# Jaccard index for image binary segmentation evaluation in dl4j

**URL:** <https://community.konduit.ai/t/jaccard-index-for-image-binary-segmentation-evaluation-in-dl4j/1624>\
**Category:** Uncategorized\
**Created:** [September 28, 2021, 8:38am UTC](https://community.konduit.ai/t/jaccard-index-for-image-binary-segmentation-evaluation-in-dl4j/1624 "2021-09-28T08:38:51Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![AbdelmajidB](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/abdelmajidb/32/56_2.png) [@AbdelmajidB](https://community.konduit.ai/u/AbdelmajidB)\
**Post date:** [September 28, 2021, 8:38am UTC](https://community.konduit.ai/t/jaccard-index-for-image-binary-segmentation-evaluation-in-dl4j/1624/1 "2021-09-28T08:38:51Z")

</div>

Please i want to use jaccard index ([Metrics to Evaluate your Semantic Segmentation Model | by Ekin Tiu | Towards Data Science](https://towardsdatascience.com/metrics-to-evaluate-your-semantic-segmentation-model-6bcb99639aa2)) for image binary segmentation evaluation in dl4j, please how i can use it with the other metrics available in dl4j, accuracy, precision, recall, and f1-score.

---

<div class="post-metadata">

**Author:** ![agibsonccc](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/agibsonccc/32/697_2.png) [@agibsonccc](https://community.konduit.ai/u/agibsonccc)\
**Post date:** [September 29, 2021, 9:51pm UTC](https://community.konduit.ai/t/jaccard-index-for-image-binary-segmentation-evaluation-in-dl4j/1624/2 "2021-09-29T21:51:26Z")

</div>

@AbdelmajidB Some of the ingredients for this are sitting in our YOLO classes: [deeplearning4j/Yolo2OutputLayer.java at fc735d30023981ebbb0fafa55ea9520ec44292e0 · eclipse/deeplearning4j · GitHub](https://github.com/eclipse/deeplearning4j/blob/fc735d30023981ebbb0fafa55ea9520ec44292e0/deeplearning4j/deeplearning4j-nn/src/main/java/org/deeplearning4j/nn/layers/objdetect/Yolo2OutputLayer.java#L413)

It would need to be manual though. We would need to implement an evaluation class standalone similar to our other evaluation classes otherwise.

---

<div class="post-metadata">

**Author:** ![AbdelmajidB](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/abdelmajidb/32/56_2.png) [@AbdelmajidB](https://community.konduit.ai/u/AbdelmajidB)\
**Post date:** [October 4, 2021, 4:30pm UTC](https://community.konduit.ai/t/jaccard-index-for-image-binary-segmentation-evaluation-in-dl4j/1624/3 "2021-10-04T16:30:55Z")

</div>

@agibsonccc Thank you so much for your relevant reply.