In file binary segmentation (camvid).ipynb, block 5, there is:

# Lets look at data we have
dataset = Dataset(x_train_dir, y_train_dir, classes=['car', 'pedestrian'])
image, mask = dataset[5] # get some sample
visualize(
    image=image, 
    cars_mask=mask[..., 0].squeeze(),
    sky_mask=mask[..., 1].squeeze(),
    background_mask=mask[..., 2].squeeze(),
)

here, sky_mask

Please explain the suggested feature in detail.

Being able to use Server outside of NetworkBehaviour will make it quicker to create Server only methods. The currently you have to add a manual check for NetworkServer.active.

[Server] causes Weaver to add the following code at the start of methods, which does not depend on NetworkBehaviour.

if (!NetworkServer.active)

1. 31页，第一行
   
   应改成
   

2. 35 页， 正定矩阵的定义 （公式 2-15）
   标准正定矩阵的定义，应该没有 “对称矩阵” 这一条件吧？ 只是您在本书大多讨论的是“对称”正定矩阵，所以加上了 “对称” 这一条件？

3. 38页， 奇异值分解定义（公式 2-16）
   ![default](https://

如果设置
cfg.NUM_TRAINERS = 4
cfg.TRAINER_ID = 0，1，2，3
if self.shuffle and cfg.NUM_TRAINERS > 1: np.random.RandomState(self.shuffle_seed).shuffle(self.all_lines) num_lines = len(self.all_lines) // cfg.NUM_TRAINERS self.lines = self.all_lines[num_lines * cfg.TRAINER_ID: num_lines * (cfg.TRAINER_ID + 1)] self.shuffle_seed += 1
上面代码中的self.

Is there a corresponding paper?

This article states: "We will present our solution at the IEEE International Conference on Data Science and Advanced Analytics (DSAA)". Unfortunately, I couldn't find the corresponding paper.

Bests,
Sebastian