Commit 73460b23 authored by nilsfreyer's avatar nilsfreyer

added readme for mxnet example

parent c2c6d01c
# Calculator MXNET
## Prerequisites
1. Ubuntu Linux 16.04 LTS or 18.04 LTS (experimental)
2. Deep Learning Framework **Caffe2**. [Follow the instructions from this link](
3. Armadillo (at least armadillo version 6.600 must be used) [Official instructions at Armadillo Website](
4. OpenCV
## Prepare the data
To create the data for training, execute:
bash ./
## How to Run
Generate and build the code for the EMADL model by executing:
Finally, navigate to the target directory in order to run the calculator as follows:
./build/src/cpp/DigitCalculator ./test_img/3.jpg
You can try different images from the provided `/test_img` directory or even create your own images for testing. Note that the application program DigitCalculator will automatically rescale the given input image to the size 32x32.
## Troubleshooting Help
ERROR: HelperA.h:79:28: error: ‘sqrtmat’ was not declared in this scope.
Copy compiled armadillo lib and include files to usr/lib and usr/include respectively. Replace YOUR_ARMADILLO_REPOSITORY and VERSION (e.g. 8.500.1) with your corresponding information:
sudo cp libarmadillo* /usr/lib
sudo cp -r * /usr/include
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment