简体   繁体   English

如何在图(.pb)中重新训练模型?

[英]How to retrain model in graph (.pb)?

I have model saved in graph (.pb file). 我将模型保存在图形(.pb文件)中。 But now the model is inaccurate and I would like to develop it. 但是现在该模型不准确,我想开发它。 I have pictures of additional data to learn, but I don't if it's possible or if it's how to do it? 我有要学习的其他数据的图片,但是如果有可能或者它是怎么做的,我没有吗? The result must be the modified of new data pb graph. 结果必须是新数据pb图的修改。

It's a good question. 这是一个好问题。 Actually it would be nice, if someone could explain how to do this. 实际上,如果有人可以解释如何做到这一点,那就太好了。 But in addition i can say you, that it would come to "catastrophic forgetting", so it wouldn't work out. 但除此之外,我可以对您说,这将导致“灾难性的遗忘”,因此无法解决。 You had to train all your data again. 您必须再次训练所有数据。

But anyway, i also would like to know that espacially for ssd, just for test reasons. 但是无论如何,我也想出于测试的目的,特别针对ssd知道这一点。

The mozzila/DeepSpeech community has contributed a way to initialize training from a frozen graph(.pb). mozzila / DeepSpeech社区提供了一种从冻结图(.pb)初始化训练的方法。 It does not restores optimizer parameters, so adjusting the learning rate is necessary. 它不会恢复优化器参数,因此需要调整学习率。

You could find the code at: 您可以在以下位置找到代码:

https://github.com/mozilla/DeepSpeech/blob/master/DeepSpeech.py#L1562 https://github.com/mozilla/DeepSpeech/blob/master/DeepSpeech.py​​#L1562

Hope this helps! 希望这可以帮助!

声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.

相关问题 如何通过spacy重新训练模型? - How the model is retrain by spacy? 如何将急切执行的模型转换为静态图并保存为.pb文件? - How to convert model in eager execution to static graph and save in .pb file? 如何重新训练/更新 keras 模型? - How to retrain/update keras model? 如何加载和重新训练 tflean 模型 - How to load and retrain tflean model 如何为自定义图像重新训练 mobilenet 模型 - How to retrain mobilenet model for custom images 如何重新训练检测 model 并为英特尔 Movidius 量化它? - How to retrain a detection model and quantize it for Intel Movidius? 如何将Tensorflow Simple Audio Recognition冷冻图(.pb)转换为Core ML模型? - How to convert Tensorflow Simple Audio Recognition frozen graph(.pb) to Core ML model? 如何将具有自定义 keras 层(.h5)的 keras 模型冻结到张量流图(.pb)? - How to freeze a keras model with custom keras layers(.h5) to tensorflow graph(.pb)? 如何将预训练的 tensorflow pb 冻结图转换为可修改的 h5 keras 模型? - How to convert a pretrained tensorflow pb frozen graph into a modifiable h5 keras model? 如何将基于 tensorflow 构建的修改模型(用于迁移学习,in.ckpt 格式)导出到冻结图(.pb 文件) - How to export a modified model(used for transfer learning, in .ckpt format) built on tensorflow to a frozen graph(.pb file)
 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM