Difference between revisions of "EBC Exercise 49 Setting Up coral"
m (→Install) |
m (→Set up hardware: Setting up USB) |
||
Line 17: | Line 17: | ||
A then it disappears and the following appears | A then it disappears and the following appears | ||
Google Inc. | Google Inc. | ||
+ | |||
+ | On my Surface I had to | ||
+ | * quit VirtualBox | ||
+ | * On your host machine, download the '''VirtualBox Extension Pack''' from: https://www.virtualbox.org/wiki/Downloads. | ||
+ | * on your host, login as Administrator | ||
+ | * run VirtualBox, but don't start a machine | ||
+ | * go to Extensions and click the '''+''' button and add the extension pack you just downloaded | ||
+ | * go to the USB settings and select the USB3.0 xHCI button | ||
+ | * logoff as Administrator | ||
+ | * run VirtualBox and start your machine | ||
+ | * repeat the plugging in steps above | ||
=== Test === | === Test === |
Revision as of 12:28, 4 April 2019
Embedded Linux Class by Mark A. Yoder
Here are instructions on how to run Google's coral ([1])
Install
wget http://storage.googleapis.com/cloud-iot-edge-pretrained-models/edgetpu_api.tar.gz # 6 seconds tar xzf edgetpu_api.tar.gz cd python-tflite-source
Edit last line of install.sh to use python3
bash ./install.sh # 22 seconds, 33s on Surface
Set up hardware
Plug in. If you are running a virtual machine, have it capture
Global Unichip Corp.
A then it disappears and the following appears
Google Inc.
On my Surface I had to
- quit VirtualBox
- On your host machine, download the VirtualBox Extension Pack from: https://www.virtualbox.org/wiki/Downloads.
- on your host, login as Administrator
- run VirtualBox, but don't start a machine
- go to Extensions and click the + button and add the extension pack you just downloaded
- go to the USB settings and select the USB3.0 xHCI button
- logoff as Administrator
- run VirtualBox and start your machine
- repeat the plugging in steps above
Test
# From the python-tflite-source directory cd edgetpu/
python3 demo/classify_image.py \ --model test_data/mobilenet_v2_1.0_224_inat_bird_quant_edgetpu.tflite \ --label test_data/inat_bird_labels.txt \ --image test_data/parrot.jpg
The following took 6 seconds on my Ubuntu virtual machine.
Embedded Linux Class by Mark A. Yoder