Las traducciones son generadas a través de traducción automática. En caso de conflicto entre la traducción y la version original de inglés, prevalecerá la version en inglés.
Modelos probados
Las siguientes secciones plegables proporcionan información sobre los modelos de aprendizaje automático que probó el equipo de Amazon SageMaker Neo. Amplíe la sección plegable en función de su estructura para comprobar si se ha probado un modelo.
nota
Esta no es una lista exhaustiva de los modelos que se pueden compilar con Neo.
Consulte Marcos admitidos los operadores compatibles con SageMaker Neo
Modelos |
ARMV8 |
ARMMali |
Ambarella CV22 |
Nvidia |
Panorama |
TI TDA4VM |
Qualcomm 03 QCS6 |
X86_Linux |
X86_Windows |
---|---|---|---|---|---|---|---|---|---|
AlexNet |
|||||||||
Resnet 50 |
X |
X |
X |
X |
X |
X |
X |
||
YOLOv2 |
X |
X |
X |
X |
X |
||||
YOLOv2_diminuto |
X |
X |
X |
X |
X |
X |
X |
||
YOLOv3_416 |
X |
X |
X |
X |
X |
||||
YOLOv3_tiny |
X |
X |
X |
X |
X |
X |
X |
Modelos |
ARMV8 |
ARMMali |
Ambarella CV22 |
Nvidia |
Panorama |
TI TDA4VM |
Qualcomm 03 QCS6 |
X86_Linux |
X86_Windows |
---|---|---|---|---|---|---|---|---|---|
AlexNet |
X |
||||||||
Densenet 121 |
X |
||||||||
DenseNet201 |
X |
X |
X |
X |
X |
X |
X |
X |
|
GoogLeNet |
X |
X |
X |
X |
X |
X |
X |
||
Inception v3 |
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_ 50_32x4d ResNext |
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 |
Modelos |
ARMV8 |
ARMMali |
Ambarella CV22 |
Nvidia |
Panorama |
TI TDA4VM |
Qualcomm 03 QCS6 |
X86_Linux |
X86_Windows |
---|---|---|---|---|---|---|---|---|---|
densenet 121 |
X |
X |
X |
X |
X |
X |
X |
X |
|
densenet 201 |
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 |
Modelos |
ARMV8 |
ARMMali |
Ambarella CV22 |
Nvidia |
Panorama |
TI TDA4VM |
Qualcomm 03 QCS6 |
X86_Linux |
X86_Windows |
---|---|---|---|---|---|---|---|---|---|
AlexNet |
X |
||||||||
mobilenetv2-1.0 |
X |
X |
X |
X |
X |
X |
X |
X |
|
resnet 18 contra 1 |
X |
X |
X |
X |
|||||
resnet18 v2 |
X |
X |
X |
X |
|||||
resnet50 v1 |
X |
X |
X |
X |
X |
X |
|||
resnet50 v2 |
X |
X |
X |
X |
X |
X |
|||
resnet 152 v1 |
X |
X |
X |
X |
|||||
resnet 152 v2 |
X |
X |
X |
X |
|||||
squeezenet 1.1 |
X |
X |
X |
X |
X |
X |
X |
||
vgg19 |
X |
X |
Modelos |
ARMV8 |
ARMMali |
Ambarella CV22 |
Ambarella CV25 |
Nvidia |
Panorama |
TI TDA4VM |
Qualcomm 03 QCS6 |
X86_Linux |
X86_Windows |
---|---|---|---|---|---|---|---|---|---|---|
densenet 121 |
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 |
||
squeezenet 1.0 |
X |
X |
X |
X |
X |
X | ||||
squeezenet 1.1 |
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 |