A trained detector for text in natural images.
What it does
Trains and prepares scene-text detectors, with workflows for evaluation, inference, pruning, quantization, and export.
When to use it
Use when training, evaluating, exporting, pruning, quantizing, retraining, or running inference with a TAO OCDNet model.
How to use it
Give it training and validation datasets; it runs OCDNet training and saves results to an output folder.
What you provide
- Your files
Latest review
What you need · 5
Requires Docker for the container-based runtime.
Requires NVIDIA Container Toolkit alongside Docker.
Requires at least one GPU with 8GB or more VRAM per GPU.
Must run first for a standalone installation when the session was not initialized by the TAO skill bank plugin.
Access · 0
No additional actions listed.