[LAB 11 · 从 RGB 到像素：读出、FCN 与边界](/course/notebooks/9e268706471944e3a59e6f568f9ce9a3.html)

# 先预测采样结果，再判断指标名称 · 实现代码
[独立阅读](/course/notebook-blocks/69c46b79dec64732aba46f41c673c245.html)
按问题继续

前景/背景/mIoU口径、RGB到mask训练、FCN与1×1读出及边界
展开完整实现代码
```
import importlib.util, subprocess, sys
from pathlib import Path
# The only download, if needed, is open-source Python packages, not model weights.
if importlib.util.find_spec('torch') is None:
    subprocess.check_call([sys.executable, '-m', 'pip', 'install', 'torch', '--index-url', 'https://download.pytorch.org/whl/cpu'])
missing=[p for p in ['numpy','matplotlib'] if importlib.util.find_spec(p) is None]
if missing: subprocess.check_call([sys.executable,'-m','pip','install',*missing])
import torch, numpy as np
print('Python',sys.version.split()[0], 'torch',torch.__version__, 'numpy',np.__version__, 'device: CPU')
```