AI Models verified for OpenVINO™ - ONNX only#
The following is a list of ONNX models that have been verified to work with OpenVINO. Note that other models may also work properly but have not been tested.
AI Models that run on Intel® Core Ultra™ Processors with OpenVINO™ toolkit:
Model |
Category |
Framework |
Precision |
AI PC CPU |
AI PC GPU |
AI PC NPU |
---|---|---|---|---|---|---|
GPT-2 |
Large Language Model |
onnx |
FP16 |
|||
GPT-2 |
Large Language Model |
onnx |
FP32 |
|||
aclnet |
Sound Classification |
onnx |
FP16 |
|||
aclnet |
Sound Classification |
onnx |
FP16-INT8 |
|||
aclnet |
Sound Classification |
onnx |
FP32 |
|||
aclnet-int8 |
Sound Classification |
onnx |
FP16-INT8 |
|||
albert-base-v2 |
Transformer |
onnx |
FP16 |
|||
alexnet |
Image Classification |
onnx |
FP32 |
|||
alexnet |
Image Classification |
onnx |
FP16 |
|||
anti-spoof-mn3 |
Object Detection |
onnx |
FP16 |
|||
asl-recognition-0003 |
Image Classification |
onnx |
FP16 |
|||
asl-recognition-0003 |
Image Classification |
onnx |
FP16-INT8 |
|||
asl-recognition-0003 |
Image Classification |
onnx |
FP32 |
|||
asl-recognition-0004 |
Image Classification |
onnx |
FP16 |
|||
began |
Image Processing, Enhancement |
onnx |
FP16 |
|||
began |
Image Processing, Enhancement |
onnx |
FP32 |
|||
bert-base-cased |
Natural Language Processing |
onnx |
FP16 |
|||
bert-base-cased |
Natural Language Processing |
onnx |
FP16-INT8 |
|||
bert-base-cased |
Natural Language Processing |
onnx |
FP32 |
|||
bert-base-cased-squad2 |
Natural Language Processing |
onnx |
FP32 |
|||
bert-base-cased-squad2 |
Natural Language Processing |
onnx |
FP16 |
|||
bert-base-ner |
Natural Language Processing |
onnx |
FP16 |
|||
bert-base-ner |
Natural Language Processing |
onnx |
FP32 |
|||
bert-base-ner |
Natural Language Processing |
onnx |
FP16-INT8 |
|||
bert-base-uncased-mrpc |
Natural Language Processing |
onnx |
FP16-INT8 |
|||
bert-base-uncased-mrpc |
Natural Language Processing |
onnx |
FP32 |
|||
bert-base-uncased-mrpc |
Natural Language Processing |
onnx |
FP16 |
|||
bert-large-cased |
Natural Language Processing |
onnx |
FP16-INT8 |
|||
bert-large-cased |
Natural Language Processing |
onnx |
FP32 |
|||
bert-large-uncased-whole-word-masking-squad-0001 |
Natural Language Processing |
onnx |
FP16 |
|||
bert-large-uncased-whole-word-masking-squad-0001 |
Natural Language Processing |
onnx |
FP32 |
|||
bert-large-uncased-whole-word-masking-squad-emb-0001 |
Natural Language Processing |
onnx |
FP32 |
|||
bert-large-uncased-whole-word-masking-squad-int8-0001 |
Natural Language Processing |
onnx |
FP16-INT8 |
|||
bert-small-uncased-whole-word-masking-squad-0001 |
Natural Language Processing |
onnx |
FP32 |
|||
bert-small-uncased-whole-word-masking-squad-0002 |
Natural Language Processing |
onnx |
FP16 |
|||
bert-small-uncased-whole-word-masking-squad-0002 |
Natural Language Processing |
onnx |
FP32 |
|||
bert-small-uncased-whole-word-masking-squad-emb-int8-0001 |
Natural Language Processing |
onnx |
FP16-INT8 |
|||
bert-small-uncased-whole-word-masking-squad-int8-0002 |
Natural Language Processing |
onnx |
FP16-INT8 |
|||
brain-tumor-segmentation-0002 |
Image Classification |
onnx |
FP16 |
|||
brain-tumor-segmentation-0002 |
Image Classification |
onnx |
FP16-INT8 |
|||
clip-vit-b-16-plus-240-laion400m-e32 |
dual use |
onnx |
FP16 |
|||
clip-vit-b-16-plus-240-laion400m-e32 |
dual use |
onnx |
FP32 |
|||
colorization-siggraph |
Colorization |
onnx |
FP16 |
|||
colorization-siggraph |
Colorization |
onnx |
FP32 |
|||
colorization-v2 |
Colorization |
onnx |
FP16-INT8 |
|||
common-sign-language-0001 |
Image Classification |
onnx |
FP16 |
|||
common-sign-language-0001 |
Image Classification |
onnx |
FP32 |
|||
common-sign-language-0002 |
Image Classification |
onnx |
FP16 |
|||
common-sign-language-0002 |
