graph - Getting unwanted and duplicate blocks in tensorboard but not in model.summary()
问题描述
I am using a CNN architecture and adding few more layers in between and creating a new model. By using model.summary() on this new model, I see everything is aligned fine but in tensorboard, I am seeing duplicate blocks connected around with new blocks.Kind of new network parallely drawn with the old network block and some connection in between.
I am using tensorboard = Tensorboard() for the tensorboard in keras.
Please advise why I see these connections and old network blocks in parallel with new model blocks but on the other hand model.summary() looks totally fine.
I am trying to understand so any detail on this will help.
解决方案
I have faced the similar issue.
The main reason for this is, whenever the model is created, every layer gets a new name. For example: if you have a model with two 2d-convolutional layers followed by a dense layer. Creating the model for the 1st time and executing model.Summary()
, results in the below layer names:
- conv2d_1
- conv2d_2
- dense_1
While re-executing the same code, yields:
- conv2d_3
- conv2d_4
- dense_2
At the same time, the logs that Tensor-board uses are overwritten. Hence, parallel blocks of layers with different names appears.
推荐阅读
- python - 如何在包含列总和的熊猫数据框中附加一行
- elasticsearch - 更改 lucene/elasticsearch 中的复合令牌默认行为
- excel - 具有重复值的 Excel 行号
- python - 这个用于查找所有可能路径的图形的 python 代码运行但不返回任何结果
- java - jackson-databind 2.9.9.3 在 AnnotatedCreatorCollector 中抛出 NullPointerException
- javascript - 如何使用 Javascript 制作密码提示,它将显示带有正确密码的图片或文本?
- sql - 在计算 SUM 之前过滤列(错误:将数据类型 varchar 转换为 int 时出错)
- c# - 尝试反序列化多维数组时出现 Newtonsoft JSON JsonReaderException
- python - 2020年安装python2
- wordpress - 显示来自 woocommerce 可变产品的默认和选定的变体价格