Pretrained SOTA Deep Learning models, callbacks and more for research and production with PyTorch Lightning and PyTorch
Website • Installation • Main goals • latest Docs • stable Docs • Community • Grid AI • Licence
Continuous Integration
| System / PyTorch ver. | 1.6 (min. req.) | 1.7 (latest) |
|---|---|---|
| Linux py3.{6,8} |  |
|
| OSX py3.{6,8} | |
|
| Windows py3.7* |  |
|
- * testing just the package itself, we skip full test suite - excluding
testsfolder
Install
Simple installation from PyPI
pip install pytorch-lightning-bolts
Install bleeding-edge (no guarantees)
pip install git+https://github.com/PytorchLightning/[email protected] --upgrade
In case you want to have full experience you can install all optional packages at once
pip install pytorch-lightning-bolts["extra"]
What is Bolts
Bolts is a Deep learning research and production toolbox of:
- SOTA pretrained models.
- Model components.
- Callbacks.
- Losses.
- Datasets.
Main Goals of Bolts
The main goal of Bolts is to enable rapid model idea iteration.
Example 1: Finetuning on data
from pl_bolts.models.self_supervised import SimCLR
from pl_bolts.models.self_supervised.simclr.transforms import SimCLRTrainDataTransform, SimCLREvalDataTransform
import pytorch_lightning as pl
# data
train_data = DataLoader(MyDataset(transforms=SimCLRTrainDataTransform(input_height=32)))
val_data = DataLoader(MyDataset(transforms=SimCLREvalDataTransform(input_height=32)))
# model
weight_path = 'https://pl-bolts-weights.s3.us-east-2.amazonaws.com/simclr/bolts_simclr_imagenet/simclr_imagenet.ckpt'
simclr = SimCLR.load_from_checkpoint(weight_path, strict=False)
simclr.freeze()
# finetune
Example 2: Subclass and ideate
from pl_bolts.models import ImageGPT
from pl_bolts.models.self_supervised import SimCLR
class VideoGPT(ImageGPT):
def training_step(self, batch, batch_idx):
x, y = batch
x = _shape_input(x)
logits = self.gpt(x)
simclr_features = self.simclr(x)
# -----------------
# do something new with GPT logits + simclr_features
# -----------------
loss = self.criterion(logits.view(-1, logits.size(-1)), x.view(-1).long())
logs = {"loss": loss}
return {"loss": loss, "log": logs}
Who is Bolts for?
- Corporate production teams
- Professional researchers
- Ph.D. students
- Linear + Logistic regression heroes
I don't need deep learning
Great! We have LinearRegression and LogisticRegression implementations with numpy and sklearn bridges for datasets! But our implementations work on multiple GPUs, TPUs and scale dramatically...
Check out our Linear Regression on TPU demo
from pl_bolts.models.regression import LinearRegression
from pl_bolts.datamodules import SklearnDataModule
from sklearn.datasets import load_boston
import pytorch_lightning as pl
# sklearn dataset
X, y = load_boston(return_X_y=True)
loaders = SklearnDataModule(X, y)
model = LinearRegression(input_dim=13)
# try with gpus=4!
# trainer = pl.Trainer(gpus=4)
trainer = pl.Trainer()
trainer.fit(model, train_dataloader=loaders.train_dataloader(), val_dataloaders=loaders.val_dataloader())
trainer.test(test_dataloaders=loaders.test_dataloader())
Is this another model zoo?
No!
Bolts is unique because models are implemented using PyTorch Lightning and structured so that they can be easily subclassed and iterated on.
For example, you can override the elbo loss of a VAE, or the generator_step of a GAN to quickly try out a new idea. The best part is that all the models are benchmarked so you won't waste time trying to "reproduce" or find the bugs with your implementation.
Team
Bolts is supported by the PyTorch Lightning team and the PyTorch Lightning community!
Licence
Please observe the Apache 2.0 license that is listed in this repository. In addition the Lightning framework is Patent Pending.
Citation
To cite bolts use:
@article{falcon2020framework,
title={A Framework For Contrastive Self-Supervised Learning And Designing A New Approach},
author={Falcon, William and Cho, Kyunghyun},
journal={arXiv preprint arXiv:2009.00104},
year={2020}
}
To cite other contributed models or modules, please cite the authors directly (if they don't have bibtex, ping the authors on a GH issue)
source: https://arxiv.org/pdf/1702.05373.pdf [Table-I]
source: https://arxiv.org/pdf/1702.05373.pdf [Table-II]
1 Jan 13, 2022
1.5k Dec 30, 2022
4 Feb 22, 2022
102 Dec 26, 2022
26 Dec 13, 2022
12 Dec 30, 2022
91 Dec 21, 2022
45 Dec 13, 2022
38 Dec 06, 2022
336 Dec 09, 2022
158 Dec 28, 2022
36 Dec 18, 2022
2.5k Dec 31, 2022
28 Nov 25, 2022
57 Oct 03, 2022
19 Dec 12, 2022
2 Sep 19, 2022
1 Oct 05, 2021
180 Dec 30, 2022
0 Jan 20, 2022