Image Classification |
onnx |
FP16-INT8 |
|||
common-sign-language-0002 |
Image Classification |
onnx |
FP32 |
|||
convnext-tiny |
Vision Transformer |
onnx |
FP16 |
|||
convnext-tiny |
Vision Transformer |
onnx |
FP32 |
|||
corel_nnart_001 |
onnx |
FP16-INT8 |
||||
ctdet_coco_dlav0_512 |
Object Detection |
onnx |
FP16 |
|||
ctdet_coco_dlav0_512 |
Object Detection |
onnx |
FP16-INT8 |
|||
ctdet_coco_dlav0_512 |
Object Detection |
onnx |
FP32 |
|||
deblurgan-v2 |
Image Motion Deblurring |
onnx |
FP16 |
|||
deblurgan-v2 |
Image Motion Deblurring |
onnx |
FP32 |
|||
deeplabv3-mobilenetv3 |
Semantic Image Segmentation |
onnx |
FP16-INT8 |
|||
deeplabv3-mobilenetv3 |
Semantic Image Segmentation |
onnx |
FP16 |
|||
deeplabv3-mobilenetv3 |
Semantic Image Segmentation |
onnx |
FP32 |
|||
deit-b |
Image Classification Transformer |
onnx |
FP16 |
|||
densenet-121 |
Image Classification |
onnx |
FP16 |
|||
densenet-121 |
Image Classification |
onnx |
FP32 |
|||
densenet-161 |
Image Classification |
onnx |
FP16 |
|||
densenet-161 |
Image Classification |
onnx |
FP16-INT8 |
|||
detr_resnet50 |
Object Detection |
onnx |
FP16 |
|||
detr_resnet50 |
Object Detection |
onnx |
FP32 |
|||
distilbert-base-cased |
Natural Language Processing |
onnx |
FP16 |
|||
distilbert-base-cased |
Natural Language Processing |
onnx |
FP32 |
|||
distilbert-base-uncased |
Natural Language Processing |
onnx |
FP16 |
|||
distilbert-base-uncased |
Natural Language Processing |
onnx |
FP16-INT8 |
|||
distilbert-base-uncased |
Natural Language Processing |
onnx |
FP32 |
|||
distilbert-base-uncased-sst-2 |
Natural Language Processing |
onnx |
FP16-INT8 |
|||
distilbert-base-uncased-sst-2 |
Natural Language Processing |
onnx |
FP32 |
|||
distilbert-base-uncased-sst-2 |
Natural Language Processing |
onnx |
FP16 |
|||
dla-34 |
Image Classification |
onnx |
FP16 |
|||
dla-34 |
Image Classification |
onnx |
FP16-INT8 |
|||
dna_r9.4.1 |
DNA Classification |
onnx |
FP32 |
|||
DNA Classification |
onnx |
FP16 |
||||
DNA Classification |
onnx |
FP32 |
||||
dna_r9.4.1_2d |
DNA Classification |
onnx |
FP16 |
|||
dna_r9.4.1_2d |
DNA Classification |
onnx |
FP16-INT8 |
|||
dna_r9.4.1_2d |
DNA Classification |
onnx |
FP32 |
|||
dpn-68 |
Image Classification, Dual Path Network |
onnx |
FP16 |
|||
dpn-68 |
Image Classification, Dual Path Network |
onnx |
FP16-INT8 |
|||
dpn-68 |
Image Classification, Dual Path Network |
onnx |
FP32 |
|||
drn-d-38 |
Semantic Image Segmentation |
onnx |
FP16 |
|||
ebgan |
Image Processing, Enhancement |
onnx |
FP16 |
|||
ebgan |
Image Processing, Enhancement |
onnx |
FP32 |
|||
edsr3-nas |
Image Processing, Enhancement |
onnx |
FP32 |
|||
edsr3-nas |
Image Processing, Enhancement |
onnx |
FP16 |
|||
efficientnet-b0 |
Object Detection |
onnx |
FP16 |
|||
efficientnet-b0 |
Object Detection |
onnx |
FP32 |
|||
efficientnet-b0 |
Object Detection |
onnx |
FP16-INT8 |
|||
efficientnet-v2-m |
Object Detection |
onnx |
FP16 |
|||
efficientnet-v2-m |
Object Detection |
onnx |
FP16-INT8 |
|||
efficientnet-v2-m |
Object Detection |
onnx |
FP32 |
|||
esrgan |
Image Processing, Enhancement |
onnx |
FP32 |
|||
esrgan |
Image Processing, Enhancement |
onnx |
FP16 |
|||
f3net |
Object Detection |
onnx |
FP32 |
|||
f3net |
Object Detection |
onnx |
FP16 |
|||
f3net |
Object Detection |
onnx |
FP16-INT8 |
|||
face-detection-0200 |
Object Detection |
onnx |
FP16 |
|||
face-detection-0202 |
Object Detection |
onnx |
FP16 |
|||
face-detection-0202 |
Object Detection |
onnx |
FP32 |
|||
face-detection-0204 |
Object Detection |
onnx |
FP16 |
|||
face-detection-0205 |
Object Detection |
onnx |
FP16 |
|||
face-detection-0205 |
Object Detection |
onnx |
FP32 |
|||
face-detection-0206 |
Object Detection |
onnx |
FP16 |
|||
face-detection-0206 |
Object Detection |
onnx |
FP16-INT8 |
|||
