Results for “monocular-depth”

6 skills

tao-train-depth-anything-v2

Train, evaluate, export, and run inference for monocular depth estimation models using Metric Depth Anything v2 or Relative Depth Anything architectures via the TAO toolkit.

More results

deepstream-import-vision-model

Import object detection models from HuggingFace or NVIDIA NGC into a DeepStream pipeline with automated ONNX download, TensorRT engine build, custom parser, multi-stream benchmark, and PDF report generation.

tao-finetune-cosmos-reason

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

nemo-mbridge-perf-moe-vlm-training

Provides practical guidance for training Mixture-of-Experts Vision-Language Models in Megatron Bridge, comparing FSDP and 3D-parallel approaches with lessons from recent multimodal experiments.

Reduce high-dimensional data with UMAP for visualization, clustering preprocessing, and supervised or semi-supervised learning, including parameter tuning guidance.

tao-finetune-clip

Fine-tune and deploy CLIP vision-language models for zero-shot classification, image-text retrieval, and embedding extraction with ONNX and TensorRT support.