深度卷积神经网络(AlexNet)

https://zh.d2l.ai/chapter_convolutional-modern/alexnet.html

我为什么在colab上训练模型,最后看曲线的时候,平台爆出这个错误?
麻烦帮我看一下

可以参考下这个 :
(43条消息) 关于使用对d2l 画图过程中出现cannot import name ‘_check_savefig_extra_args‘ from ‘matplotlib.backend_bases‘_SnoopyTag的博客-CSDN博客

自己模拟了一下AlexNet,
image
设置的0.01学习率,为什么这么震荡呢?是学习率太大的原因吗

I have a question that the input is 224x224(r), and the k=11, p=1, s=4, resulting an output tensor 54x54 in the article.(x means multiply)

But as the formula is:
(r+px2-k)/s+1=(224+1x2-11)/4+1=54.75, so how to deal with the 0.75 in the real condition, or just ignore the little question?
thank you!