quickvision 0.2.0

Computer Vision models and training

Quickvision

• Faster Computer Vision.

Install Quickvision

• Install from PyPi.

• Current stable release 0.1.1 needs PyTorch 1.7.1 and torchvision 0.8.2.

  pip install quickvision
  

What is Quickvision?

• Quickvision makes Computer Vision tasks much faster and easier with PyTorch.

  It provides: -

  1. Easy to use PyTorch native API, for fit(), train_step(), val_step() of models.
  2. Easily customizable and configurable models with various backbones.
  3. A complete PyTorch native interface. All models are nn.Module, all the training APIs are optional and not binded to models.
  4. A lightning API which helps to accelerate training over multiple GPUs, TPUs.
  5. A datasets API to convert common data formats very easily and quickly to PyTorch formats.
  6. A minimal package, with very low dependencies.

• Train your models faster. Quickvision has already implemented the long learning in PyTorch.

Quickvision is just 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 Tensor so that you don't need to convert it.

Do you want just a model with some backbone configuration?

• Use model made by us. It's just a nn.Module which has Tensors only Input and Output format.
• Quickvision provides reference scripts too for training it!

Do you want to train your model but not write lengthy loops?

• Just use our training methods such as fit(), train_step(), val_step().

Do you want multi GPU training but worried about model configuration?

• Just subclass the PyTorch Lightning model!
• Implement the train_step(), val_step().