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.

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.

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

Estimate cell state transitions from unspliced/spliced mRNA dynamics using scVelo, infer trajectory directions, compute latent time, and identify driver genes in single-cell RNA-seq data.

Analyze RNA velocity in single-cell RNA-seq data with scVelo, estimating cell state transitions from unspliced/spliced mRNA dynamics, inferring trajectory directions, computing latent time, and identifying driver genes.

Scales machine learning training from single GPU to multi-node clusters with minimal code changes. Supports PyTorch, TensorFlow, and HuggingFace with built-in hyperparameter tuning, fault tolerance, and elastic scaling.