{ "_id": "6aebde1f2e87f76f20ad2ca6", "Package": "rplatypus", "Type": "Package", "Title": "Computer Vision for Medical Imaging", "Version": "0.2.1", "Authors@R": "person(\"Michal\", \"Maj\", email = \"michalmaj116@gmail.com\",\nrole = c(\"aut\", \"cre\"))", "Description": "Semantic segmentation and object detection for medical\nimages, from a folder of pictures to a trained model and a\nfigure, in a handful of lines or one configuration file.\nArchitectures, losses and training run on 'PyTorch' through\n'pyplatypus', a 'Python' package which is installed and\nisolated automatically; nothing has to be set up by hand. R\nkeeps the parts that make an analysis fast - reading and\ncombining masks, drawing boxes, plotting, comparing models.", "License": "MIT + file LICENSE", "URL": "https://github.com/maju116/rplatypus,\nhttps://maju116.github.io/rplatypus/", "BugReports": "https://github.com/maju116/rplatypus/issues", "SystemRequirements": "Python (>= 3.10). Not a prerequisite the user\ninstalls: the package declares what it needs through\n'reticulate' and 'uv' provisions an isolated environment on\nfirst use, leaving any system Python untouched.", "Encoding": "UTF-8", "Config/testthat/edition": "3", "VignetteBuilder": "knitr", "Config/roxygen2/version": "8.1.0", "NeedsCompilation": "no", "Packaged": { "Date": "2026-11-05 01:34:34 UTC", "User": "root" }, "Author": "Michal Maj [aut, cre]", "Maintainer": "Michal Maj ", "Config/pak/sysreqs": "python3", "Repository": "https://cran.r-universe.dev", "Date/Publication": "2026-11-04 22:00:02 UTC", "RemoteUrl": "https://github.com/cran/rplatypus", "RemoteRef": "HEAD", "RemoteSha": "3bd95253d551ac3f849d3f4fba10126a719aca0f", "_user": "cran", "_type": "src", "_file": "rplatypus_0.2.1.tar.gz", "_fileid": "https://r2.ropensci.org/779d9d7e131ca47880ab79140ac5d2224196dcd0d15f2ff35e2ac3c8861d49e6", "_filesize": 3760029, "_sha256": "779d9d7e131ca47880ab79140ac5d2224196dcd0d15f2ff35e2ac3c8861d49e6", "_expires": "2027-02-13T01:38:37.000Z", "_created": "2026-11-05T01:34:34.000Z", "_published": "2026-11-05T01:38:39.443Z", "_upstream": "https://github.com/cran/rplatypus", "_status": "success", "_maintainer": { "name": "Michal Maj", "email": "michalmaj116@gmail.com", "login": "maju116", "twitter": "@MichalMaj116", "description": "I’m a data scientist with over 10 years of experience in the field, R/Shiny developer and a freelancer interested in deep/machine learning and statistics.", "uuid": 11685462 }, "_jobs": [ { "job": 126989781628, "time": 175, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "13379962702" }, { "job": 126989781651, "time": 195, "config": "linux-release-x86_64", "r": "4.6.2", "check": "OK", "artifact": "13380666063" }, { "job": 126988493438, "time": 211, "config": "source", "r": "4.6.2", "check": "OK", "artifact": "13380530971" }, { "job": 126989781682, "time": 114, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "13380780640" }, { "job": 126989781766, "time": 86, "config": "windows-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "13380117343" }, { "job": 126989781789, "time": 113, "config": "windows-release-x86_64", "r": "4.6.2", "check": "OK", "artifact": "13380561053" } ], "_buildurl": "https://github.com/r-universe/cran/actions/runs/41949056778", "_commit": { "id": "3bd95253d551ac3f849d3f4fba10126a719aca0f", "author": "Michal Maj ", "committer": "cran-robot ", "message": "version 0.2.1\n", "time": 1793829602 }, "_distro": "resolute", "_host": "GitHub-Actions", "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 4.1", "role": "Depends" }, { "package": "ggplot2", "role": "Imports" }, { "package": "grDevices", "role": "Imports" }, { "package": "parallel", "role": "Imports" }, { "package": "rlang", "role": "Imports" }, { "package": "reticulate", "version": ">= 