Namburger

import tensorflow as tf
if not str(tf.__version__).startswith('1.15'):
    print('please use tensorflow 1.15')
    exit()
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Input, Conv2D

tf.enable_eager_execution()

image_shape = (64,64,3)

Namburger

import os
import argparse
import cv2
import numpy as np
import sys
import time
import importlib.util
from tflite_runtime.interpreter import Interpreter
from tflite_runtime.interpreter import load_delegate

Namburger

# MAKE THIS DOCKERFILE

FROM ubuntu:20.04
ENV TZ=US/Central
RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone

WORKDIR /home
ENV HOME /home
VOLUME /data
EXPOSE 8888

Namburger

I got librosa working on the Dev Board running Mendel Day (4.0). 
Some steps may not be necessary at later OS release.

1) Preparations:
The Dev Board may not have enough storage, so I suggest first to add an sdcard (I have a 16GB card), than mount it:

mkdir /home/mendel/sdcard
sudo mount /dev/mmcblk1p1 /home/mendel/sdcard

With extra storage now, we can add some swap which may be necessary for the build:

Namburger

/dts-v1/;
/plugin/;

/ {
        compatible = "fsl,imx8mq-hdmi";

        fragment@0 {
                target-path = "/hdmi@32c00000";
                __overlay__ {
                        status = "disabled";

Namburger

FROM ubuntu:18.04

WORKDIR /home
ENV HOME /home
RUN cd ~
RUN apt-get update
RUN apt-get install -y git nano python3-pip python-dev pkg-config wget usbutils curl

RUN echo "deb https://packages.cloud.google.com/apt coral-edgetpu-stable main" \
| tee /etc/apt/sources.list.d/coral-edgetpu.list

Namburger

# This is an example of starting a systemd object detection service on boot on the Coral Dev Board.

# 1) create a file call detects.service with the following contents:

[Unit]
Description=systemd object detection service
After=weston.target

[Service]
PAMName=login

Namburger

FROM arm64v8/debian:latest

WORKDIR /home
ENV HOME /home
RUN cd ~
RUN apt-get update
RUN apt-get install -y git nano python3-pip python-dev pkg-config wget usbutils curl

RUN echo "deb https://packages.cloud.google.com/apt coral-edgetpu-stable main" \
| tee /etc/apt/sources.list.d/coral-edgetpu.list

Namburger

# Install tflite_runtime package to evaluate the model.
!pip3 install https://dl.google.com/coral/python/tflite_runtime-2.1.0.post1-cp36-cp36m-linux_x86_64.whl

# Now we do evaluation on the tflite model.
import os
import numpy as np
from tflite_runtime.interpreter import Interpreter
from tflite_runtime.interpreter import load_delegate
from PIL import Image
from PIL import ImageDraw

Namburger

THIS IS DEPRECATED


# docker can be installed on the dev board following these instructions: 
# https://github.com/f0cal/google-coral/issues/32#issuecomment-571629174
# 1) create this dockerfile
# 2) build: docker build -t "coral" .
# 3) run: docker run -it --device /dev/apex_0:/dev/apex_0 coral /bin/bash
# 4) Try the classify_image demo:
# apt-get install edgetpu-examples