Perplexity for LLM EvaluationHow to use perplexity to evaluation LLMs’ confidence in next-token prediction.Jun 13Jun 13
Published inGenerative AIImage Inpainting for SDXL 1.0 Base Model + RefinerAnd how to log our results in an experiment tracking toolAug 21, 2023A response icon3Aug 21, 2023A response icon3
Published inGenerative AIExplainable AI: Visualizing Attention in TransformersAnd logging the results in an experiment tracking toolJul 17, 2023A response icon10Jul 17, 2023A response icon10
Published inArtificial Intelligence in Plain EnglishSAM + Stable Diffusion for Text-to-Image InpaintingCreate a pipeline with GroundingDINO, Segment Anything, and Stable Diffusion and track the results in CometJun 27, 2023A response icon5Jun 27, 2023A response icon5
Published inDataDrivenInvestorDebugging Image Classifiers With Confusion MatricesHow to intuitively explore model predictions on specific images over timeMay 17, 2023A response icon1May 17, 2023A response icon1
Published inTowards AICompare and Evaluate Object Detection Models From TorchVisionVisualizing the performance of Fast RCNN, Faster RCNN, Mask RCNN, RetinaNet, and FCOSMay 8, 2023A response icon1May 8, 2023A response icon1
Published inDataDrivenInvestorPowering Anomaly Detection for Industry 4.0Build, track, and organize production-grade anomaly detection modelsFeb 21, 2023A response icon1Feb 21, 2023A response icon1
Published inBetter ProgrammingCredit Card Fraud Detection With AutoencodersAnd how to intuitively debug your results with CometFeb 16, 2023A response icon2Feb 16, 2023A response icon2
Published inTowards AIN-dimensional DICOM Volumes With ImageIOVisualizing, augmenting, and interacting with high-dimensional DICOM volumes in PythonFeb 2, 2023A response icon2Feb 2, 2023A response icon2