
Finds object-detection images where a model's predictions miss ground truth per class
- Open source
- 4K GitHub stars
- Computer vision


Finds object-detection images where a model's predictions miss ground truth per class

Runs an iterative NVIDIA TAO AOI loop that improves PCB defect-inspection models

Trains, evaluates and runs Visual ChangeNet models for PCB and AOI defect inspection

Guides an agent through root cause analysis of NVIDIA TAO ChangeNet classification model

Routes weak VCN samples into per-module parquet subsets for mining and AnomalyGen

Trains, evaluates, distills and quantizes PyTorch image classifiers inside TAO containers

Runs an iterative RT-DETR retraining loop for binary industrial defect detection

Runs NVIDIA TAO Grounding DINO detection through an iterative data-mining and retraining

Scores object detection predictions against ground truth to produce per-class mAP metrics

Trains, evaluates and exports TAO monocular depth models from single RGB images

Trains, evaluates, exports and runs TAO models that classify actions in video clips

Guides an agent through training, evaluating and exporting TAO SegFormer segmentation
The closest alternatives to Tao analyze gaps visual changenet are Tao analyze gaps od map, Tao run deft aoi, Tao train visual changenet, Tao analyze changenet rca and Tao route visual changenet samples.
Yes. Tao analyze gaps od map, Tao run deft aoi, Tao train visual changenet have a free or open-source option.