[LAB 05 · 像素 patch 词典：拟合与重建](/course/notebooks/de39b998077f44cca4b8407085547766.html)

# 1 · 准备与固定输入 · 实现代码
[独立阅读](/course/notebook-blocks/d9b6b1782dd5404895a80b24f6a87f64.html)
按问题继续

真实MNIST patch的Lloyd拟合、词典中心、保留误差与历史输出
展开完整实现代码
```
# 当前项目中的独立材料：已存在则复用，缺失才从本讲原站准备。
from pathlib import Path
import io, zipfile, urllib.request
_base = Path.cwd()
_folder = 'lab10-patch'
_sentinel = 'assets/target.npz'
_choices = [_base/_folder, _base/'lecture03-labs'/_folder, _base]
_ready = next((p for p in _choices if (p/_sentinel).is_file()), None)
if _ready is None:
    _url = 'https://codingai-lec03.pages.dev/course/materials/' + _folder + '.zip'
    _payload = urllib.request.urlopen(_url, timeout=60).read()
    with zipfile.ZipFile(io.BytesIO(_payload)) as _archive:
        _names = [i.filename for i in _archive.infolist() if not i.is_dir()]
        _prefix = _folder + '/'
        _prefixed = all(n.startswith(_prefix) for n in _names)
        _destination = _base if _prefixed else _base/_folder
        for _item in _archive.infolist():
            _target = (_destination/_item.filename).resolve()
            if not _target.is_relative_to(_destination.resolve()):
                raise ValueError('材料包中有越界路径，停止解压。')
            if _item.is_dir():
                _target.mkdir(parents=True, exist_ok=True)
            elif not _target.exists():
                _target.parent.mkdir(parents=True, exist_ok=True)
                _target.write_bytes(_archive.read(_item))
    _ready = next((p for p in _choices if (p/_sentinel).is_file()), None)
assert _ready is not None, '请将本讲完整材料包解压到当前项目的 ' + _folder + '/；保留文件结构。'
LAB_ROOT = _ready
print('材料目录已就绪：', LAB_ROOT)

import json, hashlib, platform, sys
from pathlib import Path
import numpy as np
import matplotlib.pyplot as plt
ROOT=LAB_ROOT
if not (ROOT/'assets').is_dir() and (ROOT/'lab10-patch'/'assets').is_dir():ROOT=ROOT/'lab10-patch'
assert (ROOT/'assets').is_dir(), '请解压本实验完整包，并在该目录或其父目录运行。'
OUT=ROOT/'runs/current'; OUT.mkdir(parents=True,exist_ok=True)
FIG=OUT/'figures'; FIG.mkdir(exist_ok=True)
plt.rcParams.update({'figure.dpi':120,'font.size':10,'axes.spines.top':False,'axes.spines.right':False})
BLUE,GOLD,GREEN,PURPLE='#002676','#E6A500','#00856A','#69458D'
def sha_file(path):return hashlib.sha256(Path(path).read_bytes()).hexdigest()
def savefig(name):
    if not plt.gcf().get_constrained_layout():plt.tight_layout()
    plt.savefig(FIG/name,dpi=140,bbox_inches='tight');plt.show()

provenance=json.loads((ROOT/'assets/provenance.json').read_text())
assert sha_file(ROOT/'assets/target.npz')==provenance['target_asset_sha256']
with np.load(ROOT/'assets/target.npz',allow_pickle=False) as z:
    images=z['images'];sample_ids=z['official_train_ids'];split=z['split']
# digit_labels are in the source archive but deliberately never read here.
assert len(set(sample_ids))==640
train=np.flatnonzero(split==0);heldout=np.flatnonzero(split==2)
assert not set(sample_ids[train])&set(sample_ids[heldout])
partition=np.random.default_rng(20260908).permutation(60000)
assert np.array_equal(sample_ids,partition[12000:12640])
x=images.astype(np.float32)/255
shifted=np.zeros_like(x);shifted[:,:,:,2:]=x[:,:,:,:-2];x=shifted
assert x.shape==(640,1,28,28)
print('无标签 fit 输入：',len(train),'张；保留：',len(heldout),'张。没有导入 torch、加载 CNN 或读取类别标签。')

```