Skip to main content

descriptron-vision

Mask and landmark prediction for Descriptron: torchvision detectors, SAM2-PAL propagation and DINOv3 landmark transfer.

pip install descriptron-vision
descriptron-train --task masks --coco-json annotations.json --img-dir images/ \
                  --output-dir out/ --total-iters 20000
descriptron-predict --checkpoint out/model_final_*.pth --coco-json annotations.json \
                    --img-dir images/ --annotations_out predictions.json

No compiler required. torch and torchvision are ordinary wheels on Linux, macOS and Windows. For CUDA, install torch from PyTorch's own index first:

pip install torch torchvision --index-url https://download.pytorch.org/whl/cu121
pip install descriptron-vision

On a Mac the detectors can use the Apple GPU through PyTorch's MPS device, which is why this backend exists: Detectron2 has no macOS wheels and no Apple Silicon support.

Two optional dependencies that cannot be declared

PyPI rejects a git dependency in package metadata, so neither SAM2 nor Detectron2 is listed. Both are imported lazily, and the error names the command to install them. The Docker image carries both ready to run.

Choosing a backbone

--arch v1 (default) is maskrcnn_resnet50_fpn; --arch v2 is maskrcnn_resnet50_fpn_v2. v2 scores higher on COCO, but on a few hundred training images v1 won on 3 of 3 folds of a grouped species hold-out — its lighter two-FC box head converges further in the same budget. Measured on the data, not assumed from the model zoo.

Metadata

Release files for descriptron-vision 2.7.0

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

Source distribution (sdist)

Source distribution for descriptron-vision 2.7.0
File Size Uploaded
descriptron_vision-2.7.0.tar.gz 178.8 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for descriptron-vision 2.7.0
File Interpreter ABI Platform
descriptron_vision-2.7.0-py3-none-any.whl Python 3 none any Details

Total release size: 375.0 kB

Release files / descriptron_vision-2.7.0.tar.gz

Download URL descriptron_vision-2.7.0.tar.gz
Size 178.8 kB
Tags Source
SHA-256 checksum
How to use checksums
5e137f208368f9ab10102b368ba3ad675b982a1fc8e5d6170646cfa2a629f5f9
BLAKE2b-256 checksum
How to use checksums
1e73537a0ecccdfc20f5f12669648233abf7edaa3cd2457ca5d69b7fe153cf22
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.4

Release files / descriptron_vision-2.7.0-py3-none-any.whl

Download URL descriptron_vision-2.7.0-py3-none-any.whl
Size 196.2 kB
Tags Python 3
SHA-256 checksum
How to use checksums
952fcad762ccb27f42185f69d90079de6fddddde464723c5fe47edf93961f749
BLAKE2b-256 checksum
How to use checksums
a3f6e1a819f2c676aa5c0eba977b1c5640f36307db56dbd72ac3285a3751b786
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.4

Release history Release notifications | RSS feed

2.7.8

2 release files

2.7.6

2 release files

2.7.5

2 release files

This release

2.7.0 This release

2 release files

2.6.0

2 release files

2.5.2

2 release files

2.5.1

2 release files

2.3.0

2 release files

2.2.0

2 release files

2.1.3

2 release files

2.1.2

2 release files

2.1.1

2 release files

2.1.0

2 release files

2.0.4

2 release files

2.0.3

2 release files

2.0.2

2 release files

2.0.1

2 release 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