raphael/hailo-inference
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

adds further instructions

Browse Source
This commit is contained in:
Raphael Maenle 2022-03-21 09:56:09 +01:00
parent 0dbabe328d
commit baefc3c761
1 changed files with 36 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
README.md
View File

@ -37,9 +37,6 @@ You'll need a way to train your network (yielding a .pb file from it) and the ha
which are getting monthly updates at the time of writing. This of course means that these notes are rapidly aging into inaccuracy. which are getting monthly updates at the time of writing. This of course means that these notes are rapidly aging into inaccuracy.
- clone the [hailo model zoo](https://github.com/hailo-ai/hailo_model_zoo), which has some convenient yolov5 - clone the [hailo model zoo](https://github.com/hailo-ai/hailo_model_zoo), which has some convenient yolov5
Docker containers. Docker containers.
### Setup
- unzip the `hailo software suite` and run inside `./hailo_sw_suite_docker_run.sh`. If this is your fist time running, the container will set up. - unzip the `hailo software suite` and run inside `./hailo_sw_suite_docker_run.sh`. If this is your fist time running, the container will set up.
Otherwise, you'll have to either `--resume` or `--override` Otherwise, you'll have to either `--resume` or `--override`
@ -51,6 +48,7 @@ You'll need a way to train your network (yielding a .pb file from it) and the ha
# Setup Example for a custom Yolov5m # Setup Example for a custom Yolov5m
Here you'll train, quantize, compile (on a gpu if possible) and infer (on the hailo chip)
## Train your own Yolov5m ## Train your own Yolov5m
@ -70,14 +68,28 @@ You'll need a way to train your network (yielding a .pb file from it) and the ha
- in `hailo_sw_suite_docker_run.sh` add a volume so you can access your best.pb onnx file, for example - in `hailo_sw_suite_docker_run.sh` add a volume so you can access your best.pb onnx file, for example
in the `DOCKER_ARGS` you could add -v /home/user/files:/files in the `DOCKER_ARGS` you could add -v /home/user/files:/files
- run `./hailo_sw_suite_docker_run.sh --resume` to get into the docker container - run `./hailo_sw_suite_docker_run.sh --resume` to get into the docker container
- follow the rest of the tutorial from [the hailo model zoo](https://github.com/hailo-ai/hailo_model_zoo/blob/master/docs/RETRAIN_ON_CUSTOM_DATASET.md) - `cd hailo_model_zoo` and continue the tutorial.
- Note, that for yolov5m, Hailo provides a configuration yaml which defines the quantization levels for the various networks. If you have a custom network
you will have to define your custom yaml file. I liked using [netron](https://github.com/lutzroeder/Netron) to visualize the network for that. Further Notes and Examples:
- Another example to compile the model is to run: `python hailo_model_zoo/main.py compile yolov5m --ckpt /files/my_dataset/best.onnx --calib-path /files/watt_dataset/dataset/dataset/images/ --yaml ./hailo_model_zoo/cfg/networks/yolov5m.yaml`
- note that here you're quantizing and compiling to HEF file. If you just want to quantize into a _har_ file, run `python hailo_model_zoo/main.py quantize yolov5m --ckpt /files/my_dataset/best.onnx --calib-path /files/my_dataset/dataset/dataset/images/ --yaml ./hailo_model_zoo/cfg/networks/yolov5m.yaml`, which yields the _.har_ representation of the file
- You have to provide a list of images for quantization (--calib-path)
- also provide a quantization scheme (--yaml), where hailo\_model\_zoo provides a variety
- **There's no real reason to not use _compile_ directly from what I know.**
- Note that the file locations in these examples are different to Hailos. These worked, while Hailo's didn't.
- follow the getting started guide from [hailo model zoo / GETTING STARTED](https://github.com/hailo-ai/hailo_model_zoo/blob/master/docs/GETTING_STARTED.md), specifically the
_optimizing_ and _compile_ steps if you want more information on quantization parameters and how to go on from there.
## run inference ## run inference
- this git repository includes a _inference.py_ file, which which loads a specified _.hef_ file. Change that to your _.hef_ file location.
- If you have anything other than yolov5m, you will have to change the pre/post-processing steps. Otherwise it won't work. Check out the Hailo Handler Class and go from there.
# Other Networks # Other Networks
- what other networks can I deploy on Hailo? - For yolov5m, Hailo provides a configuration yaml which defines the quantization levels for the various networks. If you have a custom network you will have to define your custom yaml file. I liked using [netron](https://github.com/lutzroeder/Netron) to visualize the network for that.
- Anything the hailo\_model\_zoo provides a configuration file for (under `hailo_odel_zoo/cfg/networks/`) can be easily trained and deployed using the process
described above.
- Also check out the [Hailo Tappas](https://hailo.ai/developer-zone/tappas-apps-toolkit/) which supply a variety of pre-trained _.hef_ files, which you can run
without having to compile anything.