New custom callbacks: ImageSegmentationResultCallback: Callback that logs the results of the training on TensorBoard and on saved files; and WarmupCallback: Applies freeze weight on encoder during callback epochs and then unfreezes the weights after the warmup epochs. Metrics added to Segmentation Model: Accuracy; Precision; Recall; and Jaccard Index (IoU)
Dataset conversion added. It is possible to convert between some formats of dataset; Tversky Loss an...
Bug fix on convert dataset; Bug fix on PolygonRNNDataset; Bug fix on PolygonRNNResultCallback when u...
New Mod PolyMapper model; Matching methods added; Evaluation methods added; What's Changed Merge p...
What's Changed Version 0.16.2 by @phborba in https://github.com/phborba/pytorch_segmentation_models...
Bug fix on loss sync; Custom models from Frame Field implementation (to compare training results); N...
What's Changed Version 0.16.2 by @phborba in https://github.com/phborba/pytorch_segmentation_models...
Custom metric option in the model config; pytorch_toolbelt added as required package. This enables u...
Vector IOU; Polis metric added; IoU added to PolygonRNN training loop; Object detection visualizatio...
What's Changed bug fix by @phborba in https://github.com/phborba/pytorch_segmentation_models_traine...
New evaluation metrics; New evaluation on test set; New inference service with image upload; Bug fix...
Polygon inference Unittests to Polygon inference; Bug fixes warmup callback (invalid signature on me...
Bug fixes on mask building; Bug fixes on detection model training. New mode on build masks
New Naive Mod PolyMapper model (Object Detection + PolygonRNN); New Naive Mod Polymapper dataset; Ne...
What's Changed Version 0.16.2 by @phborba in https://github.com/phborba/pytorch_segmentation_models...
Minor improvements and bug fixes on polygon building inference; Bug fixes on mask builder; Performan...
Dataset conversion added. It is possible to convert between some formats of dataset; Tversky Loss an...
Bug fix on convert dataset; Bug fix on PolygonRNNDataset; Bug fix on PolygonRNNResultCallback when u...
New Mod PolyMapper model; Matching methods added; Evaluation methods added; What's Changed Merge p...
What's Changed Version 0.16.2 by @phborba in https://github.com/phborba/pytorch_segmentation_models...
Bug fix on loss sync; Custom models from Frame Field implementation (to compare training results); N...
What's Changed Version 0.16.2 by @phborba in https://github.com/phborba/pytorch_segmentation_models...
Custom metric option in the model config; pytorch_toolbelt added as required package. This enables u...
Vector IOU; Polis metric added; IoU added to PolygonRNN training loop; Object detection visualizatio...
What's Changed bug fix by @phborba in https://github.com/phborba/pytorch_segmentation_models_traine...
New evaluation metrics; New evaluation on test set; New inference service with image upload; Bug fix...
Polygon inference Unittests to Polygon inference; Bug fixes warmup callback (invalid signature on me...
Bug fixes on mask building; Bug fixes on detection model training. New mode on build masks
New Naive Mod PolyMapper model (Object Detection + PolygonRNN); New Naive Mod Polymapper dataset; Ne...
What's Changed Version 0.16.2 by @phborba in https://github.com/phborba/pytorch_segmentation_models...
Minor improvements and bug fixes on polygon building inference; Bug fixes on mask builder; Performan...
Dataset conversion added. It is possible to convert between some formats of dataset; Tversky Loss an...
Bug fix on convert dataset; Bug fix on PolygonRNNDataset; Bug fix on PolygonRNNResultCallback when u...
New Mod PolyMapper model; Matching methods added; Evaluation methods added; What's Changed Merge p...