face-detection-retail-0005 |
Object Detection |
onnx |
FP16 |
|||
face-detection-retail-0005 |
Object Detection |
onnx |
FP16-INT8 |
|||
face-detection-retail-0005 |
Object Detection |
onnx |
FP32 |
|||
face-recognition-resnet100-arcface |
Object Detection |
onnx |
FP16 |
|||
face-recognition-resnet100-arcface |
Object Detection |
onnx |
FP16-INT8 |
|||
face-reidentification-retail-0095 |
Object Detection |
onnx |
FP16-INT8 |
|||
face-reidentification-retail-0095 |
Object Detection |
onnx |
FP16 |
|||
faceboxes |
Object Detection |
onnx |
FP16-INT8 |
|||
faceboxes |
Object Detection |
onnx |
FP32 |
|||
faceboxes |
Object Detection |
onnx |
FP16 |
|||
facenet |
Object Detection |
onnx |
FP16 |
|||
facenet |
Object Detection |
onnx |
FP16-INT8 |
|||
facenet |
Object Detection |
onnx |
FP32 |
|||
facial-landmarks-98-detection-0001 |
Object Detection |
onnx |
FP16 |
|||
facial-landmarks-98-detection-0001 |
Object Detection |
onnx |
FP32 |
|||
faster_rcnn_resnet50_fpn_coco |
Object Detection |
onnx |
FP16 |
|||
faster_rcnn_resnet50_fpn_coco |
Object Detection |
onnx |
FP16-INT8 |
|||
faster_rcnn_resnet50_fpn_coco |
Object Detection |
onnx |
FP32 |
|||
fastseg-large |
Semantic Segmentation |
onnx |
FP16 |
|||
fastseg-large |
Semantic Segmentation |
onnx |
FP32 |
|||
fastseg-small |
Semantic Segmentation |
onnx |
FP16 |
|||
fastseg-small |
Semantic Segmentation |
onnx |
FP16-INT8 |
|||
fastseg-small |
Semantic Segmentation |
onnx |
FP32 |
|||
fbcnn |
Image Processing, Enhancement |
onnx |
FP16-INT8 |
|||
fbcnn |
Image Processing, Enhancement |
onnx |
FP32 |
|||
fbnetc-100 |
Image Classification |
onnx |
FP16-INT8 |
|||
fbnetc-100 |
Image Classification |
onnx |
FP32 |
|||
fbnetc-100 |
Image Classification |
onnx |
FP16 |
|||
forward-tacotron-duration-prediction |
Text-to-Speech |
onnx |
FP16 |
|||
forward-tacotron-duration-prediction |
Text-to-Speech |
onnx |
FP32 |
|||
forward-tacotron-regression |
Text-to-Speech |
onnx |
FP16 |
|||
forward-tacotron-regression |
Text-to-Speech |
onnx |
FP16-INT8 |
|||
gaze-estimation-adas-0002 |
Object Detection |
onnx |
FP16 |
|||
googlenet-v3 |
Image Classification |
onnx |
FP16 |
|||
googlenet-v3 |
Image Classification |
onnx |
FP16-INT8 |
|||
gpt2-wikitext2-int8-onnx-0001 |
Large Language Model |
onnx |
FP16-INT8 |
|||
handwritten-english-recognition-0001 |
Text Detection |
onnx |
FP16 |
|||
handwritten-english-recognition-0001 |
Text Detection |
onnx |
FP32 |
|||
handwritten-japanese-recognition-0001 |
Text Detection |
onnx |
FP16-INT8 |
|||
handwritten-simplified-chinese-recognition-0001 |
Text Detection |
onnx |
FP16 |
|||
handwritten-simplified-chinese-recognition-0001 |
Text Detection |
onnx |
FP32 |
|||
hbonet-0.25 |
Image Classification |
onnx |
FP16 |
|||
hbonet-0.25 |
Image Classification |
onnx |
FP32 |
|||
hbonet-0.5 |
Image Classification |
onnx |
FP16 |
|||
hbonet-0.5 |
Image Classification |
onnx |
FP16-INT8 |
|||
hbonet-0.5 |
Image Classification |
onnx |
FP32 |
|||
hbonet-1.0 |
Image Classification |
onnx |
FP16 |
|||
hbonet-1.0 |
Image Classification |
onnx |
FP16-INT8 |
|||
hg-s8-b1-mpii |
Object Detection |
onnx |
FP16-INT8 |
|||
hg-s8-b1-mpii |
Object Detection |
onnx |
FP16 |
|||
higher-hrnet-w32-512 |
Object Detection |
onnx |
FP16 |
|||
higher-hrnet-w32-512 |
Object Detection |
onnx |
FP32 |
|||
horizontal-text-detection-0001 |
Text Detection |
onnx |
FP16 |
|||
horizontal-text-detection-0001 |
Text Detection |
onnx |
FP16-INT8 |
|||
horizontal-text-detection-0001 |
Text Detection |
onnx |
FP32 |
|||
hrnet-v2-c1-segmentation |
Semantic Segmentation |
onnx |
FP16-INT8 |
|||
human-pose-estimation-0002 |
Object Detection |
onnx |
FP16 |
|||
human-pose-estimation-0002 |
Object Detection |
onnx |
FP32 |
|||
human-pose-estimation-0003 |
Object Detection |
onnx |
FP16 |
|||
human-pose-estimation-0003 |
