Training and inference scripts with Intel-optimized MKL
The model scripts can be run on Linux and require the following dependencies to be installed:
Use Case | Framework | Model | Mode | Instructions |
---|---|---|---|---|
Image Recognition | TensorFlow | DenseNet169 | Inference | FP32 |
Image Recognition | TensorFlow | Inception V3 | Inference | Int8 FP32 |
Image Recognition | TensorFlow | Inception V4 | Inference | Int8 FP32 |
Image Recognition | TensorFlow | MobileNet V1* | Inference | Int8 FP32 |
Image Recognition | TensorFlow | ResNet 101 | Inference | Int8 FP32 |
Image Recognition | TensorFlow | ResNet 50 | Inference | Int8 FP32 |
Image Recognition | TensorFlow | ResNet 50v1.5 | Inference | Int8 FP32 BFloat16** |
Image Recognition | TensorFlow | ResNet 50v1.5 | Training | FP32 BFloat16** |
Image Segmentation | TensorFlow | UNet | Inference | FP32 |
Image Segmentation | TensorFlow | MaskRCNN | Inference | FP32 |
Language Modeling | TensorFlow | BERT | Inference | FP32 BFloat16** |
Language Modeling | TensorFlow | BERT | Training | FP32 BFloat16** |
Language Translation | TensorFlow | BERT | Inference | FP32 |
Language Translation | TensorFlow | GNMT* | Inference | FP32 |
Language Translation | TensorFlow | Transformer_LT_Official | Inference | FP32 |
Language Translation | TensorFlow | Transformer_LT_mlperf | Training | FP32 BFloat16** |
Object Detection | TensorFlow | Faster R-CNN | Inference | Int8 FP32 |
Object Detection | TensorFlow | R-FCN | Inference | Int8 FP32 |
Object Detection | TensorFlow | SSD-MobileNet* | Inference | Int8 FP32 |
Object Detection | TensorFlow | SSD-ResNet34* | Inference | Int8 FP32 |
Object Detection | TensorFlow | SSD-ResNet34 | Training | FP32 BFloat16** |
Recommendation | TensorFlow | NCF | Inference | FP32 |
Recommendation | TensorFlow | Wide & Deep Large Dataset | Inference | Int8 FP32 |
Recommendation | TensorFlow | Wide & Deep Large Dataset | Training | FP32 |
Recommendation | TensorFlow | Wide & Deep | Inference | FP32 |
Reinforcement | TensorFlow | MiniGo | Training | FP32 |
Text-to-Speech | TensorFlow | WaveNet | Inference | FP32 |
Use Case | Framework | Model | Mode | Instructions |
---|---|---|---|---|
Image Recognition | TensorFlow Serving | Inception V3 | Inference | FP32 |
Image Recognition | TensorFlow Serving | ResNet 50v1.5 | Inference | FP32 |
Language Translation | TensorFlow Serving | Transformer_LT_Official | Inference | FP32 |
Object Detection | TensorFlow Serving | SSD-MobileNet | Inference | FP32 |
Use Case | Framework | Model | Mode | Instructions |
---|---|---|---|---|
Recommendation | PyTorch | DLRM | Training | BFloat16** |
*Means the model belongs to MLPerf models and will be supported long-term.
**Means the BFloat16 data type support is experimental.