A modern programming language that makes developers happier.

kotlinlang

Hi all, I’ve got ONNX model and some Python scripts doing post-processing to give me segmented bounding boxes. Wondering if I can pull off the same thing with KotlinDL. Anyone tried this before? If so, how’d you go about it? Any tips or code snippets would be awesome!

It should be possible (depending on the model and type of post-processing). Please check out the examples from KotlinDL. For example, here is a code for object detection using the SSD model: <https://github.com/Kotlin/kotlindl/blob/master/examples/src/main/kotlin/examples/onnx/objectdetection/ssd/SSD.kt>. <https://github.com/Kotlin/kotlindl/blob/master/onnx/src/jvmMain/kotlin/org/jetbrains/kotlinx/dl/onnx/inference/objectdetection/SSDObjectDetectionModel.kt|https://github.com/Kotlin/kotlindl/blob/master/onnx/src/jvmMain/kotlin/org/jetbrai[…]nx/dl/onnx/inference/objectdetection/SSDObjectDetectionModel.kt>