-
We have 32 Coral Dev Boards and most of the demos now fail after flashing enterprise-eagle-20200724205123 because edgetpu https://github.com/google-coral/edgetpu has been branded Legacy and replaced b…
-
sudo apt-get install libedgetpu1-legacy-std
sudo apt-get install python3-edgetpu
sudo apt-get install libedgetpu1-legacy-max
sudo -H pip3 install https://github.com/google-coral/pycoral/releases/do…
-
- Attempting to run a custom model (based on MobileDet) using PyCoral
- Below code is how I ran it. Basing it off of the example provided for object detection (which does work when using the sample c…
-
### Description
I have compiled the Edge TPU runtime, Tensorflow lite and the PyCoral API from source on my Arch installation. After some initial troubles with the paths to my gcc libs, everyting w…
-
Hey there!
I've trained a UNet model following these [instructions](https://colab.research.google.com/drive/1CCSM2FLOtHx0dPr1HgHFX0yLAgpOs7eT?usp=sharing#scrollTo=unP3cnxo_N72) but with two classes…
-
Looks like it's complaining for "edgetpu" => ModuleNotFoundError: No module named 'edgetpu'
Is there a quick workaround for using the previous API instead? Like flashing Day 13?
Thx
-
When reading the Datasheet, both should have the edge TPU available. But when I run my code with the USB Accelerator I have around 5x faster inference speed vs the DevBoard Mini. I exclusively measure…
aeon0 updated
3 years ago
-
So, I'm quite stumped by this. So I had this model that I compiled for the edge tpu that runs an inference in about 0.017 seconds which is a tiny bit slow for me so I decided to simplify the model a l…
-
Trying to run detect.py on the coral dev board, using coral camera, and running into this issue continually.
`$ python3 detect.py`
`Loading ../all_models/mobilenet_ssd_v2_coco_quant_postprocess_…
-
Hi, does this project work on native OSX? I'm running Catalina. Coral (with pycoral) is installed properly, demo examples work.
When trying to run the posenet simple image example, it seems to find…