{"name": "GeoSeg Studio", "package_name": "GeoSegStudio", "description": "Full-pipeline deep learning semantic segmentation for geospatial raster data.", "about": "GeoSeg Studio is a complete deep learning segmentation environment for QGIS. It covers the full workflow in one plugin: prepare training data (clip, split, augment), train your own segmentation model, evaluate performance, run predictions on new rasters, and post-process vector outputs \u2014 all without leaving QGIS. Runs on both QGIS 3 (Qt5) and QGIS 4 (Qt6). EXTERNAL DEPENDENCY: PyTorch and torchvision are not bundled. On first run the plugin offers to install them with pip into an isolated virtual environment that it manages itself; nothing outside that environment is modified. This requires an internet connection and about 5 GB of free disk space, and can be skipped or done manually (see requirements.txt). GPU acceleration needs an NVIDIA card with driver 522.06 or newer; the installer detects the driver and preselects a matching CUDA build. On macOS, on AMD/Intel GPUs, and where no suitable NVIDIA driver is present the plugin runs on CPU, which is considerably slower for training.", "homepage": "https://github.com/dronnix-io/GeoSegStudio", "repository": "https://github.com/dronnix-io/GeoSegStudio.git", "tracker": "https://github.com/dronnix-io/GeoSegStudio/issues", "author": "Salar Ghaffarian", "tags": ["ai", "remote sensing", "pytorch", "u-net", "deep learning", "semantic segmentation", "neural network", "training", "raster", "segmentation"], "downloads": 696, "latest_version": "1.1.1", "versions": [{"version": "1.1.1", "experimental": false, "qgis_min": "3.34.0", "qgis_max": "4.99.0", "downloads": 116, "uploaded_by": "salarghaffarian", "upload_datetime": "2026-09-12T04:16:17.970889"}, {"version": "1.0.0", "experimental": false, "qgis_min": "3.34.0", "qgis_max": "3.99.0", "downloads": 580, "uploaded_by": "salarghaffarian", "upload_datetime": "2026-04-04T17:31:24.076373"}]}