uci-inception

uci-inception example

This is an example of human activity recognition using UCI HAR dataset.

The model was built with Inception structures.

      Input
        |
        |
      Conv
    /   |   \
   /    |    \
Conv  Conv  Maxpool
   \    |    /
    \   |   /
     Concat
        |
      Conv
        |   
      Dense
        |
      Dense
        |
     Softmax

The example implementation is based on RT-THREAD.

Preparation

You will need to download the dataset before doing the test.

Linux user:

• run data/download_dataset.py to download the UCI HAR dataset

Windows user:

• download dataset from [here](https://archive.ics.uci.edu/ml/machine-learning-databases/00240/UCI HAR Dataset.zip)
• unzip the file to this folder. Which will looks like data/UCI HAR Dataset/...

Copy all scripts from nnom/scripts/* into this folder.

Dependancy:

In RT-Thread, you must open the support for Y-modem.