Michael O'Cleirigh

@fgervais I also made some documentation updates to the readme for instructions on how to build using the esp-idf docker images. On the latest micropython (currently working toward 1.15) most/all...

@MATTYGILO I can only go by the code you posted. Generally you need to follow these steps: 1. Create the interpreter for the model. 2. Set the value for the...

@MATTYGILO a tensor is an array. Because you expect it to be of shape [1, 400] I expect it to be an array of 400 int8 elements. You can use...

I hit the ARG_MAX limit on ubuntu trying to build a custom user module in micropython. I only had 255 files but due to the path depth it went over...

I just hard coded the spectrogram settings used on the reference example. It's 100% possible to create a config object for the various settings and use it to change the...

As a test I turned off all of the 84 ops and the firmware size was shrunk by 200 kb from: 1.8 MB to 1.6 MB.

I checked the size of the [reference build](https://github.com/micropython/micropython/runs/3381023215?check_suite_focus=true#step:4:4353) and it is 1.5 MB

I need to assess the experience when a user tries to use a model that uses an op that is not built into the firmware. I should be able to...

While we don't seem to have any space limitations at the moment. I think the research work on this topic can be merged down so that others have the ability...

The only documentation are the examples themselves or the microlite module code. The parameters for the microlite.interpreter are: 1. Tensorflow lite for microcontrollers model loaded into byte array. The size...