Tencent/tencent-ml-images
Largest multi-label image database; ResNet-101 model; 80.73% top-1 acc on ImageNet
Combines ImageNet and Open Images sources via WordNet-based semantic merging to unify 11,166 categories across multi-label annotations. Provides TensorFlow-compatible training pipeline including TFRecord preparation, pre-training on ML-Images, and fine-tuning workflows for downstream tasks like single-label classification and feature extraction.
3,077 stars. No commits in the last 6 months.
Stars
3,077
Forks
511
Language
Python
License
—
Category
Last pushed
Apr 20, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Tencent/tencent-ml-images"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
qubvel/efficientnet
Implementation of EfficientNet model. Keras and TensorFlow Keras.
KichangKim/DeepDanbooru
AI based multi-label girl image classification system, implemented by using TensorFlow.
matlab-deep-learning/Image-Classification-in-MATLAB-Using-TensorFlow
This example shows how to call a TensorFlow model from MATLAB using co-execution with Python.
harvitronix/five-video-classification-methods
Code that accompanies my blog post outlining five video classification methods in Keras and TensorFlow
AFAgarap/cnn-svm
An Architecture Combining Convolutional Neural Network (CNN) and Linear Support Vector Machine...