Results for “stdio-transport”

Trains vision transformers via self-distillation without labels for self-supervised visual representation learning, and supports export and inference of NVDINOv2 backbones.

Trains, evaluates, exports, and runs inference for FastFoundationStereo (FFS) stereo depth estimation models, a distilled variant of FoundationStereo with lower latency.

Trains, evaluates, exports, and runs inference on FoundationStereo models for stereo depth estimation and 3D reconstruction from stereo image pairs.

Trains, evaluates, exports, quantizes, and runs inference for SegFormer semantic segmentation models using NVIDIA TAO.

Flash a promoted BSP image to a Jetson device in RCM mode using NVIDIA's flash.sh or l4t_initrd_flash.sh toolchain.

Fine-tune Cosmos Reason video QA models using supervised fine-tuning with FSDP parallelism, including dataset preparation, spec construction, and AutoML support.

Train, evaluate, distill, quantize, export, and run inference for RT-DETR object detection models using NVIDIA TAO.

Train, evaluate, export, distill, quantize, or run inference for a TAO DINO 2D object detector using transformer-based detection with denoising training and multi-scale features.

Manage VIOS and NvStreamer REST API operations for video input/output and storage, including sensors, streams, snapshots, clips, and recordings.

Train, evaluate, export, and run inference for pose classification models using ST-GCN on skeleton keypoint sequences.

Build production-quality Model Context Protocol (MCP) servers in C#/.NET using the official 1.x NuGet packages, covering transports, tools, prompts, resources, and common pitfalls.