||
1.Considering that ImageNet consists of many fine-grained object categories and that some images contain multiple object categories, this is an incredible feat, nearly on par with human performance. While at first glance the model may appear incredibly complex, upon closer inspection, the overall structure of the model can be broken down into a few basic sections: the stem, the inception modules, the auxiliary classifiers, and finally the output classifier.
2. GoogLetNet is Inception-V1. Its TensorFlow implementation is at https://gist.github.com/joelouismarino/a2ede9ab3928f999575423b9887abd14
Its related blog is at http://joelouismarino.github.io/blog_posts/blog_googlenet_keras.html
Inception-V3 is at https://github.com/tensorflow/models/tree/master/inception
3. Take advantage of Keras to recall GoogLeNet
Archiver|手机版|科学网 ( 京ICP备07017567号-12 )
GMT+8, 2024-9-24 07:22
Powered by ScienceNet.cn
Copyright © 2007- 中国科学报社