DavidLandup0/deepvision
PyTorch and TensorFlow/Keras image models with automatic weight conversions and equal API/implementations - Vision Transformer (ViT), ResNetV2, EfficientNetV2, NeRF, SegFormer, MixTransformer, (planned...) DeepLabV3+, ConvNeXtV2, YOLO, etc.
This project helps machine learning engineers and researchers quickly build and train computer vision models. It takes raw image data and outputs trained models for tasks like image classification and semantic segmentation. The key benefit is allowing seamless switching between TensorFlow and PyTorch frameworks, using the same model architectures and easily converting weights.
No commits in the last 6 months.
Use this if you are a machine learning practitioner who needs to develop computer vision applications and wants the flexibility to work across both TensorFlow and PyTorch without rewriting model code or worrying about framework compatibility.
Not ideal if you are new to deep learning or only ever work within a single machine learning framework like a specific version of TensorFlow or PyTorch.
Stars
42
Forks
7
Language
Python
License
Apache-2.0
Category
Last pushed
Jul 01, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/DavidLandup0/deepvision"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Jittor/jittor
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.
zhanghang1989/ResNeSt
ResNeSt: Split-Attention Networks
berniwal/swin-transformer-pytorch
Implementation of the Swin Transformer in PyTorch.
NVlabs/FasterViT
[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with...
ViTAE-Transformer/ViTPose
The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose...