Python 神经网络 我如何改进我的代码，使其更快

Question

I builded a U-Net NN to predict mask of the ship on the image, and I even cannot use this NN for 300 images (768x768). So, what I need to change in my code, to make it faster and less resource-consuming Link to code: https://pastecode.io/s/7yfjawdi .

Answer 1

You could run it on googlecolab ( https://colab.research.google.com/?utm_source=scs-index ). This would take care of the resource and for your first problem ( how to make it faster?) you could leverage their gpu/tpu which they provide on the colab environment itself.