Big-Little Net
IBMImage classificationObject recognitionOpen weights
Developed by IBM in 2018, Big-Little Net is a image classification model with 77360000.0 parameters with openly available weights.
About Big-Little Net
In this paper, we propose a novel Convolutional Neural Network (CNN) architecture for learning multi-scale feature representations with good tradeoffs between speed and accuracy. This is achieved by using a multi-branch network, which has different c
Details
- Provider
- IBM
- Task
- Image classification,Object recognition
- Parameters
- 77360000.0
- Released
- 2018-07-10
- Open weights
- Yes