Deeplite's Projects
Official PyTorch training code of Accelerating Deep Neural Networks via Semi-Structured Activation Sparsity (ICCV2023-RCV)
A collection of metrics to profile a single deep learning model or compare two different deep learning models
Collection of SOTA efficient computer vision models for embedded applications, with pre-trained weights and training recipes
Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.
Public documentation of Deeplite Neutrino™ engine.
Public examples to use Deeplite Neutrino™ engine for model architecture optimization.
A method to increase the speed and lower the memory footprint of existing vision transformers.