taki0112/SENet-Tensorflow
TensorFlow implementation of Squeeze-and-Excitation networks and related architectures for image classification.
Not currently ranked — collecting fresh signals.
star history
This repository provides a TensorFlow implementation of Squeeze and Excitation (SE) blocks integrated into ResNeXt, Inception-v4, and Inception-resnet-v2 architectures. The code experiments with these models on the Cifar10 image classification dataset. It includes SE block definitions with channel excitation via fully connected layers and global average pooling.
Frequently asked
- What is taki0112/SENet-Tensorflow?
- TensorFlow implementation of Squeeze-and-Excitation networks and related architectures for image classification.
- Is SENet-Tensorflow open source?
- Yes — taki0112/SENet-Tensorflow is open source, released under the MIT license.
- What language is SENet-Tensorflow written in?
- taki0112/SENet-Tensorflow is primarily written in Python.
- How popular is SENet-Tensorflow?
- taki0112/SENet-Tensorflow has 756 stars on GitHub.
- Where can I find SENet-Tensorflow?
- taki0112/SENet-Tensorflow is on GitHub at https://github.com/taki0112/SENet-Tensorflow.