Supported Models#

This page lists models supported by Intel® DL Streamer.

Supported Architectures#

DL Streamer supports the following model architectures from GETI and major model hubs such as Ultralytics and Hugging Face.

The table provides links to model preparation instructions describing download and conversion steps that can be performed either manually or by using dedicated scripts.

Category Architecture Model Preparation Example Model Demo App
Anomaly Detection Padim GETI   GETI Deployment
STFPM
UFlow
Detection YOLOv5u Ultralytics Exporter yolov5nu.pt Object Detection and Classification with YOLO
YOLOv8 yolov8n.pt
YOLOv9 yolov9s.pt
YOLOv10 yolov10n.pt
YOLO11 yolo11n.pt
YOLO26 yolo26n.pt
YOLOE-26 Ultralytics Exporter yoloe-26n-seg.pt Prompt-based Object Detection
RTDetrForObjectDetection Optimum-onnx
+
OpenVINO ovc 		PekingU/rrtdetr_r50vd Smart Network Video Recorder for Lane Hogging Detection
RtDetrV2ForObjectDetection PekingU/rtdetr_v2_r18vd
ATSS with ResNet or MobilenetV2 GETI    
SSD with MobilenetV2
RT-DETR
YOLOX
D-Fine
CenterFace download_public_models.sh centerface.onnx Custom Post-Processing Library Sample - Classification
YOLOv7 download_public_models.sh
labels-file=coco_80cl.txt
model-proc=yolo-v7.json 		yolov7.pt Object Detection and Classification with YOLO
Emotion Recognition HSEmotion download_public_models.sh enet_b0_8_va_mtl.onnx Custom Post-Processing Library Sample - Classification
Feature Extraction Mars-small128 download_public_models.sh   Deep SORT Tracking
Image Classification ViTForImageClassification Optimum-Intel dima806/fairface_age_image_detection Face Detection and Classification
Mobilenet-V3 GETI    
EfficientNet-B0
DeitTiny
Image Embeddings CLIPModel CLIP ViT Conversion openai/clip-vit-large-patch14 Frame Embeddings
Instance Segmentation YOLOv8-seg Ultralytics Exporter yolov8n-seg.pt Object Detection and Classification with YOLO
YOLO11-seg yolo11n-seg.pt
YOLO26-seg yolo26n-seg.pt
MaskRCNN with EfficientNet, ResNet50, or Swin Transformer GETI    
RTMDet
Optical Character Recognition Paddle OCRv4 download_public_models.sh ch_PP-OCRv4_rec_infer License Plate Recognition Sample
Oriented Detection YOLOv8-obb Ultralytics Exporter yolov8n-obb.pt Object Detection and Classification with YOLO
YOLO11-obb yolo11n-obb.pt
YOLO26-obb yolo26n-obb.pt
Pose Estimation YOLOv8-pose Ultralytics Exporter yolov8n-pose.pt Object Detection and Classification with YOLO
YOLO11-pose yolo11n-pose.pt
YOLO26-pose yolo26n-pose.pt
Semantic Segmentation Lite-HRNet GETI    
SegNext
DinoV2
Speech Recognition WhisperForConditionalGeneration Optimum-Intel openai/whisper-tiny Audio Transcription
VLM InternVLChatModel Optimum-Intel OpenGVLab/InternVL2-1B Gvagenai Demo
LlavaForConditionalGeneration llava-hf/llava-1.5-7b-hf
LlavaQwen2ForCausalLM qnguyen3/nanoLLaVA
BunnyQwenForCausalLM qnguyen3/nanoLLaVA-1.5
LlavaNextForConditionalGeneration llava-hf/llava-v1.6-mistral-7b-hf
LlavaNextVideoForConditionalGeneration llava-hf/LLaVA-NeXT-Video-7B-hf
MiniCPMO openbmb/MiniCPM-o-2_6
MiniCPMV openbmb/MiniCPM-V-2_6
Phi3VForCausalLM microsoft/Phi-3-vision-128k-instruct
Phi4MMForCausalLM microsoft/Phi-4-multimodal-instruct
Qwen2VLForConditionalGeneration Qwen/Qwen2-VL-2B-Instruct
Qwen2_5_VLForConditionalGeneration Qwen/Qwen2.5-VL-3B-Instruct
Gemma3ForConditionalGeneration google/gemma-3-4b-it