Object Detection |
onnx |
FP32 |
|||
human-pose-estimation-0004 |
Object Detection |
onnx |
FP16 |
|||
human-pose-estimation-0005 |
Object Detection |
onnx |
FP32 |
|||
human-pose-estimation-0006 |
Object Detection |
onnx |
FP16 |
|||
human-pose-estimation-0007 |
Object Detection |
onnx |
FP16 |
|||
human-pose-estimation-3d-0001 |
Object Detection |
onnx |
FP32 |
|||
human-pose-estimation-3d-0001 |
Object Detection |
onnx |
FP16 |
|||
inceptionv3-int8-onnx-0001 |
Image Classification |
onnx |
FP16-INT8 |
|||
instance-segmentation-person-0007 |
Instance Segmentation |
onnx |
FP32 |
|||
instance-segmentation-security-0002 |
Instance Segmentation |
onnx |
FP16 |
|||
instance-segmentation-security-0010 |
Instance Segmentation |
onnx |
FP32 |
|||
instance-segmentation-security-0050 |
Instance Segmentation |
onnx |
FP16 |
|||
instance-segmentation-security-0050 |
Instance Segmentation |
onnx |
FP32 |
|||
instance-segmentation-security-0228 |
Instance Segmentation |
onnx |
FP16 |
|||
instance-segmentation-security-1025 |
Instance Segmentation |
onnx |
FP32 |
|||
instance-segmentation-security-1039 |
Instance Segmentation |
onnx |
FP16 |
|||
iseebetter |
Video Super-Resolution |
onnx |
FP16 |
|||
iseebetter |
Video Super-Resolution |
onnx |
FP32 |
|||
landmarks-regression-retail-0009 |
Object Detection |
onnx |
FP16-INT8 |
|||
levit-128s |
Image Classification |
onnx |
FP16-INT8 |
|||
lraspp-mobilenet-v3-large |
Semantic Segmentation |
onnx |
FP16 |
|||
lraspp-mobilenet-v3-large |
Semantic Segmentation |
onnx |
FP16-INT8 |
|||
lraspp-mobilenet-v3-large |
Semantic Segmentation |
onnx |
FP32 |
|||
machine-translation-nar-de-en-0001 |
Natural Language Processing |
onnx |
FP16 |
|||
machine-translation-nar-de-en-0002 |
Natural Language Processing |
onnx |
FP16 |
|||
machine-translation-nar-en-de-0001 |
Natural Language Processing |
onnx |
FP16 |
|||
machine-translation-nar-en-de-0002 |
Natural Language Processing |
onnx |
FP16 |
|||
machine-translation-nar-en-ru-0002 |
Natural Language Processing |
onnx |
FP16 |
|||
machine-translation-nar-en-ru-0002 |
Natural Language Processing |
onnx |
FP32 |
|||
machine-translation-nar-ru-en-0002 |
Natural Language Processing |
onnx |
FP16 |
|||
machine-translation-nar-ru-en-0002 |
Natural Language Processing |
onnx |
FP16-INT8 |
|||
midasnet |
Monodepth |
onnx |
FP16 |
|||
midasnet |
Monodepth |
onnx |
FP16-INT8 |
|||
mlp-mixer-b16-224-miil |
Image Classification |
onnx |
FP16 |
|||
mlp-mixer-b16-224-miil |
Image Classification |
onnx |
FP16-INT8 |
|||
mlp-mixer-b16-224-miil |
Image Classification |
onnx |
FP32 |
|||
mnasnet-0.5 |
Image Classification |
onnx |
FP16 |
|||
mobilebert |
Natural Language Processing |
onnx |
FP16-INT8 |
|||
mobilenet-v2 |
Object Detection |
onnx |
FP16 |
|||
mobilenet-v2 |
Object Detection |
onnx |
FP16-INT8 |
|||
mobilenet-v2 |
Object Detection |
onnx |
FP32 |
|||
mobilenet-v3-large-1.0-224 |
Object Detection |
onnx |
FP16 |
|||
mobilenet-v3-large-1.0-224 |
Object Detection |
onnx |
FP16-INT8 |
|||
mobilenet-v3-large-1.0-224 |
Object Detection |
onnx |
FP32 |
|||
mobilenet-v3-small-1.0-224 |
Object Detection |
onnx |
FP16 |
|||
mobilenet-v3-small-1.0-224 |
Object Detection |
onnx |
FP16-INT8 |
|||
mobilenet-v3-small-1.0-224 |
Object Detection |
onnx |
FP32 |
|||
mobilenetv2-int8-onnx-0001 |
Object Detection |
onnx |
FP16-INT8 |
|||
modnet_photographic_portrait_matting |
Background Matting |
onnx |
FP16 |
|||
modnet_photographic_portrait_matting |
Background Matting |
onnx |
FP32 |
|||
modnet_webcam_portrait_matting |
Background Matting |
onnx |
FP16-INT8 |
|||
modnet_webcam_portrait_matting |
Background Matting |
onnx |
FP32 |
|||
nanodet-m-1.5x-416 |
Object Detection |
onnx |
FP16 |
|||
nanodet-m-1.5x-416 |
Object Detection |
onnx |
FP32 |
|||
nanodet-m-1.5x-416 |
Object Detection |
onnx |
