAR100 | 100 | 32x32x3 | :white_check_mark: |
CIFAR Fellowship | 110 | 32x32x3 | :white_check_mark: |
ImageNet100 | 100 | 224x224x3 | :x: |
ImageNet1000 | 1000 | 224x224x3 | :x: |
Permuted MNIST | 10 + X * 10 | 224x224x3 | :white_check_mark: |
Furthermore some "Meta"-datasets are available:
- InMemoryDataset: for in-memory numpy array
- PyTorchDataset: for any dataset defined in torchvision
- ImageFolderDataset: for datasets having a tree-like structure, with one folder per class
- Fellowship: to combine several datasets
Sample Images
MNIST:
Task 0 | Task 1 | Task 2 | Task 3 | Task 4 |
FashionMNIST:
Task 0 | Task 1 | Task 2 | Task 3 | Task 4 |
CIFAR10:
Task 0 | Task 1 | Task 2 | Task 3 | Task 4 |
MNIST Fellowship (MNIST + FashionMNIST + KMNIST):
Task 0 | Task 1 | Task 2 |
PermutedMNIST:
Task 0 | Task 1 | Task 2 | Task 3 | Task 4 |
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
clloader-arthurdouillard-0.0.1.tar.gz
(409.8 kB
view hashes)
Built Distribution
Close
Hashes for clloader-arthurdouillard-0.0.1.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 89551bb617ee77d92ef3c7e9184315419a6f8f09bd6602017708b5575424edb6 |
|
MD5 | 5e0ac75abb2df7a35ace0b874531dbe7 |
|
BLAKE2b-256 | 9931bd2599e2ddbceea37cea43f011c407d4cb3a5cd620c3da626c5efd9f345e |
Close
Hashes for clloader_arthurdouillard-0.0.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 6fd2d2bf93814a8f4ce0c8b6f9b10dfcca2a8ee8b25939b9891c58ee86236046 |
|
MD5 | 56a3b39caa030398c62824942d452872 |
|
BLAKE2b-256 | 70575b7182ad26a819afde674c79b230c339dea387250c3dec6d4a1a88e9f34a |