Commit e8c39ad4 authored by LongChan's avatar LongChan
Browse files

added all basic flow

parent 5bad1c18
......@@ -19,8 +19,8 @@ We provide a fast optimization algorithm and a step-to-step guide on how to gene
### Demos
The following demos use pre-generated datasets and topologies that can be found in:
- [~/optimization_algo/topologies](~/optimization_algo/topologies/) contains all the topologies descriping their respective CNN structures
- [~/optimization_algo/data_source](~/optimization_algo/data_source/) contains all the cycle-accurate data generated using [SCALE sim]()
- [topologies](~/optimization_algo/topologies/) contains all the topologies descriping their respective CNN structures
- [data_source](~/optimization_algo/data_source/) contains all the cycle-accurate data generated using [SCALE sim]()
The instruction below will do a sweep run on each of the following networks:
- FasterRCNN
......@@ -41,24 +41,26 @@ To get optimization result with
# ./sweep_nets_cma.sh
```
1. Genetic Algorithm (GA)
2. Genetic Algorithm (GA)
```bash
# cd optimization_algo/scripts
# ./sweep_nets_ga.sh
```
1. CMA
3. Hyperparameter Optimiztion
```bash
# cd optimization_algo/scripts
# ./sweep_nets_cma.sh
# ./sweep_nets_ho.sh
```
2. Brute Force
4. Brute Force
```bash
# cd optimization_algo/scripts
# ./sweep_nets_brute.sh
```
Result of the optimization will be added to the corresponding csv file under this [folder](../optimization_algo/resulting_csv)
#### Custom topologies
#### Custom target board
......
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