Continuous activation map generation at training process

Versión 1.0.3 (10 MB) por Kenta
Please click the thumbnail to watch the GIF file. 概要はサムネイルをクリックして下さい.This demo shows how to continuously create a class activation mapping.
143 descargas
Actualizado 22 Mar 2020

[English]
This demo shows how to continuously create a class activation mapping (CAM) during the training process with a custom learning rate schedule.
Automatic differentiation enables you to customize CNN as you want. This example trains a network to classify data and simulteniously compute the CAM (Class Activation Mapping) of the validation data with the weights during the training.
This demo can visualize how the CNNs get to focus on the region in the image to classify which leads to the reability of the network and helps a lot in education of CNNs. Further, if the CNN is over-tuned to the dataset, the process also can be visualized.
The class activation mapping was done referring to the paper below.
Zhou, Bolei, Aditya Khosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba. "Learning deep features for discriminative localization." In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921-2929. 2016.
This demo using the custom training loop was made with the official document below.
https://jp.mathworks.com/help/deeplearning/ug/train-network-using-custom-training-loop.html
If you like to explore the reason of the classification behind the network for the test image, you can use this demo (https://jp.mathworks.com/matlabcentral/fileexchange/75418-classify-crack-image-using-deep-learning-and-explain-why).

[Japanese]
深層学習の分類時にどこに注目したのかを示すデモです。カスタムループを用いて、訓練中に、ネットワークの注目範囲がどのように変化するのかを可視化します。サムネイルのGIFのように、各イテレーションごとにCAMとよばれる、CNNの注目範囲を可視化し、
重み更新によって、どんどんよい特徴を捉えるようになっていることを示しています。イテレーションごとに特徴量を可視化することで、訓練の進むイメージを視覚的につかめるかもしれないと思い作成しました。カスタムループを用いない例は以下のURLにありました。
https://jp.mathworks.com/matlabcentral/fileexchange/69357-class-activation-mapping
また、可視化のほかの例としては以下のようなものがあります。
https://jp.mathworks.com/matlabcentral/fileexchange/75418-classify-crack-image-using-deep-learning-and-explain-why

Citar como

Kenta (2024). Continuous activation map generation at training process (https://github.com/giants19/Continuous-class-activation-generation-during-training-process-using-Matlab), GitHub. Recuperado .

Compatibilidad con la versión de MATLAB
Se creó con R2020a
Compatible con cualquier versión
Compatibilidad con las plataformas
Windows macOS Linux

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

No se pueden descargar versiones que utilicen la rama predeterminada de GitHub

Versión Publicado Notas de la versión
1.0.3

Description added

1.0.2

Description added

1.0.1

Thumbnail changed

1.0.0

Para consultar o notificar algún problema sobre este complemento de GitHub, visite el repositorio de GitHub.
Para consultar o notificar algún problema sobre este complemento de GitHub, visite el repositorio de GitHub.