OMZ Models#

The table below lists supported models from OpenVINO™ Open Model Zoo. These models can be downloaded using the download_omz_models.sh script:

Category Model Name labels-file model-proc Demo App
Action Recognition action-recognition-0001 kinetics_400.txt   Action Recognition Demo
driver-action-recognition-adas-0002 driver_actions.txt  
weld-porosity-detection-0001   weld-porosity-detection-0001.json
Classification anti-spoof-mn3   anti-spoof-mn3.json Interactive Face Detection Demo
densenet-121-tf imagenet_2012.txt preproc-aspect-ratio.json Classification Demo
dla-34
efficientnet-b0
efficientnet-b0-pytorch
efficientnet-v2-b0
efficientnet-v2-s
emotion-ferplus-8   emotion-ferplus-8.json  
googlenet-v1-tf imagenet_2012.txt preproc-aspect-ratio.json Classification Demo
googlenet-v2-tf imagenet_2012_bkgr.txt
googlenet-v3
googlenet-v3-pytorch imagenet_2012.txt
googlenet-v4-tf imagenet_2012_bkgr.txt
hbonet-0.25 imagenet_2012.txt
hbonet-1.0
inception-resnet-v2-tf imagenet_2012_bkgr.txt
mixnet-l imagenet_2012.txt
mobilenet-v1-0.25-128 imagenet_2012_bkgr.txt
mobilenet-v1-1.0-224-tf
mobilenet-v2-1.0-224
mobilenet-v2-1.4-224
mobilenet-v2-pytorch imagenet_2012.txt
mobilenet-v3-large-1.0-224-tf
mobilenet-v3-small-1.0-224-tf
mobilenetv2-7   mobilenetv2-7.json  
nfnet-f0 imagenet_2012.txt preproc-aspect-ratio.json Classification Demo
open-closed-eye-0001   open-closed-eye-0001.json Gaze Estimation Demo
regnetx-3.2gf imagenet_2012.txt preproc-aspect-ratio.json Classification Demo
repvgg-a0
repvgg-b1
repvgg-b3
resnest-50-pytorch
resnet-18-pytorch
resnet-34-pytorch
resnet-50-pytorch
resnet-50-tf imagenet_2012_bkgr.txt
resnet18-xnor-binary-onnx-0001   resnet18-xnor-binary-onnx-0001.json
resnet50-binary-0001   resnet50-binary-0001.json
rexnet-v1-x1.0 imagenet_2012.txt preproc-aspect-ratio.json
shufflenet-v2-x1.0
swin-tiny-patch4-window7-224
Detection efficientdet-d0-tf coco_91cl.txt   Object Detection Demo
efficientdet-d1-tf  
face-detection-0200   face-detection-0200.json
face-detection-0202   face-detection-0202.json
face-detection-0204   face-detection-0204.json
face-detection-0205   face-detection-0205.json
face-detection-0206   face-detection-0206.json
face-detection-adas-0001   face-detection-adas-0001.json
face-detection-retail-0004   face-detection-retail-0004.json
face-detection-retail-0005   face-detection-retail-0005.json
faster_rcnn_inception_resnet_v2_atrous_coco coco_91cl_bkgr.txt preproc-image-info.json
faster_rcnn_resnet50_coco
horizontal-text-detection-0001   horizontal-text-detection-0001.json Text Detection Demo
mobilenet-yolo-v4-syg   mobilenet-yolo-v4-syg.json Object Detection Demo
pedestrian-and-vehicle-detector-adas-0001   pedestrian-and-vehicle-detector-adas-0001.json
pedestrian-detection-adas-0002   pedestrian-detection-adas-0002.json
person-detection-0200   person-detection-0200.json
person-detection-0201   person-detection-0201.json
person-detection-0202   person-detection-0202.json
person-detection-0203   person-detection-0203.json
person-detection-asl-0001  
person-detection-retail-0013   person-detection-retail-0013.json
person-vehicle-bike-detection-2000   person-vehicle-bike-detection-2000.json
person-vehicle-bike-detection-2001   person-vehicle-bike-detection-2001.json
person-vehicle-bike-detection-2002   person-vehicle-bike-detection-2002.json
