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!

主题

机器学习和人工智能

标签

Amazon SageMaker

语言

English

SteveLeo

已提问 5 年前211 查看次数

2 回答

最新
投票最多
评论最多

这些答案有用吗？为正确答案投票，以帮助社区从您的知识中受益。

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

已回答 5 年前

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

AWS-User-5980563

已回答 5 年前

Image Classification Algorithm Class Activation Map

相关内容