Model Garden provides a collection of state-of-the-art machine learning (ML) models for vision, text, and audio capabilities. These models are optimized for use with the Google Tensor SDK, letting you bring powerful AI features directly to your Pixel devices with seamless on-device performance.
Depth Estimation
| Model | License |
|---|---|
| depth_anything | Apache-2.0 |
| depth_anything_v2 | Apache-2.0 |
| midas_v2_1 | BSD-3-Clause |
Face Reconstruction
| Model | License |
|---|---|
| facemap_3dmm | BSD-3-Clause |
Image and text understanding
| Model | License |
|---|---|
| clip | MIT |
| mobileclip_image_encoder | MIT |
| mobileclip_text_encoder | MIT |
| tinyclip | MIT |
| trocr_decoder | MIT |
| trocr_encoder | MIT |
Image Classification
Image Segmentation
| Model | License |
|---|---|
| hrnet_w48_ocr | MIT |
| mediapipe_selfie | APACHE-2.0 |
| unet_segmentation | GPL-3.0 |
Image Super Resolution
| Model | License |
|---|---|
| esrgan | APACHE-2.0 |
Object Detection
| Model | License |
|---|---|
| 3d_deep_box | MIT |
| conditional_detr_resnet50 | Apache-2.0 |
| deformable_detr | Apache-2.0 |
| detr_resnet50 | Apache-2.0 |
| detr_resnet50_dc5 | Apache-2.0 |
| detr_resnet101 | Apache-2.0 |
| detr_resnet101_dc5 | Apache-2.0 |
| faceattribnet | AI-HUB-MODELS |
| lightweight_face_detection | AI-HUB-MODELS |
| mediapipe_face_detection | APACHE-2.0 |
| mediapipe_hand_detection | APACHE-2.0 |
| person_foot_detection | AI-HUB-MODELS |
| ppe_detection | AI-HUB-MODELS |
| rtdetr_r18vd | Apache-2.0 |
| rtmdet | Apache-2.0 |
| yolo_nas_m | Apache-2.0 |
| yolo_nas_s | Apache-2.0 |
| yolo_v4 | Apache-2.0 |
| yolo_v6 | GPL-3.0 |
| yolo_v7 | GPL-3.0 |
| yolos_tiny | APACHE-2.0 |
| yolox_tiny | APACHE-2.0 |
Optical Flow
| Model | License |
|---|---|
| raft_small | BSD-3-Clause |
Pose Estimation
| Model | License |
|---|---|
| hrnet_pose | MIT |
| lite_hrnet_pose | APACHE-2.0 |
| mediapipe_pose | APACHE-2.0 |
| movenet | MIT |
| posenet | Apache-2.0 |
| posenet_pose | Apache-2.0 |
| rtmpose_body2d | Apache-2.0 |
Question Answering
| Model | License |
|---|---|
| tinyroberta | CC-BY-4.0 |
Semantic Segmentation
| Model | License |
|---|---|
| bgnet | Apache-2.0 |
| bisenet | No license file |
| ddrnet23_slim | MIT |
| deeplabv3_mobilenet_v3_large | BSD-3-Clause |
| deeplabv3_plus_mobilenet | MIT |
| deeplabv3_resnet101 | BSD-3-Clause |
| deeplabv3_resnet50 | BSD-3-Clause |
| fcn_resnet50 | BSD-3-Clause |
| ffnet_122ns_lowres | BSD-3-Clause |
| ffnet_40s | BSD-3-Clause |
| ffnet_54s | BSD-3-Clause |
| ffnet_78s | BSD-3-Clause |
| ffnet_78s_lowres | BSD-3-Clause |
| isnet | Apache 2.0 |
| lraspp_mobilenet_v3_large | BSD-3-Clause |
| pidnet | MIT |
| sam_vit_b | APACHE-2.0 |
| sam_vit_l | APACHE-2.0 |
| segformer | NVIDIA-SCSL |
| segment_anything_model | Apache-2.0 |
| u2net_full | APACHE-2.0 |
| u2net_lite | APACHE-2.0 |
Speech Recognition
| Model | License |
|---|---|
| conformer | BSD-2-Clause |
| deepspeech | BSD-2-Clause |
| huggingface_wavlm_base_plus | Apache-2.0 |
| parakeet_ctc | Apache-2.0 |
| torchaudio_emformer_rnnt_base | BSD-2-Clause |
| wav2vec2_base_960h | APACHE-2.0 |
| whisper_base | MIT |
| whisper_medium | MIT |
| whisper_large_v2 | MIT |
| whisper_small | MIT |
| whisper_tiny | MIT |
Super Resolution
| Model | License |
|---|---|
| quicksrnet_large | BSD-3-Clause |
| quicksrnet_medium | BSD-3-Clause |
| quicksrnet_small | BSD-3-Clause |
| real_esrgan_general_x4v3 | BSD-3-Clause |
| real_esrgan_x4plus | BSD-3-Clause |
| xlsr | BSD-3-Clause |
| sesr_m5 | BSD-3-Clause |
Text Classification
| Model | License |
|---|---|
| distilbert | Apache-2.0 |
| mobilebert | Apache-2.0 |