《动手学深度学习》:面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。
First read
d2l-ai/d2l-zh shows signs of reuse beyond stars, yet recent activity is softer. Read the repository as a potentially durable dependency, but verify maintenance rhythm before treating it as a default choice.
79.7K public stars in the current GitStar snapshot.
Recognizable in the ecosystem
Last commit Jul 30, 2024.
Stale activity
pypi gives the strongest production-style signal.
8M/week
One or more key signals are partial, so GitStar keeps the interpretation conservative.
Partial snapshot
Snapshot facts
Compare lens
huggingface/transformers and ultralytics/ultralytics are the closest comparison targets GitStar found. A side-by-side comparison usually tells you more than a single raw rank.
Signal trail
Read the recent motion first. This block is for deciding whether the repository still looks alive, compounding, or flattening before you trust stars alone.
Package reality
GitStar found pypi:notebook. Package traffic can help separate visible repositories from dependencies that are quietly used in real workflows.
Validation note
GitStar can summarize public signals for d2l-ai/d2l-zh, but the GitHub repository is still the primary place to confirm release cadence, issue activity, and maintainer intent.
GitStar uses the strongest linked package signal below when it reads Hype vs Reality for this repository.
GitStar surfaces public popularity and package signals. These rankings are not endorsements, security reviews, or investment advice.
Why this rank
This repository stands out because it combines package adoption and stable visibility.
Reconstructed from current stars and cached daily/weekly/monthly deltas.
Recent attention and package usage are moving in the same direction.
This usually means the project has both mindshare and a measurable production footprint, which makes it a stronger validation candidate.
Shares the learning category footprint with d2l-ai/d2l-zh, so the comparison is closer to a same-problem decision than a same-language coincidence.
Shares the learning category footprint with d2l-ai/d2l-zh, so the comparison is closer to a same-problem decision than a same-language coincidence.
Shares the learning category footprint with d2l-ai/d2l-zh, so the comparison is closer to a same-problem decision than a same-language coincidence.
Shares the learning category footprint with d2l-ai/d2l-zh, so the comparison is closer to a same-problem decision than a same-language coincidence.
GitStar picked transformers + ultralytics as the closest next comparison from the related repository set.
[](https://gitstar.space/repo/d2l-ai/d2l-zh)<a href="https://gitstar.space/repo/d2l-ai/d2l-zh"><img src="https://gitstar.space/api/badge/d2l-ai/d2l-zh" alt="GitStar"></a>🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Ultralytics YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking
We write your reusable computer vision tools. 💜
Learn it. Build it. Ship it for others.
💫 Industrial-strength Natural Language Processing (NLP) in Python
🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools
This page provides a quick overview of d2l-ai/d2l-zh based on GitStar's cached data. The signal chart reconstructs approximate checkpoints from current stars plus cached daily, weekly, and monthly star deltas, so it is best read as directional context rather than as a precise historical audit log.
Want to show your project's ranking? Copy the badge embed code above and add it to your README.