1.41", "role": "Imports" }, { "package": "tools", "role": "Imports" }, { "package": "utils", "role": "Imports" }, { "package": "callr", "role": "Suggests" }, { "package": "jsonlite", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "pkgload", "role": "Suggests" }, { "package": "png", "role": "Suggests" }, { "package": "RNifti", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" }, { "package": "withr", "role": "Suggests" }, { "package": "yaml", "role": "Suggests" } ], "_owner": "cran", "_selfowned": false, "_usedby": 0, "_updates": [ { "week": "2026-45", "n": 1 } ], "_tags": [ { "name": "0.2.1", "date": "2026-11-04" } ], "_stars": 0, "_contributors": [ { "user": "maju116", "count": 1, "uuid": 11685462 } ], "_userbio": { "uuid": 6899542, "type": "organization", "name": "cran", "followers": 635, "description": "Unofficial read-only mirror of all CRAN R packages" }, "_downloads": { "count": 0, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/rplatypus" }, "_devurl": "https://github.com/maju116/rplatypus", "_pkgdown": "https://maju116.github.io/rplatypus/", "_searchresults": 18, "_rbuild": "4.6.2", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/manual.pdf", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "extra/rplatypus.html", "LICENSE" ], "_cranurl": false, "_exports": [ "augmentation_step", "available_callbacks", "available_losses", "available_metrics", "available_models", "available_optimizers", "available_tasks", "available_transforms", "available_weights", "binary_colormap", "binary_labels", "callback_cosine_annealing", "callback_csv_logger", "callback_early_stopping", "callback_model_checkpoint", "callback_reduce_lr_on_plateau", "callback_swa", "callback_terminate_on_nan", "classes_to_colours", "colours_to_classes", "ct_windows", "decode_connected_components", "decode_follow_flows", "decode_nearest_seed", "decode_watershed", "detection_anchors", "detection_crops", "detection_data", "drawing_style", "evaluate", "evaluate_cases", "evaluate_classes", "evaluate_images", "export_weights", "inspect_masks", "instance_data", "linknet", "loss_boundary", "loss_cce", "loss_cce_dice", "loss_combo", "loss_dice", "loss_focal", "loss_focal_tversky", "loss_iou", "loss_l1", "loss_lovasz", "loss_mse", "loss_smooth_l1", "loss_tversky", "mask_coverage", "mask_volume", "metric_cldice", "metric_dice", "metric_iou", "metric_tversky", "optimizer_adadelta", "optimizer_adagrad", "optimizer_adam", "optimizer_adamax", "optimizer_adamw", "optimizer_nadam", "optimizer_rmsprop", "optimizer_sgd", "overlay_agreement", "overlay_mask", "platypus_device", "platypus_fit", "platypus_spec", "platypus_status", "platypus_use_torch", "plot_anchors", "plot_boxes", "plot_masks", "read_images", "read_masks", "read_record", "res_u_net", "save_masks", "save_spec", "save_volumes", "segmentation_data", "separation_flows", "separation_rim", "series_report", "split_dataset", "split_path", "training_history", "u_net", "u_net_plus_plus", "unite_masks", "voc_colormap", "voc_labels", "volume_info", "yolo3" ], "_help": [ { "page": "as.list.platypus_spec", "title": "Turn a specification back into plain R data", "topics": [ "as.list.platypus_spec" ] }, { "page": "augmentation_step", "title": "An augmentation step", "topics": [ "augmentation_step" ] }, { "page": "available_components", "title": "What this package can do, asked of the package", "topics": [ "available_callbacks", "available_components", "available_losses", "available_metrics", "available_models", "available_optimizers", "available_tasks" ] }, { "page": "available_transforms", "title": "Which augmentations are available", "topics": [ "available_transforms" ] }, { "page": "available_weights", "title": "The published weights, and what they are", "topics": [ "available_weights" ] }, { "page": "callback_swa", "title": "Average the weights over the last part of the