Skip to content

Latest commit

 

History

History
169 lines (158 loc) · 5.2 KB

README.md

File metadata and controls

169 lines (158 loc) · 5.2 KB

Examples

Intel® Neural Compressor validated examples with multiple compression techniques, including quantization, pruning, knowledge distillation and orchestration. Part of the validated cases can be found in the example tables, and the release data is available here.

PyTorch Examples

Quantization

Model Domain Method Examples
gpt_j Natural Language Processing Weight-Only Quantization link
Static Quantization (IPEX) link
llama2_7b Natural Language Processing Weight-Only Quantization link
Static Quantization (IPEX) link
opt_125m Natural Language Processing Static Quantization (IPEX) link
Static Quantization (PT2E) link
Weight-Only Quantization link
resnet18 Image Recognition Mixed Precision link
Static Quantization link

TensorFlow Examples

Quantization

Model Domain Method Examples
bert_large_squad_model_zoo Natural Language Processing Post-Training Static Quantization link
transformer_lt Natural Language Processing Post-Training Static Quantization link
inception_v3 Image Recognition Post-Training Static Quantization link
mobilenetv2 Image Recognition Post-Training Static Quantization link
resnetv2_50 Image Recognition Post-Training Static Quantization link
vgg16 Image Recognition Post-Training Static Quantization link
ViT Image Recognition Post-Training Static Quantization link
GraphSage Graph Networks Post-Training Static Quantization link
yolo_v5 Object Detection Post-Training Static Quantization link
faster_rcnn_resnet50 Object Detection Post-Training Static Quantization link
mask_rcnn_inception_v2 Object Detection Post-Training Static Quantization link
ssd_mobilenet_v1 Object Detection Post-Training Static Quantization link
wide_deep_large_ds Recommendation Post-Training Static Quantization link
3dunet-mlperf Semantic Image Segmentation Post-Training Static Quantization link