dory
dory copied to clipboard
pulp-platform
A tool to deploy Deep Neural Networks on PULP-based SoC's
I have successfully quantized the model with the NEMO tool and generated the .onnx file, but when generating the network with the "network_generate.py" file, I get an error: "out_layer0.txt not...
This PR started as a fix for GAP9's L3->L2 bug but ended up being more. ## Added: - Georg's hack for new onnx export that doesn't have numbers ## Changes:...
While working on drone code, we noticed that there was redundant code in the network run function so I moved some code to the initializer. Alongside that I aligned a...
Is the DORY framework only compatible with commercial MCUs like GAP-8 as the target hardware, or can it also be used with custom architectures based on other PULP platforms?
Followed instructions given at https://github.com/pulp-platform/dory/tree/master?tab=readme-ov-file#building-and-using-the-dockerfile ```bash ./docker_utils/build_docker.sh ./docker_utils/run_docker.sh source ./docker_utils/docker_pulp_sdk.sh ``` `test_GAP8.py` was missing, I used the `test_PULP.py` given at the root: ```bash (dory_env) root@0ca16513dd93:/dory_checkout# python3 -m pytest test_PULP.py --compat...
Dear Dory Community, Thank you for your great work. I am trying to use Dory tool to generate the C files, to deploy in the [ai deck](https://www.bitcraze.io/products/ai-deck/) from the example...
I encountered the following issue when deploying a model using DORY: AssertionError: BatchNormalization not supported by DORY. How should I resolve this? Thank you for your reply.
Metadata
Owner
Metadata
A tool to deploy Deep Neural Networks on PULP-based SoC's