Training and inference scripts with TensorFlow optimizations that use the Intel® oneAPI Deep Neural Network Library (Intel® oneDNN) and Intel® Extension for PyTorch.
The model documentation in the tables below have information on the prerequisites to run each model. The model scripts run on Linux. Certain models are also able to run using bare metal on Windows. For more information and a list of models that are supported on Windows, see the documentation here.
For information on running more advanced use cases using the workload containers see the: advanced options documentation.
| Use Case | Model | Mode | Intel® Developer Catalog | Model Documentation | Benchmark/Test Dataset |
|---|---|---|---|---|---|
| Image Recognition | DenseNet169 | Inference | Model Containers: FP32 Model Packages: FP32 |
FP32 | ImageNet 2012 |
| Image Recognition | Inception V3 | Inference | Model Containers: Int8 FP32 Model Packages: Int8 FP32 |
Int8 FP32 | ImageNet 2012 |
| Image Recognition | Inception V4 | Inference | Model Containers: Int8 FP32 Model Packages: Int8 FP32 |
Int8 FP32 | ImageNet 2012 |
| Image Recognition | MobileNet V1* | Inference | Model Containers: Int8 FP32 Model Packages: Int8 FP32 |
Int8 FP32 BFloat16 | ImageNet 2012 |
| Image Recognition | ResNet 101 | Inference | Model Containers: Int8 FP32 Model Packages: Int8 FP32 |
Int8 FP32 | ImageNet 2012 |
| Image Recognition | ResNet 50 | Inference | Model Containers: Int8 FP32 Model Packages: Int8 FP32 |
Int8 FP32 | ImageNet 2012 |
| Image Recognition | ResNet 50v1.5 | Inference | Model Containers: Int8 FP32 BFloat16 Model Packages: Int8 FP32 BFloat16 |
Int8 FP32 BFloat16 | ImageNet 2012 |
| Image Recognition | ResNet 50v1.5 | Training | Model Containers: FP32 BFloat16 Model Packages: FP32 BFloat16 |
FP32 BFloat16 | ImageNet 2012 |
| Image Segmentation | 3D U-Net | Inference | Model Containers: FP32 Model Packages: FP32 |
FP32 | BRATS 2018 |
| Image Segmentation | 3D U-Net MLPerf* | Inference | FP32 BFloat16 | BRATS 2019 | |
| Image Segmentation | MaskRCNN | Inference | Model Containers: FP32 Model Packages: FP32 |
FP32 | MS COCO 2014 |
| Image Segmentation | UNet | Inference | Model Containers: FP32 Model Packages: FP32 |
FP32 | |
| Language Modeling | BERT | Inference | Model Containers: FP32 BFloat16 Model Packages: FP32 BFloat16 |
FP32 BFloat16 | SQuAD |
| Language Modeling | BERT | Training | Model Containers: FP32 BFloat16 Model Packages: FP32 BFloat16 |
FP32 BFloat16 | SQuAD and MRPC |
| Language Translation | BERT | Inference | FP32 | MRPC | |
| Language Translation | GNMT* | Inference | Model Containers: FP32 Model Packages: FP32 |
FP32 | MLPerf GNMT model benchmarking dataset |
| Language Translation | Transformer_LT_mlperf* | Training | Model Containers: FP32 BFloat16 Model Packages: FP32 BFloat16 |
FP32 BFloat16 | WMT English-German dataset |
| Language Translation | Transformer_LT_mlperf* | Inference | FP32 BFloat16 Int8 | WMT English-German data | |
| Language Translation | Transformer_LT_Official | Inference | Model Containers: FP32 Model Packages: FP32 |
FP32 | WMT English-German dataset |
| Object Detection | Faster R-CNN | Inference | Model Containers: Int8 FP32 Model Packages: Int8 FP32 |
Int8 FP32 | COCO 2017 validation dataset |
| Object Detection | R-FCN | Inference | Model Containers: Int8 FP32 Model Packages: Int8 FP32 |
Int8 FP32 | COCO 2017 validation dataset |
| Object Detection | SSD-MobileNet* | Inference | Model Containers: Int8 FP32 Model Packages: Int8 FP32 |
Int8 FP32 BFloat16 | COCO 2017 validation dataset |
| Object Detection | SSD-ResNet34* | Inference | Model Containers: Int8 FP32 Model Packages: Int8 FP32 |
