翻訳は機械翻訳により提供されています。提供された翻訳内容と英語版の間で齟齬、不一致または矛盾がある場合、英語版が優先します。

# テスト済みモデル
<a name="neo-supported-edge-tested-models"></a>

次の折りたたみ可能なセクションでは、Amazon SageMaker Neo チームでテスト済みの機械学習モデルの情報を提供します。お使いのフレームワークに応じて折りたたみ可能なセクションを展開して、モデルがテスト済みかどうか確認してください。

**注記**  
これは、Neo でコンパイルできるモデルを包括的にリストしたものではありません。

お使いのモデルを SageMaker AI Neo でコンパイルできるかどうかについては、「[サポートされるフレームワーク](neo-supported-devices-edge-frameworks.md)」と「[SageMaker AI Neo Supported Operators](https://aws.amazon.com/releasenotes/sagemaker-neo-supported-frameworks-and-operators/)」を参照してください。

## DarkNet
<a name="collapsible-section-01"></a>


| モデル | ARM V8 | ARM Mali | Ambarella CV22 | NVIDIA | Panorama | TI TDA4VM | Qualcomm QCS603 | X86\_Linux | X86\_Windows | 
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | 
| Alexnet |  |  |  |  |  |  |  |  |  | 
| ResNet50 | X | X |  | X | X | X |  | X | X | 
| YOLOv2 |  |  |  | X | X | X |  | X | X | 
| YOLOv2\_tiny | X | X |  | X | X | X |  | X | X | 
| YOLOv3\_416 |  |  |  | X | X | X |  | X | X | 
| YOLOv3\_tiny | X | X |  | X | X | X |  | X | X | 

## MXNet
<a name="collapsible-section-02"></a>


| モデル | ARM V8 | ARM Mali | Ambarella CV22 | NVIDIA | Panorama | TI TDA4VM | Qualcomm QCS603 | X86\_Linux | X86\_Windows | 
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | 
| Alexnet |  |  | X |  |  |  |  |  |  | 
| Densenet121 |  |  | X |  |  |  |  |  |  | 
| DenseNet201 | X | X | X | X | X | X |  | X | X | 
| GoogLeNet | X | X |  | X | X | X |  | X | X | 
| InceptionV3 |  |  |  | X | X | X |  | X | X | 
| MobileNet0.75 | X | X |  | X | X | X |  |  | X | 
| MobileNet1.0 | X | X | X | X | X | X |  |  | X | 
| MobileNetV2\_0.5 | X | X |  | X | X | X |  |  | X | 
| MobileNetV2\_1.0 | X | X | X | X | X | X | X | X | X | 
| MobileNetV3\_Large | X | X | X | X | X | X | X | X | X | 
| MobileNetV3\_Small | X | X | X | X | X | X | X | X | X | 
| ResNeSt50 |  |  |  | X | X |  |  | X | X | 
| ResNet18\_v1 | X | X | X | X | X | X |  |  | X | 
| ResNet18\_v2 | X | X |  | X | X | X |  |  | X | 
| ResNet50\_v1 | X | X | X | X | X | X |  | X | X | 
| ResNet50\_v2 | X | X | X | X | X | X |  | X | X | 
| ResNext101\_32x4d |  |  |  |  |  |  |  |  |  | 
| ResNext50\_32x4d | X |  | X | X | X |  |  | X | X | 
| SENet\_154 |  |  |  | X | X | X |  | X | X | 
| SE\_ResNext50\_32x4d | X | X |  | X | X | X |  | X | X | 
| SqueezeNet1.0 | X | X | X | X | X | X |  |  | X | 
| SqueezeNet1.1 | X | X | X | X | X | X |  | X | X | 
| VGG11 | X | X | X | X | X |  |  | X | X | 
| Xception | X | X | X | X | X | X |  | X | X | 
| darknet53 | X | X |  | X | X | X |  | X | X | 
| resnet18\_v1b\_0.89 | X | X |  | X | X | X |  |  | X | 
| resnet50\_v1d\_0.11 | X | X |  | X | X | X |  |  | X | 
| resnet50\_v1d\_0.86 | X | X | X | X | X | X |  | X | X | 
| ssd\_512\_mobilenet1.0\_coco | X |  | X | X | X | X |  | X | X | 
| ssd\_512\_mobilenet1.0\_voc | X |  | X | X | X | X |  | X | X | 
| ssd\_resnet50\_v1 | X |  | X | X | X |  |  | X | X | 
| yolo3\_darknet53\_coco | X |  |  | X | X |  |  | X | X | 
| yolo3\_mobilenet1.0\_coco | X | X |  | X | X | X |  | X | X | 
| deeplab\_resnet50 |  |  | X |  |  |  |  |  |  | 

