# jla524/fromthetensor

From the Tensor to Stable Diffusion, a rough outline for a 10 week course.

Repository: https://github.com/jla524/fromthetensor
Canonical: https://ross.abutalabs.com/products/fromthetensor
License Family: other
Topics: deep-learning, pytorch, transformers
Last push: 2026-04-05T23:55:05+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 75, release rhythm 35, longevity 100
- inputs: {"age_days": 1606, "days_push": 150, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1084, forks 45 (observed 2026-08-28T04:03:31.519373+00:00)

## What it is
A 10-week course outline for learning deep learning from first principles by implementing papers, from tensors up to Stable Diffusion. It includes example notebooks and video links, inspired by George Hotz's 'From the Transistor' approach.

## Use cases
- learn deep learning from scratch in 10 weeks
- implement classic ML papers like AlexNet and ResNet
- understand transformers and stable diffusion from first principles
- find a structured self-study path to become an ML engineer
- practice building CNNs, RNNs, and GANs in PyTorch

## When to choose
- you want a paper-implementation-driven deep learning curriculum
- you prefer hands-on notebooks over abstract tutorials
- you want to go from tensor basics to diffusion models

## When to avoid
- you need a production library or tool rather than a course
- you want a polished, formally maintained course with support
- you are a complete beginner with no Python experience

## Facets
- artifact type: learning-resource
- maturity: active
- function: deep-learning, machine-learning
- domain: deep-learning, machine-learning, tutorials
- platform: python
- tags: course-outline, pytorch, transformers, stable-diffusion, self-study

## Member repositories
- jla524/fromthetensor (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:31.519373+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:50:02.513761+00:00, confidence not recorded.
  - readme: https://github.com/jla524/fromthetensor (fetched 2026-08-28T04:03:31.519373+00:00, sha d002366d3312)
- Data as of 2026-08-30T08:39:29.467469+00:00.