# mnist-深度学习
**Repository Path**: tang_zhen_chao/mnist_deep_learning
## Basic Information
- **Project Name**: mnist-深度学习
- **Description**: 作为深度学习中的HelloWorld，该小工程详细描述了如何从零开始深度学习
- **Primary Language**: Python
- **License**: GPL-3.0
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No
## Statistics
- **Stars**: 1
- **Forks**: 0
- **Created**: 2020-05-17
- **Last Updated**: 2020-12-19
## Categories & Tags
**Categories**: Uncategorized
**Tags**: None
## README
# mnist-Deep learning
#### Introduction
As a HelloWorld in deep learning, this small project details how to start deep learning from scratch
#### Software Architecture
The identification of the mnist data set uses two very small networks to achieve, the first is the simplest fully connected network, the second is the convolution network, the mnist data set is the entry data set, so no image enhancement is required Or use the generator to read into the memory and directly use the simple fit () command to train at one time
#### Installation tutorial
1. The main third-party libraries used are tensorflow1.x, Keras based on TensorFlow, and the basic libraries include numpy and matplotlib
2. The installation method is also very simple, for example: pip install numpy -i https://pypi.tuna.tsinghua.edu.cn/simple
3. Note that the tensorflow version cannot be 2.x
#### Instructions for use
1. First, we preview the data set, run mnistplt.py, and draw 4 images for training
As shown in the figure:
2. To train a fully connected network, run Densemnist.py to get the weight Dense.h5, load the model and predict to run Denseload.py
Fully connected network structure:
Recognition result:
3. To train the convolutional network, run CNNmnist.py, get the weight CNN.h5, load the model and predict to run CNNload.py
CNN :
Recognition result:
