Train models to match fine-grained images.
What it does
Trains, evaluates, and exports fine-grained image-recognition models that match images through learned embeddings.
When to use it
Use when training, evaluating, exporting, or running inference for a TAO metric-learning recognition model.
How to use it
Give it image datasets or model checkpoints and a requested model operation; it produces training, evaluation, inference, or export results in output folders.
What you provide
- Your files
Uses
Latest review
What you need · 5
Requires Docker to run the model workflow.
Requires the NVIDIA container toolkit alongside Docker.
Requires at least one GPU with 16GB or more VRAM per GPU; two GPUs are recommended.
Access · 1
This skill
wandb
Write
Tracks training runs with wandb