Image Classification Algorithm Class Activation Map

Hey!

I am using SageMaker's built in image classification algorithm and currently have a trained model that can make predictions. I am wondering if there is an easy way to use this model to make a class activation map to better debug my classifier and see why it is making the predictions it is?

Thanks!

주제

기계 학습 및 AI

태그

아마존 SageMaker

언어

English

SteveLeo

질문됨 5년 전211회 조회

2개 답변

최신
최다 투표
가장 많은 댓글

이 답변이 도움이 되었나요?커뮤니티가 여러분의 지식을 활용할 수 있도록 정답을 찬성하세요.

Hi Steveleo,

Thanks for trying out the image classification algorithm. The trained model from SageMaker built-in image classification is a standard MXNet model. Here is a notebook https://github.com/dmlc/mxnet-notebooks/blob/master/python/how_to/predict.ipynb that you can follow to extract features.

Thanks,
Xiong

AWS-User-5980563

답변함 5년 전

For the class activation map, please check this http://mxnet.incubator.apache.org/versions/master/tutorials/vision/cnn_visualization.html .

AWS-User-5980563

답변함 5년 전

Image Classification Algorithm Class Activation Map

관련 콘텐츠