FP16-INT8 |
|||
nfnet-f0 |
Image Classification |
onnx |
FP16 |
|||
nfnet-f0 |
Image Classification |
onnx |
FP16-INT8 |
|||
nfnet-f0 |
Image Classification |
onnx |
FP32 |
|||
open-closed-eye-0001 |
Image Classification |
onnx |
FP16-INT8 |
|||
open-closed-eye-0001 |
Image Classification |
onnx |
FP16 |
|||
open-closed-eye-0001 |
Image Classification |
onnx |
FP32 |
|||
person-attributes-recognition-crossroad-0230 |
Object Detection |
onnx |
FP16 |
|||
person-attributes-recognition-crossroad-0234 |
Object Detection |
onnx |
FP16 |
|||
person-attributes-recognition-crossroad-0238 |
Object Detection |
onnx |
FP16 |
|||
person-attributes-recognition-crossroad-0238 |
Object Detection |
onnx |
FP16-INT8 |
|||
person-detection-0100 |
Object Detection |
onnx |
FP32 |
|||
person-detection-0100 |
Object Detection |
onnx |
FP16 |
|||
person-detection-0101 |
Object Detection |
onnx |
FP16 |
|||
person-detection-0101 |
Object Detection |
onnx |
FP32 |
|||
person-detection-0102 |
Object Detection |
onnx |
FP16 |
|||
person-detection-0200 |
Object Detection |
onnx |
FP16 |
|||
person-detection-0201 |
Object Detection |
onnx |
FP16 |
|||
person-detection-0201 |
Object Detection |
onnx |
FP32 |
|||
person-detection-0202 |
Object Detection |
onnx |
FP16 |
|||
person-detection-0202 |
Object Detection |
onnx |
FP32 |
|||
person-detection-0203 |
Object Detection |
onnx |
FP16 |
|||
person-detection-0203 |
Object Detection |
onnx |
FP16-INT8 |
|||
person-detection-0301 |
Object Detection |
onnx |
FP16 |
|||
person-detection-0301 |
Object Detection |
onnx |
FP32 |
|||
person-detection-0302 |
Object Detection |
onnx |
FP16 |
|||
person-detection-0303 |
Object Detection |
onnx |
FP16 |
|||
person-detection-asl-0001 |
Object Detection |
onnx |
FP32 |
|||
person-reidentification-retail-0277 |
Object Detection |
onnx |
FP16 |
|||
person-reidentification-retail-0286 |
Object Detection |
onnx |
FP16 |
|||
person-reidentification-retail-0287 |
Object Detection |
onnx |
FP16-INT8 |
|||
person-reidentification-retail-0288 |
Object Detection |
onnx |
FP16 |
|||
person-reidentification-retail-0288 |
Object Detection |
onnx |
FP32 |
|||
person-vehicle-bike-detection-2000 |
Object Detection |
onnx |
FP16 |
|||
person-vehicle-bike-detection-2001 |
Object Detection |
onnx |
FP16 |
|||
person-vehicle-bike-detection-2001 |
Object Detection |
onnx |
FP32 |
|||
person-vehicle-bike-detection-2003 |
Object Detection |
onnx |
FP16 |
|||
person-vehicle-bike-detection-2003 |
Object Detection |
onnx |
FP32 |
|||
person-vehicle-bike-detection-2004 |
Object Detection |
onnx |
FP16 |
|||
person-vehicle-bike-detection-2004 |
Object Detection |
onnx |
FP32 |
|||
product-detection-0001 |
Object Detection |
onnx |
FP32 |
|||
product-detection-0001 |
Object Detection |
onnx |
FP16 |
|||
product-detection-0001 |
Object Detection |
onnx |
FP16-INT8 |
|||
pspnet-pytorch |
Semantic Segmentation |
onnx |
FP16 |
|||
pspnet-pytorch |
Semantic Segmentation |
onnx |
FP16-INT8 |
|||
quartznet-15x5-en |
Speech Recognition |
onnx |
FP16 |
|||
quartznet-15x5-en |
Speech Recognition |
onnx |
FP16-INT8 |
|||
quartznet-15x5-en |
Speech Recognition |
onnx |
FP32 |
|||
rcan |
Image Processing, Enhancement |
onnx |
FP32 |
|||
regnetx-3.2gf |
Image Classification |
onnx |
FP16-INT8 |
|||
regnetx-3.2gf |
Image Classification |
onnx |
FP32 |
|||
regnetx-3.2gf |
Image Classification |
onnx |
FP16 |
|||
repvgg-a0 |
Image Classification |
onnx |
FP16 |
|||
repvgg-a0 |
Image Classification |
onnx |
FP32 |
|||
repvgg-b1 |
Image Classification |
onnx |
FP16 |
|||
repvgg-b3 |
Image Classification |
onnx |
FP16 |
|||
repvgg-b3 |
Image Classification |
onnx |
FP32 |
|||
resmlp-12-distilled-224 |
Image Classification |
onnx |
FP32 |
|||
resmlp-12-distilled-224 |
Image Classification |
onnx |
FP16-INT8 |
|||
resnest-50-pytorch |
