|
--- |
|
|
|
license: apache-2.0 |
|
tags: |
|
- mindspore |
|
- image-classification |
|
datasets: |
|
- mnist |
|
|
|
--- |
|
|
|
## MindSpore Image Classification models with MNIST on the 🤗Hub! |
|
|
|
This repository contains the model from [this notebook on image classification with MNIST dataset using LeNet architecture](https://gitee.com/mindspore/mindspore/blob/r1.2/model_zoo/official/cv/lenet/README.md#). |
|
|
|
## LeNet Description |
|
Lenet-5 is one of the earliest pre-trained models proposed by Yann LeCun and others in the year 1998, in the research paper Gradient-Based Learning Applied to Document Recognition. They used this architecture for recognizing the handwritten and machine-printed characters. |
|
|
|
The main reason behind the popularity of this model was its simple and straightforward architecture. It is a multi-layer convolution neural network for image classification. |
|
|
|
![LeNet Architecture](./lenetarchitecture.jpeg) |
|
|
|
[source](https://www.analyticsvidhya.com/blog/2021/03/the-architecture-of-lenet-5/) |
|
|
|
|
|
|