[LAB 07 · MoCo：历史 key、队列与两种更新](/course/notebooks/0d1b8f6fbf6a476c93ffcc169f2ec1f4.html)

# 运行准备与结果身份 · 实现代码
[独立阅读](/course/notebook-blocks/afef202950ec4c049f8eeff5abc1af7e.html)
按问题继续

真实FIFO键、EMA、梯度更新及低于随机基线的保留结果
展开完整实现代码
```
"""CPU image contrastive experiment. No class/color label enters pretraining."""
from pathlib import Path
import copy, hashlib, json, os, platform, time
import numpy as np
import torch
from torch import nn
from torch.nn import functional as F
from sklearn.neighbors import KNeighborsClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt

torch.set_num_threads(2)
SEED=20260922

SOURCE_SHA256='09bbb32bb5502db3535d89efec2045ffcd85c249b49f622390f12875060845d4'
print("source",SOURCE_SHA256,"torch",torch.__version__)
```