Title: Synaptics AI Models | Edge AI for Developers
Open Graph Title: Synaptics AI Models | Edge AI for Developers
Description: Access pre-optimized AI models for Synaptics Astra Machina and Machina Micro Developer kits.
Open Graph Description: Access pre-optimized AI models for Synaptics Astra Machina and Machina Micro Developer kits.
Opengraph URL: https://developer.synaptics.com/models
Generator: Docusaurus v3.9.2
Domain: developer.synaptics.com
| twitter:card | summary_large_image |
| og:locale | en |
| og:locale:alternate | zh |
| docusaurus_locale | en |
| docusaurus_tag | default |
| docsearch:language | en |
| docsearch:docusaurus_tag | default |
Links:
| Skip to main content | https://developer.synaptics.com/models#__docusaurus_skipToContent_fallback |
| https://www.synaptics.com?utm_source=developer | |
| AI Developer Zone | https://developer.synaptics.com/ |
| Astra SL-Series | https://developer.synaptics.com/models |
| Overview | https://developer.synaptics.com/docs/sl/overview |
| SL2600 | https://developer.synaptics.com/docs/sl/sl2600/introduction |
| SL1600 | https://developer.synaptics.com/docs/sl/sl1600/getting-started/setup-astra |
| Astra SR-Series | https://developer.synaptics.com/models |
| Overview | https://developer.synaptics.com/docs/sr/introduction-sr |
| SR100 | https://developer.synaptics.com/docs/sr/sr100/quick-start |
| Blogs | https://developer.synaptics.com/blog |
| Models | https://developer.synaptics.com/models |
| Buy A Machina Kit | https://www.synaptics.com/products/embedded-processors/astra-machina-foundation-series?utm_source=developer#BuyEvaluationKit |
| English | https://developer.synaptics.com/models |
| English | https://developer.synaptics.com/models |
| 中文 | https://developer.synaptics.com/zh/models |
| Image ClassificationInception V4 299 QuantA quantized Inception V4 model optimized for image classification on ImageNet at 299x299 resolution. | https://developer.synaptics.com/docs/models/sl/sl1600/image_classification/imagenet/model/inception_v4_299/inception_v4_299_quant/ |
| Image ClassificationMobileNet V1 0.25 224 FloatA MobileNet V1 model with a 0.25 width multiplier optimized for image classification on ImageNet at 224x224 resolution. | https://developer.synaptics.com/docs/models/sl/sl1600/image_classification/imagenet/model/mobilenet_v1_0_25_224/mobilenet_v1_0_25_224_float/ |
| Image ClassificationMobileNet V1 0.25 224 QuantA quantized MobileNet V1 model with a 0.25 width multiplier optimized for image classification on ImageNet at 224x224 resolution. | https://developer.synaptics.com/docs/models/sl/sl1600/image_classification/imagenet/model/mobilenet_v1_0_25_224/mobilenet_v1_0_25_224_quant/ |
| Image ClassificationMobileNet V2 1.0 224 FloatA MobileNet V2 model with a 1.0 width multiplier optimized for image classification on ImageNet at 224x224 resolution. | https://developer.synaptics.com/docs/models/sl/sl1600/image_classification/imagenet/model/mobilenet_v2_1_0_224/mobilenet_v2_1_0_224_float/ |
| Image ClassificationMobileNet V2 1.0 224 QuantA quantized MobileNet V2 model with a 1.0 width multiplier optimized for image classification on ImageNet at 224x224 resolution. | https://developer.synaptics.com/docs/models/sl/sl1600/image_classification/imagenet/model/mobilenet_v2_1_0_224/mobilenet_v2_1_0_224_quant/ |
| Image ProcessingConvert NV12@1920x1080 to RGB@1920x1080A preprocessing model to convert NV12 formatted images from 1920x1080 resolution to RGB format at the same resolution. | https://developer.synaptics.com/docs/models/sl/sl1600/image_processing/preprocess/model/convert/clone_1920x1080/convert_nv12@1920x1080_rgb@1920x1080/ |
| Image ProcessingConvert NV12@1920x1080 to RGB@224x224A preprocessing model to convert NV12 formatted images from 1920x1080 resolution to RGB format at 224x224 resolution. | https://developer.synaptics.com/docs/models/sl/sl1600/image_processing/preprocess/model/convert/clone_224x224/convert_nv12@1920x1080_rgb@224x224/ |
