Mark Kurtz

icon indicating a website link https://www.linkedin.com/in/markkurtzjr/ icon indicating an email [email protected]

icon company Red Hat icon location Boston icon location Member of Technical Staff at @redhat - making AI faster, cheaper, and smarter

Results 5 issues of Mark Kurtz

YOLOv5l model crashing on c5.12xlarge for batch size > 8

From community slack https://discuss-neuralmagic.slack.com/archives/C020FPF3MQX/p1657890578280219: [mt](https://app.slack.com/team/U03JVQ69Y4D) [8:09 AM](https://discuss-neuralmagic.slack.com/archives/C020FPF3MQX/p1657890578280219) Hello! I was using deepsparse on a checkpoint of a yolov5l model generated by --one-shot on a c5.12xlarge and got the following error...

bug

SparseML create_pruning_recipe API erroring out on YOLOv3 tiny

From community slack https://discuss-neuralmagic.slack.com/team/U03P31PUJGM: [Trunov Pavel](https://app.slack.com/team/U03P31PUJGM) [11:05 AM](https://discuss-neuralmagic.slack.com/archives/C020FPF3MQX/p1657728332430099) Hello! I'm trying to prune yolov3-tiny using sparseml. There is no recipe for tiny but I've figured out that it's possible to...

bug

[Cherry Pick] Update release state for recipe bug fix and dependabot version upgrades for 0.12.1

Square head distillation implementation for new SparseML framework

Example recipe for what this enables: ``` OutputDistillationModifier: targets: ['layer.1', 'layer.2'] transforms: [] comparison: "square_head" orig_scale: 1.0 distill_scale: 1.0 ```

Automation testing