https://deeplearning.earth/tags/deployment/Recent content in Deployment on DeepLearning.EarthHugo -- gohugo.ioenMon, 12 Oct 2026 06:30:00 +0700https://deeplearning.earth/posts/2026-10-08_onnx_export_without_pytorch/Thu, 08 Oct 2026 06:00:00 +0700https://deeplearning.earth/posts/2026-10-08_onnx_export_without_pytorch/Train on the GPU box. Send the infer box a small graph. oriented-det writes a pre-NMS ONNX file. The graph decodes the boxes. A few lines of Python prepare the image and run the rotated NMS. The machine that runs it needs numpy, Pillow, and ONNX Runtime. For a tiled optical scene at 1024 pixels, that is enough to ship this week. The commands are below. ONNX Runtime overlay — Rotated FCOS DOTA 1× Hub on the export demo tile (score ≥ 0.https://deeplearning.earth/posts/2026-10-05_deploy_oriented_det_in_docker/Mon, 05 Oct 2026 06:00:00 +0700https://deeplearning.earth/posts/2026-10-05_deploy_oriented_det_in_docker/I wanted a tile to go in and polygons to come out, the way a GIS service already expects. oriented-det ships that as a container: deploy/example/. You bake a checkpoint, docker build, and POST a JPEG. GeoJSON comes back. A large scene is tiled inside the image. I tried it with Oriented R-CNN on the bus-lot demo, at score 0.55. 100 boxes came back — 95 large vehicles and 5 small ones.