Waymo Open Dataset: Tensorflow Object Detection API



Original Source Here

環境配置

安裝 Way open dataset

pip3 install waymo-open-dataset-tf-2-1-0==1.2.0

安裝 COCO API

pip install cython
pip install git+https://github.com/philferriere/cocoapi.git#subdirectory=PythonAPI

安裝 Tensorflow 2 Object Detection API

參考 TensorFlow 2 Object Detection API tutorial 安裝套件

Step1: git clone Tensorflow 2 Object Detection API

git clone https://github.com/tensorflow/models.git

Step2: 到 models/research/ 執行

protoc object_detection/protos/*.proto --python_out=. 

Step3: 將 API 加到環境變數

export PYTHONPATH=$PYTHONPATH:`pwd`:`pwd`/slim

Step4: 複製 setup.py 到 models/research/

cp object_detection/packages/tf2/setup.py ./

Step5: 安裝 setup.py

python -m pip install .

Step6: 測試是否安裝成功

python object_detection/builders/model_builder_tf2_test.py

Step7: 建立資料夾結構

Waymo
├───models #Tensorflow Object Detection API
├───training_configs #訓練用的 config
├───pre-trained-models #預訓練模型
├───exported-models #輸出模型
└───data #訓練資料
└───segment-???.tfrecord

AI/ML

Trending AI/ML Article Identified & Digested via Granola by Ramsey Elbasheer; a Machine-Driven RSS Bot

%d bloggers like this: