In addition to Weibo, there is also WeChat
Please pay attention
WeChat public account
Shulou
2025-04-05 Update From: SLTechnology News&Howtos shulou NAV: SLTechnology News&Howtos > Internet Technology >
Share
Shulou(Shulou.com)06/01 Report--
This article introduces the error tips of Hayth NNIE mapper conversion model: "input shape size is not equal to input name size", the content is very detailed, interested friends can refer to, hope to be helpful to you.
The caffe model works fine on the computer, but failed to convert the model using Heath Nnie _ mapper. The output is as follows:
Wuyy@wuyy-VirtualBox:~/dl/weights$ nnie_mapper_12 yolov3_608.cfg Mapper Version 1.2.2.1_B030 (NNIE_1.2) 19090610466402begin net parsing....***ERROR: file: parseInputDim line: 2244input shape size is not equal to input name Error: file: parseInputParamOldVersion line: 2151ERROR: RUN FAILURE in line 2151. Return = 262148***ERROR: file: parseModel line: 14827ERROR: RUN FAILURE in line 14827. Return = 262148***ERROR: file: compile line: 609ERROR: RUN FAILURE in line 609. Return = 262148***ERROR: file: iFEPCompile line: 114ERROR: RUN FAILURE in line. Return = 262148***ERROR: file: main line: 164iFEPCompile failed (262148) begin quant files writing....end quant files writing
The reason is that the format of the input layer of the deploy.prototxt file is not compatible with the format supported by Hayth's nnie_mapper. The format supported by Hayes can be found in the document: HiSVP Development Guide .pdf, Chapter: 3.2.1 deploy.prototxt input layer format the original format is as follows:
Input: "data" input_dim: 1input_dim: 3input_dim: 608input_dim: 608
The modifications are as follows:
Input: "data" input_shape {dim: 1 dim: 3 dim: 608 dim: 608}
Rerun nnie_mapper after modification, and the conversion is successful:
Wuyy@wuyy-VirtualBox:~/dl/weights$ nnie_mapper_12 yolov3_608.cfg Mapper Version 1.2.2.1_B030 (NNIE_1.2) 19090610466402begin net parsing....end net parsingbegin prev optimizing....end prev optimizing....begin net quantalizing (CPU).... end quantalizingbegin optimizing....end optimizingbegin NNIE [0] mem allocation....end NNIE [0] memory allocatingbegin NNIE [0] instruction generating....end NNIE [0] instruction generatingbegin parameter compressing... .end parameter compressingbegin compress index generating....end compress index generatingbegin binary code generating....end binary code generatingbegin quant files writing....end quant files writingwuyy@wuyy-VirtualBox:~/dl/weights$ lscnn_net_tree.dot dog_bike_car.jpg instruction.txt yolov3_416.caffemodel yolov3_608_inst.wkcnn_net_tree_gv.dot dout_nne_para.txt mapper_debug.log yolov3_416.cfg yolov3_608.prototxtcnn _ net_tree_org.dot gfpq_param.txt mapper_error.log yolov3_416.prototxtcnn_net_tree_pre.dot ibd_para.txt netmem_info.data yolov3_608.caffemodelcnn_net_tree_pre_org.dot image_ref_list.txt RUNTIME.txt yolov3_608.cfg error prompt about Hayes NNIE mapper transformation model: what to do with "input shape size is not equal to input name size" is shared here. I hope the above content can be of some help to you and learn more knowledge. If you think the article is good, you can share it for more people to see.
Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.
Views: 0
*The comments in the above article only represent the author's personal views and do not represent the views and positions of this website. If you have more insights, please feel free to contribute and share.
Continue with the installation of the previous hadoop.First, install zookooper1. Decompress zookoope
"Every 5-10 years, there's a rare product, a really special, very unusual product that's the most un
© 2024 shulou.com SLNews company. All rights reserved.