TResNet
by Alibaba-MIIL
Official Pytorch Implementation of "TResNet: High-Performance GPU-Dedicated Architecture" (WACV 2021)
AI summary
GPU architecture
A high-performance deep learning architecture designed to balance accuracy and efficiency on GPUs.
- stars
- 471
- forks
- 63
- watching
- 18
- awesome list
- 1
Similar projects
Found by comparing what the projects do, not just their names.
PixelNet Architecture
An architecture and toolset for training deep learning models to perform pixel-level tasks such as image segmentation and surface normal estimation.
Neural net architecture
An implementation of a deep neural network architecture for image classification tasks
Gpu-accelerated algo
Accelerates machine learning algorithms on GPUs to improve performance and efficiency
Neural network architecture
An implementation of a pursuit of structural diversity in very deep neural networks
Deep Learning Accelerator
A comprehensive hardware design stack for accelerating deep learning models
Image classifier
An implementation of PNASNet-5 architecture in TensorFlow for image classification on ImageNet.
calebwin/emu1.6K
GPU compute library
A library for portable, modular, and performant GPU compute programming in Rust.
Neural network architecture
An implementation of a 1-bit weight neural network architecture using PyTorch
Hardware-aware NAS
Direct neural architecture search on target task and hardware for efficient model deployment
Image classifier
A Lua-based implementation of a multi-GPU training framework for image classification using the Alexnet model.
Architecture searcher
This implementation provides a Tensorflow-based framework for searching different architectures in deep neural networks using 2nd-order approximations.
GPU language binding
Enables efficient data exchange and invocation of existing GPU kernels from host languages in the GraalVM
GPU core
An open-source implementation of a GPU core for machine learning, designed to run PyTorch and other frameworks on an ASIC.
Deep network architecture
An implementation of Wide Residual Networks in PyTorch for efficient deep learning on CIFAR10/100 datasets.
Neural net architecture
An implementation of a PyTorch-based neural network architecture for image classification tasks.
Featured in 1 awesome list
Each link jumps to the spot where the list mentions TResNet.
