Pytorch模型训练翻车记录

背景 在Google Colab上进行压缩采样的图像重建模型的训练。已经有了训练好的压缩率是0.20的模型(下文用r0.20之类的记号表示压缩率及其对应的模型)。现在想训练r0.25。觉得从头开始训练很费时间于是就想出了这么个办法 ...

2019年4月11日 · 2 分钟 · 737 字 · Thomas Xu

Installing nvidia driver on Fedora 29

Forewords Installing the nvidia driver on Fedora has been a painful experience for me. If I don’t get it wrong, I have been trying since F26! I will not touch on bumblebee. I will instead use nvidia-xrun to utilize the driver. This article serves as a reminder for myself on what did I do to make things work for my Intel/nvidia hybrid laptop. It might hopefully help other people as well. ...

2019年2月3日 · 2 分钟 · 522 字 · Thomas Xu

今与昔的境界线

南京!南京!

2018年12月13日 · 1 分钟 · 6 字 · Thomas Xu

lambda in Python: is it returning multiple values?

To begin with let’s just have look at the old school of lambda in Python. As we know, lambda x: return x**2 is exactly equivalent to def squared(x): return x**2 Now look at this >>> f1 = lambda x,y,z: x+1, y+1, z+1 >>> print(f1(1,1,1)) What will you get on the screen? A tuple of (2, 2, 2)? No. You get an error instead. Traceback (most recent call last): File "<pyshell#7>", line 1, in <module> print(f1(1,1,1)) TypeError: 'tuple' object is not callable</module> Now that the “returning part” of lambda is covering the contents before comma only, let’s explicitly add the brackets: ...

2018年9月16日 · 1 分钟 · 197 字 · Thomas Xu

Quick note on Python syntax magics

As noted in Python 3 documention, behaviors of +, -, *, etc. can be redefined. Specially, I would like to take notes on some special yet common methods. __repr__ method This method is called when you apply print on the instance. Could be useful when debugging class related problems. __enter__, __exit__ methods Those two methods are key components of a context manager. Refer to https://jeffknupp.com/blog/2016/03/07/python-with-context-managers/ to get a sense on how to manage the fragile resouces with context manager.

2018年9月11日 · 1 分钟 · 79 字 · Thomas Xu