Image Classification |
onnx |
FP16 |
|||
resnest-50-pytorch |
Image Classification |
onnx |
FP32 |
|||
resnest-50-pytorch |
Image Classification |
onnx |
FP16-INT8 |
|||
resnet-101 |
Image Classification |
onnx |
FP16 |
|||
resnet-101 |
Image Classification |
onnx |
FP32 |
|||
resnet-152 |
Image Classification |
onnx |
FP16 |
|||
resnet-152 |
Image Classification |
onnx |
FP32 |
|||
resnet-18 |
Image Classification |
onnx |
FP16 |
|||
resnet-18 |
Image Classification |
onnx |
FP16-INT8 |
|||
resnet-34-pytorch |
Image Classification |
onnx |
FP16 |
|||
resnet-34-pytorch |
Image Classification |
onnx |
FP32 |
|||
resnet-50 |
Image Classification |
onnx |
FP16-INT8 |
|||
resnet-50 |
Image Classification |
onnx |
FP32 |
|||
resnet-50 |
Image Classification |
onnx |
FP16 |
|||
resnet-50-pytorch |
Image Classification |
onnx |
FP16 |
|||
resnet-50-pytorch |
Image Classification |
onnx |
FP16-INT8 |
|||
resnet-50-pytorch |
Image Classification |
onnx |
FP32 |
|||
resnet18-xnor-binary-onnx-0001 |
Image Classification |
onnx |
FP16-INT1 |
|||
resnet50-int8-onnx-0001 |
Image Classification |
onnx |
FP16-INT8 |
|||
resnext-101-32x8d |
Image Classification |
onnx |
FP16 |
|||
resnext-101-32x8d |
Image Classification |
onnx |
FP32 |
|||
resnext-50-32x4d |
Image Classification |
onnx |
FP16 |
|||
resnext-50-32x4d |
Image Classification |
onnx |
FP16-INT8 |
|||
resnext-50-32x4d |
Image Classification |
onnx |
FP32 |
|||
resnext101-32x16d-swsl |
Image Classification |
onnx |
FP16 |
|||
resnext101-32x16d-swsl |
Image Classification |
onnx |
FP16-INT8 |
|||
resnext101-32x16d-swsl |
Image Classification |
onnx |
FP32 |
|||
retinaface-resnet50 |
Image Classification |
onnx |
FP16-INT8 |
|||
retinaface-resnet50 |
Image Classification |
onnx |
FP32 |
|||
retinanet_resnet34 |
Image Classification |
onnx |
FP16-INT8 |
|||
retinanet_resnet34 |
Image Classification |
onnx |
FP32 |
|||
retinanet_resnet34 |
Image Classification |
onnx |
FP16 |
|||
rexnet-v1-x1.0 |
Image Classification |
onnx |
FP32 |
|||
rnnt |
Speech Recognition |
onnx |
FP16 |
|||
roberta-base |
Natural Language Processing |
onnx |
FP16 |
|||
roberta-base |
Natural Language Processing |
onnx |
FP16-INT8 |
|||
roberta-base |
Natural Language Processing |
onnx |
FP32 |
|||
roberta-base-mrpc |
Natural Language Processing |
onnx |
FP16-INT8 |
|||
roberta-large |
Natural Language Processing |
onnx |
FP16 |
|||
roberta-large |
Natural Language Processing |
onnx |
FP32 |
|||
sbert-base-mean-tokens |
Natural Language Processing |
onnx |
FP16 |
|||
sbert-base-mean-tokens |
Natural Language Processing |
onnx |
FP16-INT8 |
|||
sbert-base-mean-tokens |
Natural Language Processing |
onnx |
FP32 |
|||
se-resnext-50 |
Image Classification |
onnx |
FP16 |
|||
se-resnext-50 |
Image Classification |
onnx |
FP16-INT8 |
|||
shufflenet |
Image Classification |
onnx |
FP16-INT8 |
|||
shufflenet |
Image Classification |
onnx |
FP32 |
|||
shufflenet-v2-x0.5 |
Image Classification |
onnx |
FP16 |
|||
shufflenet-v2-x1.0 |
Image Classification |
onnx |
FP16-INT8 |
|||
shufflenet-v2-x1.0 |
Image Classification |
onnx |
FP32 |
|||
single-human-pose-estimation-0001 |
Object Detection |
onnx |
FP16 |
|||
single-human-pose-estimation-0001 |
Object Detection |
onnx |
FP32 |
|||
single-image-super-resolution-1032 |
Image Processing, Enhancement |
onnx |
FP16 |
|||
single-image-super-resolution-1032 |
Image Processing, Enhancement |
onnx |
FP32 |
|||
single-image-super-resolution-1033 |
Image Processing, Enhancement |
onnx |
FP16 |
|||
smartlab-object-detection-0001 |
Object Detection |
onnx |
FP16 |
|||
smartlab-object-detection-0001 |
Object Detection |
onnx |
FP32 |
|||
smartlab-object-detection-0003 |
Object Detection |
onnx |
FP16 |
|||
smartlab-object-detection-0003 |
Object Detection |
onnx |
FP32 |
|||
spnasnet-100 |
Image Classification |
