立即学习:https://edu.csdn.net/course/play/28807/427196?utm_source=blogtoedu
实验三:使用Resnet-50进行分类实验
- 进入实验目录
cd ~/CSDN200/02/exercise-1/
- 设置实验路径
export lab_dir=~/CSDN200/02/exercise-1/
- 初始化OpenVINO
source /opt/intel/openvino/bin/setupvars.sh
- 使用模型优化器
模型已经提前下载在你的主机上了,
dc2-user@10-0-116-57:~/CSDN200/02/exercise-1$ ll public/resnet-50/
total 100104
drwxrwxr-x 2 dc2-user dc2-user 4096 Jul 8 14:27 ./
drwxrwxr-x 4 dc2-user dc2-user 4096 Jul 8 14:27 ../
-rw-rw-r-- 1 dc2-user dc2-user 102462397 Jul 8 14:27 resnet-50.caffemodel
-rw-rw-r-- 1 dc2-user dc2-user 32500 Jul 8 14:27 resnet-50.prototxt
请添加输入public/resnet-50/文件夹下的Resnet50 caffemodel模型
mo_caffe.py --input_model $lab_dir/public/resnet-50/resnet-50.caffemodel --output_dir $lab_dir
Model Optimizer arguments:
Common parameters:
- Path to the Input Model: /home/dc2-user/CSDN200/02/exercise-1//public/resnet-50/resnet-50.caffemodel
- Path for generated IR: /home/dc2-user/CSDN200/02/exercise-1/
- IR output name: resnet-50
- Log level: ERROR
- Batch: Not specified, inherited from the model
- Input layers: Not specified, inherited from the model
- Output layers: Not specified, inherited from the model
- Input shapes: Not specified, inherited from the model
- Mean values: Not specified
- Scale values: Not specified
- Scale factor: Not specified
- Precision of IR: FP32
- Enable fusing: True
- Enable grouped convolutions fusing: True
- Move mean values to preprocess section: False
- Reverse input channels: False
Caffe specific parameters:
- Path to Python Caffe* parser generated from caffe.proto: /opt/intel/openvino_2020.3.194/deployment_tools/model_optimizer/mo/front/caffe/proto
- Enable resnet optimization: True
- Path to the Input prototxt: /home/dc2-user/CSDN200/02/exercise-1//public/resnet-50/resnet-50.prototxt
- Path to CustomLayersMapping.xml: Default
- Path to a mean file: Not specified
- Offsets for a mean file: Not specified
Model Optimizer ver