person-vehicle-bike-detection-2003   person-vehicle-bike-detection-2003.json
person-vehicle-bike-detection-2004   person-vehicle-bike-detection-2004.json
person-vehicle-bike-detection-crossroad-0078   person-vehicle-bike-detection-crossroad-0078.json
person-vehicle-bike-detection-crossroad-1016   person-vehicle-bike-detection-crossroad-1016.json
person-vehicle-bike-detection-crossroad-yolov3-1020   person-vehicle-bike-detection-crossroad-yolov3-1020.json
product-detection-0001   product-detection-0001.json
retinanet-tf coco_80cl.txt  
rfcn-resnet101-coco-tf coco_91cl_bkgr.txt preproc-image-info.json
ssd_mobilenet_v1_coco  
ssd_mobilenet_v1_fpn_coco  
ssdlite_mobilenet_v2  
torchvision.models.detection.ssdlite320_mobilenet_v3_large coco_80cl.txt    
vehicle-detection-0200   vehicle-detection-0200.json Object Detection Demo
vehicle-detection-0201   vehicle-detection-0201.json
vehicle-detection-0202   vehicle-detection-0202.json
vehicle-detection-adas-0002   vehicle-detection-adas-0002.json
vehicle-license-plate-detection-barrier-0106   vehicle-license-plate-detection-barrier-0106.json Security Barrier Camera Demo
vehicle-license-plate-detection-barrier-0123   vehicle-license-plate-detection-barrier-0123.json
yolo-v3-tf coco_80cl.txt yolo-v3-tf.json Object Detection Demo
yolo-v3-tiny-tf yolo-v3-tiny-tf.json
yolo-v4-tf yolo-v4-tf.json
yolo-v4-tiny-tf yolo-v4-tiny-tf.json
Head Pose Estimation head-pose-estimation-adas-0001     Gaze Estimation Demo
Human Pose Estimation human-pose-estimation-0001   human-pose-estimation-0001.json Multi Channel Human Pose Estimation Demo
single-human-pose-estimation-0001   single-human-pose-estimation-0001.json Single Human Pose Estimation Demo
Instance Segmentation instance-segmentation-person-0007     Background Subtraction Demo
instance-segmentation-security-0002 coco_80cl.txt  
instance-segmentation-security-0091  
instance-segmentation-security-0228  
instance-segmentation-security-1039  
instance-segmentation-security-1040  
mask_rcnn_inception_resnet_v2_atrous_coco   mask-rcnn.json Mask RCNN Demo
mask_rcnn_resnet50_atrous_coco  
Object Attributes age-gender-recognition-retail-0013   age-gender-recognition-retail-0013.json Interactive Face Detection Demo
emotions-recognition-retail-0003   emotions-recognition-retail-0003.json
facial-landmarks-35-adas-0002   facial-landmarks-35-adas-0002.json Gaze Estimation Demo
facial-landmarks-98-detection-0001   facial-landmarks-98-detection-0001.json Gaze Estimation Demo
landmarks-regression-retail-0009   landmarks-regression-retail-0009.json Face Recognition Demo
person-attributes-recognition-crossroad-0230   person-attributes-recognition-crossroad-0230.json Crossroad Camera Demo
person-attributes-recognition-crossroad-0234   person-attributes-recognition-crossroad-0234.json
person-attributes-recognition-crossroad-0238   person-attributes-recognition-crossroad-0238.json
vehicle-attributes-recognition-barrier-0039   vehicle-attributes-recognition-barrier-0039.json Security Barrier Camera Demo
vehicle-attributes-recognition-barrier-0042   vehicle-attributes-recognition-barrier-0042.json
Optical Character Recognition license-plate-recognition-barrier-0007   license-plate-recognition-barrier-0007.json Security Barrier Camera Demo
Sound Classification aclnet   aclnet.json Sound Classification Demo