Product Performance Deepdive
World-class AI model compression performance, with the highest Accuracy Retention
Type | Object Detection | Classification | Super Resolution | Transformer | ||
---|---|---|---|---|---|---|
Name | YoloV7 | RetinaFace-ResNet50 | ResNet18 | MobilenetV3 (L) | IMDN | ViT B16 |
Original | 0.68 | 0.55 | 69.7 | 75.3 | 27.9 | 81.1 |
CLIKA | No Loss | No Loss | No Loss | -0.6 | -0.1 | -0.5 |
Meta PyTorch | -0.04 | -0.01 | -0.7 | -2.0 | -0.3 | FAILED |
Nvidia TensorRT | -0.28 | -0.01 | -0.6 | FAILED | -9.0 | N/A |
Google TFLite | N/A | N/A | FAILED | FAILED | N/A | N/A |
Intel NNCF | No Loss | -0.01 | -0.5 | -4.9 | -1.9 | -6.4 |