Int8 FP32 BFloat16 | COCO 2017 validation dataset |
| Object Detection | SSD-ResNet34 | Training | Model Containers: FP32 BFloat16 Model Packages: FP32 BFloat16 |
FP32 BFloat16 | COCO 2017 training dataset |
| Recommendation | DIEN | Inference | FP32 BFloat16 | DIEN dataset | |
| Recommendation | DIEN | Training | FP32 | DIEN dataset | |
| Recommendation | NCF | Inference | Model Containers: FP32 Model Packages: FP32 |
FP32 | MovieLens 1M |
| Recommendation | Wide & Deep | Inference | Model Containers: FP32 Model Packages: FP32 |
FP32 | Census Income dataset |
| Recommendation | Wide & Deep Large Dataset | Inference | Model Containers: Int8 FP32 Model Packages: Int8 FP32 |
Int8 FP32 | Large Kaggle Display Advertising Challenge dataset |
| Recommendation | Wide & Deep Large Dataset | Training | Model Containers: FP32 Model Packages: FP32 |
FP32 | Large Kaggle Display Advertising Challenge dataset |
| Text-to-Speech | WaveNet | Inference | Model Containers: FP32 Model Packages: FP32 |
FP32 |
| Use Case | Model | Mode | Model Documentation |
|---|---|---|---|
| Image Recognition | Inception V3 | Inference | FP32 |
| Image Recognition | ResNet 50v1.5 | Inference | FP32 |
| Language Translation | Transformer_LT_Official | Inference | FP32 |
| Object Detection | SSD-MobileNet | Inference | FP32 |
| Use Case | Model | Mode | Model Documentation |
|---|---|---|---|
| Image Recognition | GoogLeNet | Inference | FP32 BFloat16 |
| Image Recognition | Inception v3 | Inference | FP32 BFloat16 |
| Image Recognition | MNASNet 0.5 | Inference | FP32 BFloat16 |
| Image Recognition | MNASNet 1.0 | Inference | FP32 BFloat16 |
| Image Recognition | ResNet 50 | Inference | FP32 Int8 BFloat16 |
| Image Recognition | ResNet 50 | Training | FP32 BFloat16 |
| Image Recognition | ResNet 101 | Inference | FP32 BFloat16 |
| Image Recognition | ResNet 152 | Inference | FP32 BFloat16 |
| Image Recognition | ResNext 32x4d | Inference | FP32 BFloat16 |
| Image Recognition | ResNext 32x16d | Inference | FP32 Int8 BFloat16 |
| Image Recognition | VGG-11 | Inference | FP32 BFloat16 |
| Image Recognition | VGG-11 with batch normalization | Inference | FP32 BFloat16 |
| Image Recognition | Wide ResNet-50-2 | Inference | FP32 BFloat16 |
| Image Recognition | Wide ResNet-101-2 | Inference | FP32 BFloat16 |
| Language Modeling | BERT base | Inference | FP32 BFloat16 |
| Language Modeling | BERT large | Inference | FP16 FP32 Int8 BFloat16 BFloat32 |
| Language Modeling | BERT large | Training | FP32 BFloat16 |
| Language Modeling | DistilBERT base | Inference | FP32 BFloat16 |
| Language Modeling | RNN-T | Inference | FP32 BFloat16 |
| Language Modeling | RNN-T | Training | FP32 BFloat16 |
| Language Modeling | RoBERTa base | Inference | FP32 BFloat16 |
| Language Modeling | T5 | Inference | FP32 Int8 |
| Object Detection | Faster R-CNN ResNet50 FPN | Inference | FP32 BFloat16 |
| Object Detection | Mask R-CNN | Inference | FP32 BFloat16 |
| Object Detection | Mask R-CNN | Training | FP32 BFloat16 |
| Object Detection | Mask R-CNN ResNet50 FPN | Inference | FP32 BFloat16 |
| Object Detection | RetinaNet ResNet-50 FPN | Inference | FP32 BFloat16 |
| Object Detection | SSD-ResNet34 | Inference | FP32 Int8 BFloat16 |
| Object Detection | SSD-ResNet34 | Training | FP32 BFloat16 |
| Recommendation | DLRM | Inference | FP32 Int8 BFloat16 |
| Recommendation | DLRM | Training | FP32 BFloat16 |
| Shot Boundary Detection | TransNetV2 | Inference | FP32 BFloat16 |
| AI Drug Design (AIDD) | AlphaFold2 | Inference | FP32 |
*Means the model belongs to MLPerf models and will be supported long-term.