## Keras
<a name="collapsible-section-03"></a>


| モデル | ARM V8 | ARM Mali | Ambarella CV22 | NVIDIA | Panorama | TI TDA4VM | Qualcomm QCS603 | X86\_Linux | X86\_Windows | 
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | 
| densenet121 | X | X | X | X | X | X |  | X | X | 
| densenet201 | X | X | X | X | X | X |  |  | X | 
| inception\_v3 | X | X |  | X | X | X |  | X | X | 
| mobilenet\_v1 | X | X | X | X | X | X |  | X | X | 
| mobilenet\_v2 | X | X | X | X | X | X |  | X | X | 
| resnet152\_v1 |  |  |  | X | X |  |  |  | X | 
| resnet152\_v2 |  |  |  | X | X |  |  |  | X | 
| resnet50\_v1 | X | X | X | X | X |  |  | X | X | 
| resnet50\_v2 | X | X | X | X | X | X |  | X | X | 
| vgg16 |  |  | X | X | X |  |  | X | X | 

## ONNX
<a name="collapsible-section-04"></a>


| モデル | ARM V8 | ARM Mali | Ambarella CV22 | NVIDIA | Panorama | TI TDA4VM | Qualcomm QCS603 | X86\_Linux | X86\_Windows | 
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | 
| alexnet |  |  | X |  |  |  |  |  |  | 
| mobilenetv2-1.0 | X | X | X | X | X | X |  | X | X | 
| resnet18v1 | X |  |  | X | X |  |  |  | X | 
| resnet18v2 | X |  |  | X | X |  |  |  | X | 
| resnet50v1 | X |  | X | X | X |  |  | X | X | 
| resnet50v2 | X |  | X | X | X |  |  | X | X | 
| resnet152v1 |  |  |  | X | X | X |  |  | X | 
| resnet152v2 |  |  |  | X | X | X |  |  | X | 
| squeezenet1.1 | X |  | X | X | X | X |  | X | X | 
| vgg19 |  |  | X |  |  |  |  |  | X | 

## PyTorch (FP32)
<a name="collapsible-section-05"></a>


| モデル | ARM V8 | ARM Mali | Ambarella CV22 | Ambarella CV25 | NVIDIA | Panorama | TI TDA4VM | Qualcomm QCS603 | X86\_Linux | X86\_Windows | 
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | 
| densenet121 | X | X | X | X | X | X | X |  | X | X | 
| inception\_v3 |  | X |  |  | X | X | X |  | X | X | 
| resnet152 |  |  |  |  | X | X | X |  |  | X | 
| resnet18 | X | X |  |  | X | X | X |  |  | X | 
| resnet50 | X | X | X | X | X | X |  |  | X | X | 
| squeezenet1.0 | X | X |  |  | X | X | X |  |  | X | 
| squeezenet1.1 | X | X | X | X | X | X | X |  | X | X | 
| yolov4 |  |  |  |  | X | X |  |  |  |  | 
| yolov5 |  |  |  | X | X | X |  |  |  |  | 
| fasterrcnn\_resnet50\_fpn |  |  |  |  | X | X |  |  |  |  | 
| maskrcnn\_resnet50\_fpn |  |  |  |  | X | X |  |  |  |  | 

## TensorFlow
<a name="collapsible-section-06"></a>

------
#### [ TensorFlow ]


| モデル | ARM V8 | ARM Mali | Ambarella CV22 | Ambarella CV25 | NVIDIA | Panorama | TI TDA4VM | Qualcomm QCS603 | X86\_Linux | X86\_Windows | 
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | 
| densenet201 | X | X | X | X | X | X | X |  | X | X | 
| inception\_v3 | X | X | X |  | X | X | X |  | X | X | 
| mobilenet100\_v1 | X | X | X |  | X | X | X |  |  | X | 
| mobilenet100\_v2.0 | X | X | X |  | X | X | X |  | X | X | 
| mobilenet130\_v2 | X | X |  |  | X | X | X |  |  | X | 
| mobilenet140\_v2 | X | X | X |  | X | X | X |  | X | X | 
| resnet50\_v1.5 | X | X |  |  | X | X | X |  | X | X | 
| resnet50\_v2 | X | X | X | X | X | X | X |  | X | X | 
| squeezenet | X | X | X | X | X | X | X |  | X | X | 
| mask\_rcnn\_inception\_resnet\_v2 |  |  |  |  | X |  |  |  |  |  | 
| ssd\_mobilenet\_v2 |  |  |  |  | X | X |  |  |  |  | 
| faster\_rcnn\_resnet50\_lowproposals |  |  |  |  | X |  |  |  |  |  | 
| rfcn\_resnet101 |  |  |  |  | X |  |  |  |  |  | 

