Ricardo de Azambuja

Results 43 comments of Ricardo de Azambuja

I'm also having problems with the camera (original, V2.1) when it's connected through the AIY vision hat. When I connect it directly to the RPI Zero W, I'm able to...

Ok, following my tests, I flashed, again, the image recommended by @manoj7410 and this time I run ```sudo apt upgrade```, you know, just in case the problem was solved in...

@tuttelikz Would you mind telling me if your camera was connected to the AIY Vision Bonnet or directly to the RPI Zero W?

@tuttelikz Thanks for your answer! Now, a probably silly question: is everything working on the AIY Vision Bonnet after the upgrade and which raspbian version are you using? And would...

@tuttelikz, my solution was to connect the camera directly to the RPI Zero W. Everything works fine that way, but I would like to verify if it's much slower compared...

@combs Would you mind sharing the results of your tests? Thanks!

I'm curious about the max frequencies and any extra caveat :)

Ok, if nobody from Google wants to help or simply doesn't have time to help, why don't you release the full source code for the bonnet_model_compiler?

Hi @0russ, I wouldn't say I really solved the problem because my aim was to automatically replace the operations that make the compiler crash, but after many hours testing I...

Sorry @0russ, I meant the [original mobilenet embed config file](https://github.com/tensorflow/models/blob/master/research/object_detection/samples/configs/embedded_ssd_mobilenet_v1_coco.config). The V3 will not work because of the new ops it is using and also the final size (I think...