byzh-ai

更方便的深度学习。

pip install byzh-ai → 导入名 byzh_ai

模块一览

所有子包以 B 开头，类以 B_ 开头，函数以 b_ 开头。

模块 说明
Bdata 主流数据集一键下载/缓存/标准化（MNIST、CIFAR、FashionMNIST、Tiny ImageNet 等），支持 TensorDataset / DataLoader 构建与分层采样
Bdemo MNIST 完整训练演示、训练器功能测试（单卡/多卡）、分类评估测试
Bearly_stop 多种早停策略（精度停滞、精度增量不足、损失停滞、过拟合检测）及模型参数自动回滚重载
Blr_schedulers 自定义学习率调度器：Warmup 线性升温、阶梯衰减、Warmup + 衰减组合
Bmodel 即用型深度学习模型：SimpleCNN、LeNet-5、ResNet-18、RNN、LSTM、Transformer、脉冲神经网络（Spike RNN/LSTM/ResNet-18）等
Btrainer 通用训练器，封装训练/验证/测试循环，集成早停/重载、学习率调度、checkpoint、多 GPU（DataParallel / DDP）、SNN 支持、日志记录、损失/精度绘图
Butils 深度学习工具：自动设备选择（NPU/GPU/CPU）、GPU 监控与空闲检测、模型参数量/FLOPs 统计、随机种子统一设置、数据集均值/标准差计算、超参数网格搜索、递增运行目录管理
Bvisual 训练损失/精度曲线绘制、混淆矩阵热力图绘制

依赖

  • byzh-core>=0.0.10.0 — 进度条、日志写入器、彩色终端输出、文件/目录操作等基础工具
  • torch、torchvision — 深度学习框架
  • numpy、pandas、matplotlib、seaborn — 数据处理与可视化
  • scikit-learn — 数据划分、指标计算
  • thop — FLOPs 计算（需自行安装）
  • spikingjelly — 脉冲神经网络（可选）
  • PyYAML — YAML 配置解析
  • Pillow — 图像处理

License

MIT

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Newer release available (0.0.10.16)

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for byzh_rc from gravatar.com byzh_rc

Credits

Author: byzh_rc

License

MIT

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

byzh_ai-0.0.10.15.tar.gz (118.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

byzh_ai-0.0.10.15-py3-none-any.whl (202.1 kB view details)

Uploaded Python 3

File details

Details for the file byzh_ai-0.0.10.15.tar.gz.

File metadata

  • Download URL: byzh_ai-0.0.10.15.tar.gz
  • Upload date:
  • Size: 118.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.5

File hashes

Hashes for byzh_ai-0.0.10.15.tar.gz
Algorithm Hash digest
SHA256 e09cd2c8bd4e3d1ffbcdf92fa1be81e93eb3f25b24909ade54cb9a494cd44e4a
MD5 288b4e7fdb4192402b857615b0b87926
BLAKE2b-256 46777a746472e81f01acd6e28874c699541c4f5d40c7f2c1fbc8b2fd4529ce37

See more details on using hashes here.

File details

Details for the file byzh_ai-0.0.10.15-py3-none-any.whl.

File metadata

  • Download URL: byzh_ai-0.0.10.15-py3-none-any.whl
  • Upload date:
  • Size: 202.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.5

File hashes

Hashes for byzh_ai-0.0.10.15-py3-none-any.whl
Algorithm Hash digest
SHA256 d4af8dbb3102a2b103051ae7cafc4af0da9db4a3daeb94ea71856079fc83a12d
MD5 b697d1d1a1973a94d20474f38a25c205
BLAKE2b-256 4a7945636704dac5af9aa5e08915e30b161f76c68d6aee5bdb067548c879e05d

See more details on using hashes here.

Release history Release notifications | RSS feed

0.0.10.16

2 files

This release

0.0.10.15 This release

2 files

0.0.10.14

2 files

0.0.10.13

2 files

0.0.10.12

2 files

0.0.10.11

2 files

0.0.10.10

2 files

0.0.10.9

2 files

0.0.10.8

2 files

0.0.10.7

2 files

0.0.10.6

2 files

0.0.10.5

2 files

0.0.10.4

2 files

0.0.10.3

2 files

0.0.10.2

2 files

0.0.10.1

2 files

0.0.10.0

2 files

0.0.9.71

2 files

0.0.9.70

2 files

0.0.9.69

2 files

0.0.9.68

2 files

0.0.9.67

2 files

0.0.9.66

2 files

0.0.9.65

2 files

0.0.9.64

2 files

0.0.9.63

2 files

0.0.9.62

2 files

0.0.9.61

2 files

0.0.9.60

2 files

0.0.9.59

2 files

0.0.9.58

2 files

0.0.9.57

2 files

0.0.9.56

2 files

0.0.9.55

2 files

0.0.9.54

2 files

0.0.9.53

2 files

0.0.9.52

2 files

0.0.9.51

2 files

0.0.9.50

2 files

0.0.9.49

2 files

0.0.9.48

2 files

0.0.9.47

2 files

0.0.9.46

2 files

0.0.9.45

2 files

0.0.9.44

2 files

0.0.9.43

2 files

0.0.9.42

2 files

0.0.9.41

2 files

0.0.9.40

2 files

0.0.9.39

2 files

0.0.9.38

2 files

0.0.9.37

2 files

0.0.9.36

2 files

0.0.9.35

2 files

0.0.9.34

2 files

0.0.9.33

2 files

0.0.9.32

2 files

0.0.9.31

2 files

0.0.9.30

2 files

0.0.9.29

2 files

0.0.9.28

2 files

0.0.9.27

2 files

0.0.9.26

2 files

0.0.9.25

2 files

0.0.9.24

2 files

0.0.9.23

2 files

0.0.9.22

2 files

0.0.9.21

2 files

0.0.9.20

2 files

0.0.9.19

2 files

0.0.9.18

2 files

0.0.9.17

2 files

0.0.9.16

2 files

0.0.9.15

2 files

0.0.9.14

2 files

0.0.9.13

2 files

0.0.9.12

2 files

0.0.9.11

2 files

0.0.9.10

2 files

0.0.9.9

2 files

0.0.9.8

2 files

0.0.9.7

2 files

0.0.9.6

2 files

0.0.9.5

2 files

0.0.9.4

2 files

0.0.9.3

2 files

0.0.9.2

2 files

0.0.9.1

2 files

0.0.9.0

2 files

0.0.8.0

2 files

0.0.7.1

2 files

0.0.7.0

2 files

0.0.6.1

2 files

0.0.6.0

2 files

0.0.5.0

2 files

0.0.4.3

2 files

0.0.4.2

2 files

0.0.4.1

2 files

0.0.4.0

2 files

0.0.2.3

2 files

0.0.2.2

2 files

0.0.2.1

2 files

0.0.2.0

2 files

0.0.1.7

2 files

0.0.1.6

2 files

0.0.1.5

2 files

0.0.1.4

2 files

0.0.1.3

2 files

0.0.1.2

2 files

0.0.1.1

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page