innat/DOLG-TensorFlow
Implementation of Deep Orthogonal Fusion of Local and Global Features in TensorFlow 2
This project helps machine learning engineers improve image recognition accuracy by generating more powerful image representations. It takes an input image and outputs a compact, rich image representation by combining both its fine-grained details and overall context. This is designed for ML practitioners building computer vision models for tasks like image classification, object detection, or image retrieval.
No commits in the last 6 months. Available on PyPI.
Use this if you are a machine learning engineer working on computer vision tasks and want to extract more effective and discriminative features from images.
Not ideal if you are looking for a pre-trained, ready-to-use image recognition application without needing to integrate custom model components.
Stars
26
Forks
7
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jun 19, 2023
Commits (30d)
0
Dependencies
3
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/innat/DOLG-TensorFlow"
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.
berniwal/swin-transformer-pytorch
Implementation of the Swin Transformer in PyTorch.
zhanghang1989/ResNeSt
ResNeSt: Split-Attention Networks
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...