第十周----TensorFlow Object Detection API学习
因为参加软件杯缘故,就对TensorFlow Object Detection API以及mask rcnn进行学习。
首先是配置,我是windows cpu所以会很麻烦。
参考:https://blog.csdn.net/zj1131190425/article/details/80711857
很详细,但是我出现了以下问题:
1.
Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
解决方案:https://blog.csdn.net/feng98ren/article/details/84874326
我是cpu,所以直接添加了如下语句
import os os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
2.
UserWarning: Matplotlib is currently using agg, which is a non-GUI backend.
我直接运行的models下的py文件,所以找到 models-master/research/object_detection/uitls/visualization_utils.py
将其中的Agg改为TKAgg
运行成功: