[英]Can you plot the accuracy graph of a pre-trained model? Deep Learning
I am new to Deep Learning.我是深度学习的新手。 I finished training a model that took 8 hours to run, but I forgot to plot the accuracy graph before closing the jupyter notebook.
我完成了一个需要 8 小时运行的 model 的训练,但在关闭 jupyter 笔记本之前我忘记了 plot 准确度图。
I need to plot the graph, and I did save the model to my hard-disk.我需要 plot 图表,我确实将 model 保存到我的硬盘上。 But how do I plot the accuracy graph of a pre-trained model?
但是我如何 plot 预训练的 model 的准确度图? I searched online for solutions and came up empty.
我在网上搜索了解决方案,结果一无所获。
Any help would be appreciated!任何帮助,将不胜感激! Thanks!
谢谢!
What kind of framework did you use and which version?您使用了什么样的框架以及哪个版本? In the future problem, you may face, this information can play a key role in the way we can help you.
在未来您可能面临的问题中,这些信息可以在我们帮助您的方式中发挥关键作用。
Unfortunately, for Pytorch/Tensorflow the model you saved is likely to be saved with only the weights of the neurons , not with its history.不幸的是,对于 Pytorch/Tensorflow,您保存的 model 可能只保存神经元的权重,而不是其历史。 Once Jupyter Notebook is closed, the memory is cleaned (and with it, the data of your training history).
一旦 Jupyter Notebook 关闭,memory 就会被清理(以及你的训练历史数据)。
The only thing you can extract is the final loss/accuracy you had.您唯一可以提取的是您拥有的最终损失/准确性。
However, if you regularly saved a version of the model, you can load them and compute manually the accuracy/loss that you need.但是,如果您定期保存 model 的版本,您可以加载它们并手动计算您需要的准确度/损失。 Next, you can use matplotlib to reconstruct the graph.
接下来,您可以使用 matplotlib 来重构图。
I understand this is probably not the answer you were looking for.我知道这可能不是您想要的答案。 However, if the hardware is yours, I would recommend you to restart training.
但是,如果硬件是你的,我建议你重新开始训练。 8h is not that much to train a model in deep learning.
8h 在深度学习中训练 model 并不算多。
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.