Package: petrographer 0.0.0.9000

Nicolas Gauthier

petrographer: Petrographic Thin Section Analysis with Deep Learning

Automated petrographic analysis of thin section images using deep learning models. Provides tools for training RF-DETR detection and segmentation models, running predictions with SAHI (Slicing Aided Hyper Inference), calculating morphological properties, and analyzing results. Supports both local and HPC training workflows with seamless R-Python integration via reticulate.

Authors:Nicolas Gauthier [aut, cre], Ashley Rutkoski [aut]

petrographer_0.0.0.9000.tar.gz
petrographer_0.0.0.9000.zip(r-4.7-any)petrographer_0.0.0.9000.zip(r-4.6-any)petrographer_0.0.0.9000.zip(r-4.5-any)
petrographer_0.0.0.9000.tgz(r-4.6-any)petrographer_0.0.0.9000.tgz(r-4.5-any)
petrographer_0.0.0.9000.tar.gz(r-4.7-any)petrographer_0.0.0.9000.tar.gz(r-4.6-any)
petrographer_0.0.0.9000.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
petrographer/json (API)

# Install 'petrographer' in R:
install.packages('petrographer', repos = c('https://flmnh-ai.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/flmnh-ai/petrographer/issues

Pkgdown/docs site:https://flmnh-ai.github.io

On CRAN:

Conda:

quarto

4.59 score 5 stars 13 scripts 25 exports 53 dependencies

Last updated from:cdaf571196. Checks:7 ERROR, 2 OK. Indexed: yes.

TargetResultTimeFilesSyslog
linux-develERROR179
source / vignettesOK198
linux-releaseERROR176
macos-releaseERROR186
macos-oldrelERROR163
windows-develERROR227
windows-releaseERROR218
windows-oldrelERROR238
wasm-releaseOK128

Exports:align_imagesanalyze_segmentation_dirclean_temp_datasetsconfusion_matrixevaluate_model_sahievaluate_trainingfrom_pretrainedget_dataset_pathget_population_statsget_training_datasetlist_datasetslist_modelslist_trained_modelsmodel_infopg_plot_annotationspg_plot_dataset_imagepg_save_dataset_previewpin_datasetpin_modelpredict_imagepredict_imagesslice_datasetsummarize_by_imagetrain_modelvalidate_dataset

Dependencies:askpassbitbit64clicliprcpp11crayoncurldigestdplyrfsgenericsglueherehmshttrjsonlitelatticelifecyclemagrittrMatrixmimeopensslpillarpinspkgconfigpngprettyunitsprocessxprogresspspurrrR6rappdirsRcppRcppTOMLreadrreticulaterlangrprojrootstringistringrsystibbletidyrtidyselecttzdbutf8vctrsvroomwhiskerwithryaml

Analyzing Predictions
Load the Toolkit | Load a Model | Detection Workflow | Predict a Single Image | Review the Output Columns | Summarize a Single Image | Batch Process a Directory | Summarize Across Images | Plot Detection-Level Distributions | Segmentation Workflow | Inspect Morphology Columns | Single-Image Morphology Summary | Plot Morphology | Batch Segmentation Analysis | Summaries from Batch Segmentation | Choosing an Analysis Path | Next Steps
Rendered fromanalyzing-predictions.qmdusingquarto::html

Last update: 2026-04-21
Started: 2026-04-21

Training Custom Models
Choose a Training Task | Prepare the Dataset | Optional: Slice Large Images | Optional: Pin the Dataset | Start Training | Detection Example | Segmentation Example | Local vs HPC Training | Local Training | HPC Training | Choose a Model Variant | What Training Produces | Evaluate and Inspect the Result | Detection Validation | Segmentation Validation | Maintainership and Publishing | Troubleshooting
Rendered fromtraining-models.qmdusingquarto::html

Last update: 2026-04-21
Started: 2025-10-14

Whole-Slide Prediction Basics
Load the Toolkit | Point to a Large Image | Load a Pretrained Model | Run SAHI Inference | Review the Overlay | Summarize Detections | Batch Process a Directory | Next Steps
Rendered fromwhole-slide-basics.qmdusingquarto::html

Last update: 2026-04-21
Started: 2025-10-14