run", "topics": [ "callback_swa" ] }, { "page": "callbacks", "title": "Callbacks", "topics": [ "callbacks", "callback_cosine_annealing", "callback_csv_logger", "callback_early_stopping", "callback_model_checkpoint", "callback_reduce_lr_on_plateau", "callback_terminate_on_nan" ] }, { "page": "classes_to_colours", "title": "Paint a mask with its colormap", "topics": [ "classes_to_colours" ] }, { "page": "colormaps", "title": "Colormaps and their labels", "topics": [ "binary_colormap", "binary_labels", "colormaps", "voc_colormap", "voc_labels" ] }, { "page": "colours_to_classes", "title": "Read a colour mask back to class indices", "topics": [ "colours_to_classes" ] }, { "page": "ct_windows", "title": "The named CT windows", "topics": [ "ct_windows" ] }, { "page": "decodings", "title": "How predicted channels become objects", "topics": [ "decode_connected_components", "decode_follow_flows", "decode_nearest_seed", "decode_watershed", "decodings" ] }, { "page": "detection_anchors", "title": "The anchors a detector used, and whether they were fitted", "topics": [ "detection_anchors" ] }, { "page": "detection_crops", "title": "Cut every detection out of the image it was found in", "topics": [ "detection_crops" ] }, { "page": "detection_data", "title": "Where the images and their annotation files are", "topics": [ "detection_data" ] }, { "page": "drawing_style", "title": "The decisions a drawing makes", "topics": [ "drawing_style" ] }, { "page": "encoders", "title": "Pretrained encoders, and what they are worth", "topics": [ "encoders" ] }, { "page": "evaluate", "title": "Compare the trained models", "topics": [ "evaluate", "evaluate.platypus_fit" ] }, { "page": "evaluate_cases", "title": "Score every case separately", "topics": [ "evaluate_cases", "evaluate_cases.platypus_fit", "summary.platypus_cases" ] }, { "page": "evaluate_classes", "title": "Average precision per class", "topics": [ "evaluate_classes", "evaluate_classes.platypus_fit" ] }, { "page": "evaluate_images", "title": "Score every image separately", "topics": [ "evaluate_images", "evaluate_images.platypus_fit" ] }, { "page": "export_weights", "title": "Save a trained model's weights", "topics": [ "export_weights" ] }, { "page": "inspect_masks", "title": "What the colormap or labels match in your masks", "topics": [ "inspect_masks" ] }, { "page": "instance_data", "title": "Data for instance segmentation: tell the objects apart, not just find them", "topics": [ "instance_data" ] }, { "page": "loss_boundary", "title": "A loss that knows how far a wrong voxel is from the truth", "topics": [ "loss_boundary" ] }, { "page": "losses", "title": "Loss functions", "topics": [ "losses", "loss_cce", "loss_cce_dice", "loss_combo", "loss_dice", "loss_focal", "loss_focal_tversky", "loss_iou", "loss_l1", "loss_lovasz", "loss_mse", "loss_smooth_l1", "loss_tversky" ] }, { "page": "mask_coverage", "title": "How much of each class a mask covers", "topics": [ "mask_coverage" ] }, { "page": "mask_volume", "title": "How much of a volume a class occupies, in millilitres", "topics": [ "mask_volume" ] }, { "page": "metrics", "title": "Metrics", "topics": [ "metrics", "metric_cldice", "metric_dice", "metric_iou", "metric_tversky" ] }, { "page": "models", "title": "Segmentation models", "topics": [ "linknet", "models", "res_u_net", "u_net", "u_net_plus_plus" ] }, { "page": "optimizers", "title": "Optimisers", "topics": [ "optimizers", "optimizer_adadelta", "optimizer_adagrad", "optimizer_adam", "optimizer_adamax", "optimizer_adamw", "optimizer_nadam", "optimizer_rmsprop", "optimizer_sgd" ] }, { "page": "overlay_agreement", "title": "Where a prediction and the truth disagree", "topics": [ "overlay_agreement" ] }, { "page": "overlay_mask", "title": "Lay a mask over the image it belongs to", "topics": [ "overlay_mask" ] }, { "page": "platypus_conditions", "title": "When