Welcome to TorchOk’s documentation!
TorchOk is a toolkit for fast Deep Learning experiments in Computer Vision. It’s based on PyTorch and utilizes PyTorch Lightning for training pipeline routines.
The toolkit consists of:
Neural Network models which are proved to be the best not only on PapersWithCode but in practice. All models are under plug&play interface that easily connects backbones, necks and heads for reuse across tasks
Out-of-the-box support of common Computer Vision tasks: classification, segmentation, image representation and detection
Commonly used datasets, image augmentations and transformations (from Albumentations)
Fast implementations of retrieval metrics (with the help of FAISS and ranx) and lots of other metrics from torchmetrics
Export models to ONNX and ability to test the exported model without changing the datasets
All components can be customized inheriting the unified interfaces: Lightning’s training loop, tasks, models, datasets, augmentations and transformations, metrics, loss functions, optimizers and LR schedulers
Training, validation and testing configurations are represented by YAML config files and managed by Hydra
Only straightforward training techniques are implemented. No whistles and bells