Skip to main content

lung-cancer-astra-weights

3D CT image backbone weights (Inflated 3D ResNet-152) used by lung-cancer-astra.

PyPI limits a single file to 100 MB and each weight file is 225 MiB, so every weight is published as three shard packages. This package depends on them and joins the shards on first use, verifying the SHA-256 of the result.

Both backbones are optional extras, so you only download what you need:

pip install "lung-cancer-astra-weights[merlin]"         # merlin backbone (3 shards)
pip install "lung-cancer-astra-weights[astra]"          # astra backbone (3 shards)
pip install "lung-cancer-astra-weights[merlin,astra]"   # both
import lung_cancer_astra_weights as w
w.path("merlin")   # -> path of the joined weight file (cached)
w.verify("astra")

The joined files are written to $LCA_WEIGHTS_DIR or ~/.cache/lung_cancer_astra.

Weight Size Source License
merlin 235 MB stanfordmimi/Merlin MIT (Stanford MIMI Lab)
astra 235 MB zzzwzh/Astra_CTRG MIT

Both files hold the image backbone only (930 tensors, 117.5 M parameters, bfloat16); the text encoder, the perceiver and the language model are not included.

Metadata

Release files for lung-cancer-astra-weights 0.1.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for lung-cancer-astra-weights 0.1.1
File Size Uploaded Provenance Actions
lung_cancer_astra_weights-0.1.1.tar.gz 3.1 kB Without provenance Details for lung_cancer_astra_weights-0.1.1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for lung-cancer-astra-weights 0.1.1
File Interpreter ABI Platform Actions
lung_cancer_astra_weights-0.1.1-py3-none-any.whl Python 3 none any Details for lung_cancer_astra_weights-0.1.1-py3-none-any.whl

Total release size: 6.6 kB

Release files / lung_cancer_astra_weights-0.1.1.tar.gz

Download URL lung_cancer_astra_weights-0.1.1.tar.gz
Size 3.1 kB
Tags Source
SHA-256 checksum
How to use checksums
a008040d98b21d5853c52f425210d7019cccea3b6ce4a461fb5b60569ef07162
BLAKE2b-256 checksum
How to use checksums
5d48a04486bebd7e4119873dddb31023606cfd894a83f933b80373a92bf537ce
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.10.11

Release files / lung_cancer_astra_weights-0.1.1-py3-none-any.whl

Download URL lung_cancer_astra_weights-0.1.1-py3-none-any.whl
Size 3.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
a77dbe6a5e100a646ba4f292cfb3e7feb0c425c86b3c9750f8920857cca9f04e
BLAKE2b-256 checksum
How to use checksums
c658080791376c473bd843a1bc77b6796599f248aceb77abc1709060e0e92595
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.10.11

Security for lung-cancer-astra-weights 0.1.1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

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