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

I trained the model with 4 GPUs (GTX 2080) with batchsize 4, and the PSPNet achieves the mIOU of 76.42%. But I found the visualization results are not correct. Here is an example.
.
But the ground-truth label is like:
![image](https://user-images.githubusercontent.com/35193979/64757149-

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.

Thank you for all the input.
I have, however, problems to get the tutorial (https://modeldepot.io/hellochick/pspnet) running on my machine. Unfortunately, I'm very new to python.

Minimal example:
import tensorflow as tf
import numpy as np
from scipy import misc
import matplotlib.pyplot as plt

from PIL import Image

from model import PSPNet101, PSPNet50
from tools import *

im