---
tags: 機械学習
---

# CoralをRaspberry PIで動かす With TFLite

## Run demo

`python3-pycoral`と`libedgetpu1-std`をドキュメントに従ってインストールする

https://coral.ai/docs/accelerator/get-started/#runtime-on-windows

その後、デモを動かす。

pi@raspberrypi:~/Workspace/coral/pycoral $ python3 examples/classify_image.py --model test_data/mobilenet_v2_1.0_224_inat_bird_quant_edgetpu.tflite --labels test_data/inat_bird_labels.txt --input test_data/parrot.jpg
----INFERENCE TIME----
Note: The first inference on Edge TPU is slow because it includes loading the model into Edge TPU memory.
17.3ms
4.4ms
5.3ms
4.4ms
4.4ms
-------RESULTS--------
Ara macao (Scarlet Macaw): 0.75781

ちなみに、Coralでやると。。。。 :thinking_face:

## TFLiteでAutoMLで学習済みのものを動かす

kore wo sansho

https://coral.ai/docs/edgetpu/tflite-python/#inferencing-example
https://github.com/google-coral/pycoral/blob/master/examples/detect_image.py