官术网_书友最值得收藏!

Visualizing network graphs

While being able to see into our training process and comparing models is obviously pretty great, that's not all TensorBoard can do. We can also use it to visualize network structure. Here, I've navigated to GRAPHS and pulled up the structure of the deep neural network:

TensorBoard displaying the structure of the deep neural network

The training node represents the input tensor, and by default, it's this giant octopus that connects to the rest of the graph in a somewhat unhelpful way. To fix that, you can just click the node and click Remove from the main graph. It will then be moved off to the side.

主站蜘蛛池模板: 阜阳市| 温宿县| 高州市| 紫金县| 临高县| 仁怀市| 曲水县| 宜宾县| 梧州市| 长沙县| 资溪县| 舒城县| 青浦区| 黎城县| 曲靖市| 电白县| 花莲县| 庄浪县| 黔西| 梧州市| 科技| 宝丰县| 新源县| 南昌市| 拉孜县| 河东区| 平远县| 宁陕县| 顺昌县| 崇左市| 仲巴县| 中江县| 通道| 营山县| 湖南省| 荆州市| 弥渡县| 科技| 北川| 磴口县| 稷山县|