Skip to content
Aabha AI Academy
Skip to reading

Deep Learning

Reproduce the authored package

Learners do not need to rebuild the reading guide. The generated HTML and SVGs are included. Source is editable for review and later integration.

After installing the verified CPU requirements, run from the package root:

python -m unittest discover -s tests -v
python -m dlcourse.run --task all
python -m dlcourse.diagnostics
python -m tools.export_data
python -m tools.build_visuals

To regenerate the HTML reading edition, install the small optional authoring dependency and run:

python -m pip install -r requirements-authoring.txt
python -m tools.build_guide
python -m tools.check_package

WORKBOOK.md is rebuilt from lesson prompts, so edit canonical lessons first. SOLUTIONS.md remains separate. CAPSTONE_REFERENCE.md describes recorded outputs and must be updated deliberately if the reference configuration changes. Every dependency/version change requires rerunning numerical and evaluation-boundary checks; the static checker is not sufficient.

The capstone runner refuses an existing final output. For unchanged reference reproduction, use a fresh explicitly named output directory on both commands; never treat repeated use of the same test observations as new evaluation evidence.

Download this source file