Xinyu Tu

plt.plot(history["global_history"]['accuracy'])会报错，应该修改为plt.plot(history.global_history['accuracy'])

1

### 文档修改建议 技术信息 页面 https://www.secretflow.org.cn/zh-CN/docs/secretflow/v1.3.0b0/tutorial/Federate_Learning_for_Image_Classification 源码 https://github.com/secretflow/secretflow/blob/e0435dadd4d2d1ec2303e3b6aec9059fcb816f5f/docs/tutorial/Federate_Learning_for_Image_Classification.ipynb 浏览器 Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/121.0.0.0 Safari/537.36

Questions on the communication size of AlexNet (on CIFAR 10) and LeNet (on MNIST) in Table 2 of the paper

1

We noticed that the shape of data samples in CIFAR 10 is 32x32x3, while for MNIST is 28x28x1. Moreover, the number of parameters in AlexNet is much bigger than LeNet....