熊熊的部落格

Nvidia Jatson Nano 安裝和測試TensorFlow Lite

Step01.安裝相關套件

sudo apt-get update
sudo apt-get upgrade
pip3 install Cython
pip3 install --upgrade Cython
sudo apt-get install python3-numpy
pip3 install numpy

Step02.安裝Tensorflow Lite

#1. 先確認python版本
python --version

#2. 到官網下載對應的版本
https://www.tensorflow.org/lite/guide/python

#3. 範例python 3.7
pip3 install https://dl.google.com/coral/python/tflite_runtime-2.1.0.post1-cp37-cp37m-linux_aarch64.whl

Step03.下載官網的範例

# 取得 photo(grace_hopper.bmp)
curl https://raw.githubusercontent.com/tensorflow/tensorflow/master/tensorflow/lite/examples/label_image/testdata/grace_hopper.bmp > /tmp/grace_hopper.bmp
# 取得 model(mobilenet_v1_1.0_224.tflite)
curl https://storage.googleapis.com/download.tensorflow.org/models/mobilenet_v1_2018_02_22/mobilenet_v1_1.0_224.tgz | tar xzv -C /tmp
# 取得labels(labels.txt)
curl https://storage.googleapis.com/download.tensorflow.org/models/mobilenet_v1_1.0_224_frozen.tgz  | tar xzv -C /tmp  mobilenet_v1_1.0_224/labels.txt
# 將labels.txt移動到/tmp/
mv /tmp/mobilenet_v1_1.0_224/labels.txt /tmp/

Step04.執行範例

python3 label_image.py \
--model_file /tmp/mobilenet_v1_1.0_224.tflite \
--label_file /tmp/labels.txt \
--image /tmp/grace_hopper.bmp