something is wrong: the conditions this package raises", "topics": [ "platypus_conditions" ] }, { "page": "platypus_device", "title": "Where the work will happen", "topics": [ "platypus_device" ] }, { "page": "platypus_fit", "title": "Train the models in a specification", "topics": [ "platypus_fit" ] }, { "page": "platypus_spec", "title": "Build an experiment specification", "topics": [ "platypus_spec" ] }, { "page": "platypus_status", "title": "Is the engine ready?", "topics": [ "platypus_status" ] }, { "page": "platypus_use_torch", "title": "Ask for a particular PyTorch build", "topics": [ "platypus_use_torch" ] }, { "page": "plot_anchors", "title": "Draw the anchors against the boxes they were fitted to", "topics": [ "plot_anchors" ] }, { "page": "plot_boxes", "title": "Draw boxes on images", "topics": [ "plot_boxes" ] }, { "page": "plot_masks", "title": "Look at masks beside the images they came from", "topics": [ "plot_masks" ] }, { "page": "plot.platypus_fit", "title": "Plot what happened during training", "topics": [ "plot.platypus_fit" ] }, { "page": "predict.platypus_fit", "title": "Predict masks", "topics": [ "predict.platypus_fit" ] }, { "page": "read_images", "title": "Read images as the model sees them", "topics": [ "read_images" ] }, { "page": "read_masks", "title": "Read mask files as class indices", "topics": [ "read_masks" ] }, { "page": "read_record", "title": "Read what a run wrote down about itself", "topics": [ "read_record" ] }, { "page": "save_masks", "title": "Write masks to files", "topics": [ "save_masks" ] }, { "page": "save_spec", "title": "Write a specification back out as YAML", "topics": [ "save_spec" ] }, { "page": "save_volumes", "title": "Save predicted volumes as NIfTI", "topics": [ "save_volumes" ] }, { "page": "segmentation_data", "title": "Where the images and masks are", "topics": [ "segmentation_data" ] }, { "page": "separations", "title": "What the network predicts, so objects can be told apart", "topics": [ "separations", "separation_flows", "separation_rim" ] }, { "page": "series_report", "title": "Check folders of DICOM slices before training on them", "topics": [ "series_report" ] }, { "page": "split_dataset", "title": "Split a dataset into training, validation and test sets", "topics": [ "split_dataset" ] }, { "page": "split_path", "title": "The files in one part of a split", "topics": [ "split_path" ] }, { "page": "training_history", "title": "The epoch-by-epoch record", "topics": [ "training_history" ] }, { "page": "unite_masks", "title": "Combine several binary masks into one", "topics": [ "unite_masks" ] }, { "page": "volume_info", "title": "What is in a volume file", "topics": [ "volume_info" ] }, { "page": "yolo3", "title": "YOLOv3", "topics": [ "yolo3" ] } ], "_readme": "https://github.com/cran/rplatypus/raw/HEAD/README.md", "_rundeps": [ "cli", "cpp11", "farver", "ggplot2", "glue", "gtable", "here", "isoband", "jsonlite", "labeling", "lattice", "lifecycle", "Matrix", "png", "R6", "rappdirs", "RColorBrewer", "Rcpp", "RcppTOML", "reticulate", "rlang", "rprojroot", "S7", "scales", "vctrs", "viridisLite", "withr" ], "_vignettes": [ { "source": "blood-cells.Rmd", "filename": "blood-cells.html", "title": "Finding blood cells with YOLOv3", "engine": "knitr::rmarkdown", "headings": [ "Before any of that: boxes in a few lines", "And here, unlike the nuclei vignette, a score means something", "One refusal worth meeting now", "Anchors, which a detector has and a U-Net does not", "What the loss is doing", "Scoring, and the number that is missing on purpose", "mAP@0.5, mAP@[.50:.95], and which to believe", "Looking at it", "What this does not do", "Notes on the machine" ], "created": "2026-11-04 22:00:02", "modified": "2026-11-04 22:00:02", "commits": 1 }, { "source": "data-science-bowl.Rmd", "filename": "data-science-bowl.html", "title": "Finding nuclei in the 2018 Data Science Bowl", "engine": "knitr::rmarkdown", "headings": [ "Before any of that: a mask in four lines", "The data", "Look at it before training on it", "The specification", "Train", "Compare", "Look at what it did", "The same thing from a file", "A note on older graphics cards" ], "created": "2026-11-04 22:00:02", "modified": "2026-11-04 22:00:02", "commits": 1 }, { "source": "retinal-vessels.Rmd", "filename": "retinal-vessels.html", "title": "Retinal vessels: tiling, and a metric Dice cannot replace", "engine": "knitr::rmarkdown", "headings": [ "Why a vessel cannot be resized", "The data", "The configuration", "Training", "One number hides the finding", "clDice beside Dice", "The worst case, drawn", "Notes" ], "created": "2026-11-04 22:00:02", "modified": "2026-11-04 22:00:02", "commits": 1 }, { "source": "volumes.Rmd", "filename": "volumes.html", "title": "Segmenting volumes: CT, spacing and per-patient scores", "engine": "knitr::rmarkdown", "headings": [ "Making something to segment", "Splitting by patient, not by scan", "The specification", "Training", "Scores per patient, not per dataset", "Looking at a slice", "Millilitres, not voxels", "Writing a mask back onto its scan", "DICOM, which is how the data usually arrives", "What this leaves out" ], "created": "2026-11-04 22:00:02", "modified": "2026-11-04 22:00:02", "commits": 1 }, { "source": "configuration.Rmd", "filename": "configuration.html", "title": "Writing a configuration", "engine": "knitr::rmarkdown", "headings": [ "One file, one run", "Several models at once", "Dividing one folder", "Augmentation, callbacks, and the rest of a model", "Instances instead of one mask", "Detection instead of segmentation", "Not training at all", "What is checked, and when", "The same run from code" ], "created": "2026-11-04 22:00:02", "modified": "2026-11-04 22:00:02", "commits": 1 } ], "_score": 3.6532125137753435, "_indexed": false, "_nocasepkg": "rplatypus", "_universes": [ "cran", "maju116" ], "_indexurl": "https://maju116.r-universe.dev/rplatypus", "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.2.1", "date": "2026-11-05T01:37:16.000Z", "distro": "resolute", "commit": "3bd95253d551ac3f849d3f4fba10126a719aca0f", "fileid": "https://r2.ropensci.org/af219f71c5aefbee3808f185ccae1cad96e2b6104a6c8909e825308e9eaf42fb", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cran/actions/runs/41949056778" }, { "r": "4.6.2", "os": "linux", "version": "0.2.1", "date": "2026-11-05T01:37:26.000Z", "distro": "resolute", "commit": "3bd95253d551ac3f849d3f4fba10126a719aca0f", "fileid": "https://r2.ropensci.org/f9ec896bc5fe1ebff176b50096c4167c23beb9b510d7bcb13e30c9dc61c58820", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cran/actions/runs/41949056778" }, { "r": "4.6.0", "os": "wasm", "version": "0.2.1", "date": "2026-11-05T01:36:51.000Z", "commit": "3bd95253d551ac3f849d3f4fba10126a719aca0f", "fileid": "https://r2.ropensci.org/834482b2918518ba299ba6f4609af26bb78c33e048a9a71bb6ff5f5634bef3a9", "status": "success", "buildurl": "https://github.com/r-universe/cran/actions/runs/41949056778" }, { "r": "4.7.0", "os": "win", "version": "0.2.1", "date": "2026-11-05T01:35:41.000Z", "commit": "3bd95253d551ac3f849d3f4fba10126a719aca0f", "fileid": "https://r2.ropensci.org/f1acc2684899405ef869e428b21f33461c38c4ec5872da812e52f966a5c78bb9", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cran/actions/runs/41949056778" }, { "r": "4.6.2", "os": "win", "version": "0.2.1", "date": "2026-11-05T01:35:57.000Z", "commit": "3bd95253d551ac3f849d3f4fba10126a719aca0f", "fileid": "https://r2.ropensci.org/e41c2a68783aa4b2fe910029a5b0f155742dafec06edbe2d5bc1913ba97b927e", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/cran/actions/runs/41949056778" } ] }