We’ve heard your feedback, and we’re excited to announce that access to the Dataflow Compiler (DFC) is now available!
With that, we would like to help you set the right approach towards using the DFC.
Bring Your Own Data (BYOD) - The most recommended way is using the retraining Docker containers from the Hailo Model Zoo. This will allow you to use some of the most popular networks, (re)trained on your own custom data (see this link for an end-to-end example in our GitHub repo).
Bring Your Own Model (BYOM) – This method requires a deeper understanding of the model and the conversion flow from ONNX or TensorFlow Lite (TFLite) to Hailo’s HEF format. We suggest using the DFC user guide and tutorials. This approach may present more challenges compared to using the retraining Docker containers from the Model Zoo, but for some, the ride is as enjoyable as the destination (see this link for DFC tutorials).
Large models (e.g., LLMs, Whisper, Stable-Diffusion, etc.) include some of the SoTA models and are naturally very attractive. We’re actively working on enabling the porting of these models to Hailo, but at this point in time, we cannot yet execute these on the Hailo-8L.
Please bear with us as we embark on this adventure of releasing the DFC. We are committed to giving the best experience that we can deliver, and we believe this is another step in enabling exciting projects
What i am trying to say is that you do not get to that page trying with the above addresses. They are both going to the new page https://hailo.ai/developer-zone/ and not to the download page.
I’m new here, but I believe you have to log in to dev zone in order to see it. It appears that your community login will work. But, they do appear to be logged in separately. I see it fine.
Very strange. I clicked on the links that you provided and it took me straight to it. I’m even on a different computer now and had to log in. But, took me right there after I did. I’m at a loss…
The DFC is only available on x86 machines because it is a compiler used to create models, but it does not actually run the models. On Raspberry Pi devices, we only run the pre-compiled models and use them, we do not use the DFC compiler itself on the RPi.
(see this link for DFC tutorials).
