Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

MATLAB-Deep-Learning-Model-Hub

Discover pretrained models for deep learning in MATLAB
https://github.com/matlab-deep-learning/MATLAB-Deep-Learning-Model-Hub

Last synced: 2 days ago
JSON representation

  • Transformers (Text) <a name="transformers"/>

    • Robotics

      • BERT - deep-learning/transformer-models#bert-and-finbert) <br /> [Doc](https://www.mathworks.com/help/textanalytics/ref/bert.html) |
      • all-MiniLM-L6-v2 - text-analytics-toolbox-model-for-all-minilm-l6-v2-network) |
      • all-MiniLM-L12-v2 - text-analytics-toolbox-model-for-all-minilm-l12-v2-network) |
      • GPT-2 - 2 model is a decoder model used for text summarization.| 1.2GB |[GitHub](https://github.com/matlab-deep-learning/transformer-models#gpt-2) |![](Images/gpt2.png)|

  • Audio Embeddings <a name="AudioEmbeddings"/>

  • Application Specific Audio Models<a name="Application Specific Audio Models"/>

    • Robotics

      • vadnet - |[Doc](https://www.mathworks.com/help/audio/ref/vadnet.html) |<img src="Images/vadnet.png" width=150>|
      • YAMNet
      • CREPE - |[Doc](https://www.mathworks.com/help/audio/ref/crepe.html) |<img src="Images/pitch_estimation.png" width=150>|

  • Image Classification <a name="ImageClassification"/>

  • Semantic Segmentation <a name="SemanticSegmentation"/>

    • Robotics

      • U-net - raw-camera-processing-pipeline-using-deep-learning.html) | <img src="Images/rawimage.png" width=150>|
      • 3-D U-net - 3d-brain-tumor-using-deep-learning.html) | <img src="Images/Segment3DBrainTumor.gif" width=150>|
      • AdaptSeg (GAN) - D simulation data | 54.4 | [Doc](https://www.mathworks.com/help/deeplearning/ug/train-deep-learning-semantic-segmentation-network-using-3d-simulation-data.html) |<img src="Images/adaptSeg.png" width=150>|
      • DeepLabv3+ - deep-learning/pretrained-deeplabv3plus) |
      • segmentAnythingModel - started-with-segment-anything-model.html) |

  • Image Translation <a name="ImageTranslation"/>

    • Robotics

      • Pix2PixHD(CGAN) - image-from-segmentation-map-using-deep-learning.html) |<img src="Images/SynthesizeSegmentation.png" width=150> |
      • UNIT (GAN) - to-Dusk Dusk-to-Day Image Translation | 72.5 | [Doc](https://www.mathworks.com/help/images/unsupervised-day-to-dusk-image-translation-using-unit.html) |<img src="Images/day2dusk.png" width=150>|
      • UNIT (GAN) - medical-image-denoising-using-unit.html) |<img src="Images/unit_imagedenoising.png" width=150>|
      • CycleGAN - medical-image-denoising-using-cyclegan.html) |<img src="Images/cyclegan_imagedenoising.png" width=150>|
      • VDSR - resolution image from a low-resolution image) | 2.4 | [Doc](https://www.mathworks.com/help/images/single-image-super-resolution-using-deep-learning.html) |<img src="Images/SuperResolution.png" width=150>|

  • Model requests

  • Object Detection <a name="ObjectDetection"/>

    • Robotics

      • EfficientDet-D0 - deep-learning/pretrained-efficientdet-d0) |
      • YOLO v8 - deep-learning/Pretrained-YOLOv8-Network-For-Object-Detection)|
      • Spatial-CNN - deep-learning/pretrained-spatial-CNN)|<img src="Images/lanedetection.jpg" width=150>|
      • RESA - deep-learning/Pretrained-RESA-Network-For-Road-Boundary-Detection)|<img src="Images/road_boundary.png" width=150>|
      • YOLOX - s<br />YoloX-m<br />YoloX-l | 32 <br /> 90.2<br />192.9 | 39.8 <br />45.9<br />48.6|80 |[Doc](https://www.mathworks.com/help/vision/ref/yoloxobjectdetector.html)<br />[GitHub](https://github.com/matlab-deep-learning/Pretrained-YOLOX-Network-For-Object-Detection)|
      • YOLO v4 - coco <br /> yolov4-tiny-coco| 229 <br /> 21.5 | 44.2 <br />19.7|80 |[Doc](https://www.mathworks.com/help/vision/ref/yolov4objectdetector.html)<br />[GitHub](https://github.com/matlab-deep-learning/pretrained-yolo-v4)|
      • YOLO v3 - coco <br /> tiny-yolov3-coco | 220.4 <br /> 31.5 | 34.4 <br /> 9.3 |80 |[Doc](https://www.mathworks.com/help/vision/ref/yolov3objectdetector.html) |
      • YOLO v2 - COCO <br />tiny-yolo_v2-coco|181 <br /> 40 | 28.7 <br /> 10.5 |80 |[Doc](https://www.mathworks.com/help/vision/ref/yolov2objectdetector.html)<br />[GitHub](https://github.com/matlab-deep-learning/Object-Detection-Using-Pretrained-YOLO-v2)|
      • Single Shot Detector (SSD) - detection-using-single-shot-detector.html)|<img src="Images/ObjectDetectionUsingSSD.png" width=150>|
      • Faster R-CNN - detection-using-faster-r-cnn-deep-learning.html)|<img src="Images/faster_rcnn.png" width=150>|
      • YOLO v9 - deep-learning/Pretrained-Yolov9-Network-For-Object-Detection/)|