------
#### [ TensorFlow.Keras ]


| モデル | ARM V8 | ARM Mali | Ambarella CV22 | NVIDIA | Panorama | TI TDA4VM | Qualcomm QCS603 | X86\_Linux | X86\_Windows | 
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | 
| DenseNet121 | X | X |  | X | X | X |  | X | X | 
| DenseNet201 | X | X |  | X | X | X |  |  | X | 
| InceptionV3 | X | X |  | X | X | X |  | X | X | 
| MobileNet | X | X |  | X | X | X |  | X | X | 
| MobileNetv2 | X | X |  | X | X | X |  | X | X | 
| NASNetLarge |  |  |  | X | X |  |  | X | X | 
| NASNetMobile | X | X |  | X | X | X |  | X | X | 
| ResNet101 |  |  |  | X | X | X |  |  | X | 
| ResNet101V2 |  |  |  | X | X | X |  |  | X | 
| ResNet152 |  |  |  | X | X |  |  |  | X | 
| ResNet152v2 |  |  |  | X | X |  |  |  | X | 
| ResNet50 | X | X |  | X | X |  |  | X | X | 
| ResNet50V2 | X | X |  | X | X | X |  | X | X | 
| VGG16 |  |  |  | X | X |  |  | X | X | 
| Xception | X | X |  | X | X | X |  | X | X | 

------

## TensorFlow Lite
<a name="collapsible-section-07"></a>

------
#### [ TensorFlow-Lite (FP32) ]


| モデル | ARM V8 | ARM Mali | Ambarella CV22 | NVIDIA | Panorama | TI TDA4VM | Qualcomm QCS603 | X86\_Linux | X86\_Windows | i.MX 8M Plus | 
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | 
| densenet\_2018\_04\_27 | X |  |  | X | X | X |  |  | X |  | 
| inception\_resnet\_v2\_2018\_04\_27 |  |  |  | X | X | X |  |  | X |  | 
| inception\_v3\_2018\_04\_27 |  |  |  | X | X | X |  |  | X | X | 
| inception\_v4\_2018\_04\_27 |  |  |  | X | X | X |  |  | X | X | 
| mnasnet\_0.5\_224\_09\_07\_2018 | X |  |  | X | X | X |  |  | X |  | 
| mnasnet\_1.0\_224\_09\_07\_2018 | X |  |  | X | X | X |  |  | X |  | 
| mnasnet\_1.3\_224\_09\_07\_2018 | X |  |  | X | X | X |  |  | X |  | 
| mobilenet\_v1\_0.25\_128 | X |  |  | X | X | X |  |  | X | X | 
| mobilenet\_v1\_0.25\_224 | X |  |  | X | X | X |  |  | X | X | 
| mobilenet\_v1\_0.5\_128 | X |  |  | X | X | X |  |  | X | X | 
| mobilenet\_v1\_0.5\_224 | X |  |  | X | X | X |  |  | X | X | 
| mobilenet\_v1\_0.75\_128 | X |  |  | X | X | X |  |  | X | X | 
| mobilenet\_v1\_0.75\_224 | X |  |  | X | X | X |  |  | X | X | 
| mobilenet\_v1\_1.0\_128 | X |  |  | X | X | X |  |  | X | X | 
| mobilenet\_v1\_1.0\_192 | X |  |  | X | X | X |  |  | X | X | 
| mobilenet\_v2\_1.0\_224 | X |  |  | X | X | X |  |  | X | X | 
| resnet\_v2\_101 |  |  |  | X | X | X |  |  | X |  | 
| squeezenet\_2018\_04\_27 | X |  |  | X | X | X |  |  | X |  | 

------
#### [ TensorFlow-Lite (INT8) ]


| モデル | ARM V8 | ARM Mali | Ambarella CV22 | NVIDIA | Panorama | TI TDA4VM | Qualcomm QCS603 | X86\_Linux | X86\_Windows | i.MX 8M Plus | 
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | 
| inception\_v1 |  |  |  |  |  |  | X |  |  | X | 
| inception\_v2 |  |  |  |  |  |  | X |  |  | X | 
| inception\_v3 | X |  |  |  |  | X | X |  | X | X | 
| inception\_v4\_299 | X |  |  |  |  | X | X |  | X | X | 
| mobilenet\_v1\_0.25\_128 | X |  |  |  |  | X |  |  | X | X | 
| mobilenet\_v1\_0.25\_224 | X |  |  |  |  | X |  |  | X | X | 
| mobilenet\_v1\_0.5\_128 | X |  |  |  |  | X |  |  | X | X | 
| mobilenet\_v1\_0.5\_224 | X |  |  |  |  | X |  |  | X | X | 
| mobilenet\_v1\_0.75\_128 | X |  |  |  |  | X |  |  | X | X | 
| mobilenet\_v1\_0.75\_224 | X |  |  |  |  | X | X |  | X | X | 
| mobilenet\_v1\_1.0\_128 | X |  |  |  |  | X |  |  | X | X | 
| mobilenet\_v1\_1.0\_224 | X |  |  |  |  | X | X |  | X | X | 
| mobilenet\_v2\_1.0\_224 | X |  |  |  |  | X | X |  | X | X | 
| deeplab-v3\_513 |  |  |  |  |  |  | X |  |  |  | 

------