- Machine Learning Projects for Mobile Applications
- Karthikeyan NG
- 100字
- 2021-06-10 19:41:39
Converting SavedModel into TensorFlow Lite format
Converting your ML model into a TensorFlow Lite model can be done in just one line of code by calling the conversion method. Here is the simple Python snippet that converts your existing model into TensorFlow Lite format. You can feed in the existing model and convert that into .tflite format:
import sys
from tf.contrib.lite import convert_savedmodel
convert_savedmodel.convert(
saved_model_directory="/tmp/your_model",
output_tflite_file="/tmp/my_model.tflite")
The code here converts the existing model created in other frameworks into TensorFlow Lite format using FlatBuffers. There are a few conversion strategies that need to be followed.
推薦閱讀
- 零點起飛學Xilinx FPG
- 深入淺出SSD:固態存儲核心技術、原理與實戰(第2版)
- micro:bit魔法修煉之Mpython初體驗
- Camtasia Studio 8:Advanced Editing and Publishing Techniques
- CC2530單片機技術與應用
- 面向對象分析與設計(第3版)(修訂版)
- Neural Network Programming with Java(Second Edition)
- RISC-V處理器與片上系統設計:基于FPGA與云平臺的實驗教程
- 嵌入式系統原理及應用:基于ARM Cortex-M4體系結構
- Istio實戰指南
- 可編程邏輯器件項目開發設計
- Corona SDK Mobile Game Development:Beginner's Guide
- Hands-On Markov Models with Python
- 電腦組裝與維修實戰
- Hands-On Unsupervised Learning with Python