Skip to content
Snippets Groups Projects

Repository graph

You can move around the graph by using the arrow keys.
Select Git revision
  • aifmd_dataset_support
  • main default protected
  • robertos-branch
  • v1.3.1
  • v1.3.0
  • v1.2.0
  • v1.1.0
  • v1.0.2
  • v1.0.1
  • v1.0.0
  • v1.0.0b0
  • v1.0.0a0
12 results
Created with Raphaël 2.2.019Jan1722Dec141319Sep518Aug17161514865432131Jul3028272622Jun22May16151211109818Apr17161514121164322Mar2119181716872128Feb2322161330Jan292726252423changed sample namingadapted saliency map generation and road calculation to lightning modelsadded changes from gradcam branch to add-datamoduleMerge branch 'add-datamodule' into 'main'[data/augmentations] Use the 'spawn' multiprocessing start method on all platforms[data.datamodule] Fix incomplete teardown of DataModule[scripts.predict] Fix call to 'load_from_checkpoint()'Revert "[data.datamodule] Experiment with fork/spawn setup"[data.datamodule] Experiment with fork/spawn setup[qa] Updated pre-commit hooks[data.datamodule] Fix warning and object setup[tbx11k] Loads RS bounding-boxes with sample; Add tests for bounding-boxesfixed pipeline from Commit 0a0e9529[test/test_cli] updated unit tests for training, prediction and evaluation cli scripts. Removed radiological signs (rs) related tests[tests] Remove tests for ptbench compare for now[scripts.train_analysis] Simplify and remove pandas requirements[readme,doc,pyproject,scripts] Remove traces of "tuberculosis" exclusivity[scripts] Remove outdated scripts[data.datamodule] Only reset datasets if model_transforms change[scripts.experiment] Make it run completely[scripts.experiment] Resync with changes to other scripts[scripts] Remove outdated aggregpred and predtojson scripts and associated tests[tests] Fix testing[scripts.experiment] Reflect changes from evaluation; closes #44 after noticing train-analysis is performed[doc] Documentation fixes[scripts.evaluate] Complete refactor[engine.predictor] Streamline typing around prediction[engine.predictor] Do not announce tensorboard - it is useless in this stage[scripts.predict] Reset default batch-size to 1[doc] Documentation fixes[script.evaluate] Improve exception message[engine.loggers] Avoid submodule with single module inside[engine.predictor] Allow prediction to work when batch-size!=0; Discard CSVs and use JSON for output; Implement lightning logging like in training; Separates batched (collated) data at prediction; Adapts all models to new paradigm; Remove CSVPredictionsWriter; Adapt predict script to all changes[engine.trainer] Log at every epoch (closes #28)[scripts] Bump to Python >= 3.10[cli] Refactor config and database (old datamodule) commands[manifest] Ship json from new location[config.data] Add module initialiserRe-shuffle datamodules to the "config" base directory, adjust tests and documentation[doc] Remove traces of signs-to-tb "model"