系统信息
问题描述
我正在遵循使用英特尔®神经棒2进行对象检测的教程https://towardsdatascience.com/speed-up-predictions-on-low-power-devices-using-neural-compute-stick-and-openvino-98f3ae9dcf41
在示例中,我使用以下命令安装必备组件
sudo ./opt/intel/computer_vision_sdk/deployment_tools/model_optimizer/install_prerequisites/install_prerequisites.sh
tensorflow是先决条件安装的,我也使用pip install安装了tensorflow,但是当我运行下一个命令时
mo_tf.py \
--input_model ~/Downloads/ssd_mobilenet_v1_coco_2018_01_28/frozen_inference_graph.pb \
--tensorflow_use_custom_operations_config /opt/intel/computer_vision_sdk/deployment_tools/model_optimizer/extensions/front/tf/ssd_support.json \
--tensorflow_object_detection_api_pipeline_config ~/Downloads/ssd_mobilenet_v1_coco_2018_01_28/pipeline.config \
--data_type FP16
我收到以下错误
F tensorflow/core/platform/cpu_feature_guard.cc:37]
The tensorflow library was compiled to use AVX instructions, but these aren't available in your machine
Aborted (core dumped)
尝试并导入tensorflow
时遇到相同的错误我该怎么做才能解决此错误?
答案 0 :(得分:0)
该错误消息表明机器不支持avx。是这样吗?您可以引用此链接How to tell if a Linux machine supports AVX/AVX2 instructions?进行检查。
如果您的计算机不支持AVX,那么解决方案是从不包括那些设置的源构建tensorflow