- Faster Computer Vision.
-
Install from PyPi.
-
Current stable
release 0.1.1needsPyTorch 1.7.1andtorchvision 0.8.2.pip install quickvision
-
Quickvision makes Computer Vision tasks much faster and easier with PyTorch.
It provides: -
- Easy to use PyTorch native API, for
fit(),train_step(),val_step()of models. - Easily customizable and configurable models with various backbones.
- A complete PyTorch native interface. All models are
nn.Module, all the training APIs are optional and not binded to models. - A lightning API which helps to accelerate training over multiple GPUs, TPUs.
- A datasets API to convert common data formats very easily and quickly to PyTorch formats.
- A minimal package, with very low dependencies.
- Easy to use PyTorch native API, for
-
Train your models faster. Quickvision has already implemented the long learning in PyTorch.
- Quickvision does not make you learn a new library. If you know PyTorch, you are good to go!!!
- Quickvision does not abstract any code from PyTorch, nor implements any custom classes over it.
- It keeps the data format in
Tensorso that you don't need to convert it.
- Use model made by us. It's just a
nn.Modulewhich has Tensors only Input and Output format. - Quickvision provides reference scripts too for training it!
- Just use our training methods such as
fit(),train_step(),val_step().
- Just subclass the PyTorch Lightning model!
- Implement the
train_step(),val_step().