onnx |
FP32 |
|||
spnasnet-100 |
Image Classification |
onnx |
FP16-INT8 |
|||
squeezenet1.0 |
Image Classification |
onnx |
FP16 |
|||
squeezenet1.0 |
Image Classification |
onnx |
FP16-INT8 |
|||
squeezenet1.0 |
Image Classification |
onnx |
FP32 |
|||
squeezenet1.1 |
Image Classification |
onnx |
FP16 |
|||
squeezenet1.1 |
Image Classification |
onnx |
FP32 |
|||
squeezenet1.1-pytorch1.2.0 |
Image Classification |
onnx |
FP16 |
|||
squeezenet1.1-pytorch1.2.0 |
Image Classification |
onnx |
FP16-INT8 |
|||
squeezenet1.1-pytorch1.2.0 |
Image Classification |
onnx |
FP32 |
|||
srgan |
Image Processing, Enhancement |
onnx |
FP16 |
|||
ssd-resnet34-1200 |
Object Detection |
onnx |
FP16 |
|||
ssd-resnet34-1200 |
Object Detection |
onnx |
FP16-INT8 |
|||
ssd-resnet34-1200 |
Object Detection |
onnx |
FP32 |
|||
ssd-vgg16 |
Object Detection |
onnx |
FP16 |
|||
ssd-vgg16 |
Object Detection |
onnx |
FP32 |
|||
ssd-vgg16 |
Object Detection |
onnx |
FP16-INT8 |
|||
ssd300-int8-onnx-0001 |
Object Detection |
onnx |
FP16-INT8 |
|||
ssd300-onnx-0001 |
Object Detection |
onnx |
FP16 |
|||
ssd300-onnx-0001 |
Object Detection |
onnx |
FP16-INT8 |
|||
style_transfer |
Image Processing |
onnx |
FP32 |
|||
style_transfer |
Image Processing |
onnx |
FP16 |
|||
style_transfer |
Image Processing |
onnx |
FP16-INT8 |
|||
swin-tiny-patch4-window7-224 |
Image Classification |
onnx |
FP16-INT8 |
|||
swin-tiny-patch4-window7-224 |
Image Classification |
onnx |
FP32 |
|||
t2t-vit-14 |
Image Classification |
onnx |
FP16 |
|||
t2t-vit-7 |
Image Classification |
onnx |
FP16 |
|||
t2t-vit-7 |
Image Classification |
onnx |
FP32 |
|||
text-image-super-resolution-0001 |
Image Processing, Enhancement |
onnx |
FP16 |
|||
text-image-super-resolution-0001 |
Image Processing, Enhancement |
onnx |
FP32 |
|||
text-recognition-0013 |
Text Detection |
onnx |
FP16 |
|||
text-recognition-0013 |
Text Detection |
onnx |
FP32 |
|||
text-recognition-0014 |
Text Detection |
onnx |
FP16 |
|||
text-recognition-0014 |
Text Detection |
onnx |
FP32 |
|||
text-recognition-resnet-fc |
Text Detection |
onnx |
FP16 |
|||
text-recognition-resnet-fc |
Text Detection |
onnx |
FP32 |
|||
time-series-forecasting-electricity-0001 |
Time-Series |
onnx |
FP16 |
|||
time-series-forecasting-electricity-0001 |
Time-Series |
onnx |
FP16-INT8 |
|||
tiny_yolo_v2 |
Object Detection |
onnx |
FP16 |
|||
tiny_yolo_v2 |
Object Detection |
onnx |
FP32 |
|||
tinybert_6layer_768dim_cola |
Natural Language Processing |
onnx |
FP16 |
|||
tinybert_6layer_768dim_cola |
Natural Language Processing |
onnx |
FP16-INT8 |
|||
tinybert_6layer_768dim_cola |
Natural Language Processing |
onnx |
FP32 |
|||
ultra-lightweight-face-detection-rfb-320 |
Object Detection |
onnx |
FP16 |
|||
ultra-lightweight-face-detection-slim-320 |
Object Detection |
onnx |
FP16 |
|||
ultra-lightweight-face-detection-slim-320 |
Object Detection |
onnx |
FP16-INT8 |
|||
unet-2d |
Semantic Segmentation |
onnx |
FP16 |
|||
unet-2d |
Semantic Segmentation |
onnx |
FP32 |
|||
unet-camvid-onnx-0001 |
Semantic Segmentation |
onnx |
FP16 |
|||
unet-camvid-onnx-0001 |
Semantic Segmentation |
onnx |
FP16-INT8 |
|||
unet-camvid-onnx-0001 |
Semantic Segmentation |
onnx |
FP32 |
|||
unet3d_mlperf |
Semantic Segmentation |
onnx |
FP16-INT8 |
|||
unet3d_mlperf |
Semantic Segmentation |
onnx |
FP16 |
|||
unet3d_mlperf |
Semantic Segmentation |
onnx |
FP32 |
|||
vehicle-detection-0200 |
Object Detection |
onnx |
FP16 |
|||
vehicle-detection-0200 |
Object Detection |
onnx |
FP32 |
|||
vehicle-detection-0201 |
Object Detection |
onnx |
FP16 |
|||
vehicle-detection-0201 |
Object Detection |
onnx |
FP32 |
|||
vehicle-detection-0202 |
Object Detection |
onnx |
FP16 |
|||
vehicle-detection-0202 |
Object Detection |
onnx |
FP32 |
|||
vehicle-reid-0001 |
Object Detection |