| Image ProcessingConvert NV12@1920x1080 to RGB@640x360A preprocessing model to convert NV12 formatted images from 1920x1080 resolution to RGB format at 640x360 resolution. | https://developer.synaptics.com/docs/models/sl/sl1600/image_processing/preprocess/model/convert/clone_640x360/convert_nv12@1920x1080_rgb@640x360/ |
| Image ProcessingSR Fast Y UV 1280x720 to 3840x2160A fast super-resolution model converting YUV images from 1280x720 to 3840x2160 resolution. | https://developer.synaptics.com/docs/models/sl/sl1600/image_processing/super_resolution/model/fast_y_uv/sr_fast_y_uv_1280x720_3840x2160/ |
| Image ProcessingSR Fast Y UV 1920x1080 to 3840x2160A fast super-resolution model converting YUV images from 1920x1080 to 3840x2160 resolution. | https://developer.synaptics.com/docs/models/sl/sl1600/image_processing/super_resolution/model/fast_y_uv/sr_fast_y_uv_1920x1080_3840x2160/ |
| Image ProcessingSR QDEO Y UV 1280x720 to 3840x2160A QDEO-based super-resolution model converting YUV images from 1280x720 to 3840x2160 resolution. | https://developer.synaptics.com/docs/models/sl/sl1600/image_processing/super_resolution/model/qdeo_y_uv/sr_qdeo_y_uv_1280x720_3840x2160/ |
| Image ProcessingSR QDEO Y UV 1920x1080 to 3840x2160A QDEO-based super-resolution model converting YUV images from 1920x1080 to 3840x2160 resolution. | https://developer.synaptics.com/docs/models/sl/sl1600/image_processing/super_resolution/model/qdeo_y_uv/sr_qdeo_y_uv_1920x1080_3840x2160/ |
| Pose DetectionPoseNet MobileNet 0.75 FloatA PoseNet model using MobileNet architecture with 75% width multiplier for efficient body pose estimation. | https://developer.synaptics.com/docs/models/sl/sl1600/object_detection/body_pose/model/posenet_mobilenet_075/posenet_mobilenet_075_float/ |
| Pose DetectionPoseNet MobileNet 0.75 QuantA quantized PoseNet model using MobileNet architecture with 75% width multiplier for efficient and optimized body pose estimation. | https://developer.synaptics.com/docs/models/sl/sl1600/object_detection/body_pose/model/posenet_mobilenet_075/posenet_mobilenet_075_quant/ |
| Pose DetectionYOLOv8s PoseA YOLOv8s model specialized for body pose estimation, optimized for real-time applications. | https://developer.synaptics.com/docs/models/sl/sl1600/object_detection/body_pose/model/yolo_v8/yolov8s-pose/ |
| Object DetectionMobileNet224 Full80A MobileNet model optimized for object detection on the COCO dataset with full resolution at 224x224 and 80 classes. | https://developer.synaptics.com/docs/models/sl/sl1600/object_detection/coco/model/mobilenet224_full80/mobilenet224_full80/mobilenet224_full80/ |
| Object DetectionYOLOv5m 640x480A YOLOv5m model for object detection optimized for 640x480 resolution, offering a balance between speed and accuracy. | https://developer.synaptics.com/docs/models/sl/sl1600/object_detection/coco/model/yolo_v5/yolov5m-640x480/ |
| Object DetectionYOLOv5s 640x480A YOLOv5s model for object detection optimized for 640x480 resolution, suitable for real-time applications. | https://developer.synaptics.com/docs/models/sl/sl1600/object_detection/coco/model/yolo_v5/yolov5s-640x480/yolov5s-640x480/ |
| Object DetectionYOLOv5s Face 640x480 ONNX MQA YOLOv5s model specialized for face detection, optimized for 640x480 resolution using ONNX with mixed quantization. | https://developer.synaptics.com/docs/models/sl/sl1600/object_detection/face/model/yolov5s_face_640x480_onnx/yolov5s_face_640x480_onnx_mq/ |
| Object DetectionMobileNet224 Full1A lightweight MobileNet model optimized for people detection on high-resolution images. | https://developer.synaptics.com/docs/models/sl/sl1600/object_detection/people/model/mobilenet224_full1/mobilenet224_full1/mobilenet224_full1/ |
| Speech RecognitionMoonshine Tiny BF16A high-efficiency automatic speech recognition model using variable-length architecture for real-time speech recognition, optimized for 16kHz mono audio. | https://developer.synaptics.com/docs/models/sl/sl2600/ASR/moonshine/model/moonshine_tiny/moonshine_tiny_bf16/ |