onnx |
FP16 |
|||
vfnet-resnet50-fpn-pytorch |
Object Detection |
onnx |
FP16 |
|||
vgg-16-bn |
Image Classification |
onnx |
FP16 |
|||
vgg-16-bn |
Image Classification |
onnx |
FP16-INT8 |
|||
vgg-16-bn |
Image Classification |
onnx |
FP32 |
|||
vgg16 |
Image Classification |
onnx |
FP16-INT8 |
|||
vgg16 |
Image Classification |
onnx |
FP32 |
|||
vgg16 |
Image Classification |
onnx |
FP16 |
|||
vgg19 |
Image Classification |
onnx |
FP16 |
|||
vgg19 |
Image Classification |
onnx |
FP32 |
|||
vit-base-16-224 |
Vision Transformer |
onnx |
FP16 |
|||
vit-base-16-224 |
Vision Transformer |
onnx |
FP32 |
|||
vitstr-small-patch16-224 |
Text Detection |
onnx |
FP16 |
|||
vitstr-small-patch16-224 |
Text Detection |
onnx |
FP32 |
|||
wav2vec2-base |
Speech Recognition |
onnx |
FP16-INT8 |
|||
wav2vec2-base |
Speech Recognition |
onnx |
FP32 |
|||
wavernn-rnn |
Text-to-Speech |
onnx |
FP16 |
|||
wavernn-rnn |
Text-to-Speech |
onnx |
FP32 |
|||
wavernn-upsampler |
Text-to-Speech |
onnx |
FP32 |
|||
wavernn-upsampler |
Text-to-Speech |
onnx |
FP16 |
|||
wdsr-small-x4 |
Image Processing, Enhancement |
onnx |
FP16 |
|||
wdsr-small-x4 |
Image Processing, Enhancement |
onnx |
FP16-INT8 |
|||
wdsr-small-x4 |
Image Processing, Enhancement |
onnx |
FP32 |
|||
weld-porosity-detection-0001 |
Image Classification |
onnx |
FP32 |
|||
weld-porosity-detection-0001 |
Image Classification |
onnx |
FP16 |
|||
weld-porosity-detection-0001 |
Image Classification |
onnx |
FP16-INT8 |
|||
wide-resnet-50-v2 |
Image Classification |
onnx |
FP16 |
|||
wide-resnet-50-v2 |
Image Classification |
onnx |
FP16-INT8 |
|||
wide-resnet-50-v2 |
Image Classification |
onnx |
FP32 |
|||
xlm-roberta-base |
Natural Language Processing |
onnx |
FP16 |
|||
xlm-roberta-base |
Natural Language Processing |
onnx |
FP32 |
|||
xlnet |
Transformer |
onnx |
FP16 |
|||
xlnet |
Transformer |
onnx |
FP16-INT8 |
|||
xlnet |
Transformer |
onnx |
FP32 |
|||
yolact-resnet50-fpn-pytorch |
Object Detection |
onnx |
FP16 |
|||
yolact-resnet50-fpn-pytorch |
Object Detection |
onnx |
FP32 |
|||
yolo_v2 |
Object Detection |
onnx |
FP16 |
|||
yolo_v2 |
Object Detection |
onnx |
FP32 |
|||
yolo_v3 |
Object Detection |
onnx |
FP16-INT8 |
|||
yolo_v3 |
Object Detection |
onnx |
FP32 |
|||
yolo_v3 |
Object Detection |
onnx |
FP16 |
|||
yolo_v3_tiny |
Object Detection |
onnx |
FP16-INT8 |
|||
yolo_v5l |
Object Detection |
onnx |
FP16 |
|||
yolo_v5l |
Object Detection |
onnx |
FP32 |
|||
yolo_v5m |
Object Detection |
onnx |
FP16 |
|||
yolo_v5m |
Object Detection |
onnx |
FP32 |
|||
yolo_v5m |
Object Detection |
onnx |
FP16-INT8 |
|||
yolo_v5m-v6 |
Object Detection |
onnx |
FP16 |
|||
yolo_v5m-v6 |
Object Detection |
onnx |
FP32 |
|||
yolo_v5m-v6 |
Object Detection |
onnx |
FP16-INT8 |
|||
yolo_v5m6-v6 |
Object Detection |
onnx |
FP16 |
|||
yolo_v5m6-v6 |
Object Detection |
onnx |
FP32 |
|||
yolo_v5s |
Object Detection |
onnx |
FP16 |
|||
yolo_v5s |
Object Detection |
onnx |
FP32 |
|||
yolo_v5s |
Object Detection |
onnx |
FP16-INT8 |
|||
yolo_v5s-v6 |
Object Detection |
onnx |
FP32 |
|||
yolo_v5s-v6 |
Object Detection |
onnx |
FP16 |
|||
yolo_v5s-v6 |
Object Detection |
onnx |
FP16-INT8 |
|||
yolo_v5x |
Object Detection |
onnx |
FP16 |
|||
yolo_v5x |
Object Detection |
onnx |
FP32 |
|||
yolo_v8n |
Object Detection |
onnx |
FP16 |
|||
yolo_v8n |
Object Detection |
onnx |
FP16-INT8 |
|||
yolo_v8n |
Object Detection |
onnx |
FP32 |
|||
yolof |
Object Detection |
onnx |
FP16 |
|||
yolof |
Object Detection |
onnx |
FP16-INT8 |
|||
yolor_p6 |
Object Detection |
onnx |
FP16 |
|||
yolor_p6 |
Object Detection |
onnx |
FP32 |
|||
yolor_p6 |
Object Detection |
onnx |
FP16-INT8 |
|||
yolox-tiny |
Object Detection |
onnx |
FP16 |
|||
yolox-tiny |
Object Detection |
onnx |
FP16-INT8 |
|||
yolox-tiny |
Object Detection |
onnx |
FP32 |