| Image ClassificationMobileNet V2 224x224 INT8A quantized MobileNet V2 model with a 1.0 width multiplier optimized for image classification on ImageNet at 224x224 resolution. | https://developer.synaptics.com/docs/models/sl/sl2600/image_classification/imagenet/model/mobilenet_v2/mobilenet_v2_int8/ |
| LLMGemma3 270M ITA compact 270M parameter multimodal language model from Google optimized for text classification and data extraction tasks with rapid fine-tuning capability. | https://developer.synaptics.com/docs/models/sl/sl2600/llm/gemma3/model/gemma3_270M/gemma3_270M_it/ |
| Object DetectionYOLOv8n Nano 320x320 INT8A YOLOv8n model for object detection optimized for 320x320 resolution, offering a balance between speed and accuracy. | https://developer.synaptics.com/docs/models/sl/sl2600/object_detection/coco/model/yolo_v8/yolov8_nano/yolov8_nano_320_int8/ |
| Object DetectionYOLOv8s Small 320x320 INT8A YOLOv8s model for object detection optimized for 320x320 resolution, offering a balance between speed and accuracy. | https://developer.synaptics.com/docs/models/sl/sl2600/object_detection/coco/model/yolo_v8/yolov8_small/yolov8_small_320_int8/ |
| Image ClassificationPerson Classification 256x448 (SR100 Series)A Person Classification 256x448 model, developed by Synaptics, is a lightweight quantized `tflite` model developed for the SR100 processors. | https://developer.synaptics.com/docs/models/sr/sr100/sr100_person_classification_256x448/ |
| Image ClassificationPerson Classification 448x640 (SR100 Series)A Person Classification 448x640 model, developed by Synaptics, is a lightweight quantized `tflite` model developed for the SR100 processors. | https://developer.synaptics.com/docs/models/sr/sr100/sr100_person_classification_448x640/ |
| Object DetectionPerson Detection 256x480 (SR100 Series)A Person Detection 256x480 model, developed by Synaptics, is a lightweight quantized `tflite` model developed for the SR100 processors. | https://developer.synaptics.com/docs/models/sr/sr100/sr100_person_detection_256x480/ |
| Object DetectionPerson Detection 480x640 (SR100 Series)A Person Detection 480x640 model, developed by Synaptics, is a lightweight quantized `tflite` model developed for the SR100 processors. | https://developer.synaptics.com/docs/models/sr/sr100/sr100_person_detection_480x640/ |
| Pose DetectionPerson Pose Detection 256x480 (SR100 Series)A Person Pose Detection 256x480 model, developed by Synaptics, is a lightweight quantized `tflite` model developed for the SR100 processors. | https://developer.synaptics.com/docs/models/sr/sr100/sr100_person_pose_detection_256x480/ |
| Pose DetectionPerson Pose Detection 480x640 (SR100 Series)A Person Pose Detection 480x640 model, developed by Synaptics, is a lightweight quantized `tflite` model developed for the SR100 processors. | https://developer.synaptics.com/docs/models/sr/sr100/sr100_person_pose_detection_480x640/ |
| Image SegmentationPerson Segmentation 256x480 (SR100 Series)A Person Segmentation 256x480 model, developed by Synaptics, is a lightweight quantized `tflite` model developed for the SR100 processors. | https://developer.synaptics.com/docs/models/sr/sr100/sr100_person_segmentation_256x480/ |
| Image SegmentationPerson Segmentation 480x640 (SR100 Series)A Person Segmentation 480x640 model, developed by Synaptics, is a lightweight quantized `tflite` model developed for the SR100 processors. | https://developer.synaptics.com/docs/models/sr/sr100/sr100_person_segmentation_480x640/ |
| Astra SL SDK GitHub | https://github.com/synaptics-astra |
| Astra SL SDK Linux Docs | https://synaptics-astra.github.io/doc/ |
| Astra SL SDK Releases | https://github.com/synaptics-astra/sdk/releases |
| Astra SR SDK GitHub | https://synaptics-astra-mcu.github.io/doc/v/latest/ |
| Astra Support Portal | https://synacsm.atlassian.net/servicedesk/customer/portal/543 |
| Astra FAQ | https://synacsm.atlassian.net/servicedesk/customer/portal/543/topic/7f84fdc4-c401-461f-afed-238db48690f3 |
| Astra Machina Tutorial Videos - YouTube | https://www.youtube.com/watch?v=Tgsp8Y7pCy0&list=PLHXBLqX1DLNNSw5UkRIFRBZ-IPtLDaxJ8 |
Viewport: width=device-width,initial-scale=1