  • 3D Reconstruction <a name="3DReconstruction"/>

    • Robotics

      • NeRF - deep-learning/nerf)|![NeRF](Images/nerf.jpg) |

  • Text Detection and Recognition <a name="textdetection"/>

  • Speech to Text <a name="Speech2Text"/>

    • Robotics

  • Lidar <a name="PointCloud"/>

    • Robotics

      • SalsaNext - deep-learning/pretrained-salsanext)|
      • Complex YOLO v4 - yolov4) <br /> 21 (tiny-complex-yolov4) | 3 |[GitHub](https://github.com/matlab-deep-learning/Lidar-object-detection-using-complex-yolov4)|
      • PointNet - cloud-classification-using-pointnet-deep-learning.html)|
      • PointNet++ - lidar-segmentation-using-pointnet-network.html)|
      • PointSeg - cloud-classification-using-pointnet-deep-learning.html)|
      • SqueezeSegV2 - semantic-segmentation-using-squeezesegv2.html) |
      • PointPillars - detection-using-pointpillars-network.html)|

  • Pose Estimation <a name="PoseEstimation"/>

    • Robotics

      • HR Net - full-body-w32<br />human-full-body-w48 | 106.9<br />237.7 | [Doc](https://www.mathworks.com/help/vision/ref/hrnetobjectkeypointdetector.html) |
      • OpenPose - body-pose-using-deep-learning.html) |

  • Instance Segmentation <a name="InstanceSegmentation"/>

  • Video Classification <a name="VideoClassification"/>

    • Robotics

      • SlowFast - 3D |[Doc](https://www.mathworks.com/help/vision/ref/slowfastvideoclassifier.html)
      • R(2+1)D - 3D|[Doc](https://www.mathworks.com/help/vision/ref/r2plus1dvideoclassifier.html)
      • Inflated-3D

  • Manipulator Motion Planning <a name="ManipMotionPlanning"/>

  • Path Planning with Motion Planning Networks <a name="PathPlanningMPNet"/>

Programming Languages
MATLAB 12
Categories
Image Classification <a name="ImageClassification"/> 22 Object Detection <a name="ObjectDetection"/> 11 Lidar <a name="PointCloud"/> 7 Semantic Segmentation <a name="SemanticSegmentation"/> 5 Image Translation <a name="ImageTranslation"/> 5 Transformers (Text) <a name="transformers"/> 4 Model requests 3 Video Classification <a name="VideoClassification"/> 3 Audio Embeddings <a name="AudioEmbeddings"/> 3 Application Specific Audio Models<a name="Application Specific Audio Models"/> 3 Speech to Text <a name="Speech2Text"/> 2 Text Detection and Recognition <a name="textdetection"/> 2 Path Planning with Motion Planning Networks <a name="PathPlanningMPNet"/> 2 Pose Estimation <a name="PoseEstimation"/> 2 Instance Segmentation <a name="InstanceSegmentation"/> 1 Manipulator Motion Planning <a name="ManipMotionPlanning"/> 1 3D Reconstruction <a name="3DReconstruction"/> 1
Sub Categories
Robotics 76 Lidar 1
Keywords
matlab 13 deep-learning 12 pretrained-models 11 matlab-deep-learning 10 computer-vision 8 transfer-learning 5 object-detection 3 yolo 2 audio 2 speech-to-text 2 image-processing 2 lidar 2 lidar-object-detection 2 semantic-segmentation 2 lane-detector 1 lane-detection 1 lane 1 detected-lanes 1 lane-lines-detection 1 scnn 1 scnn-network 1 spatial-cnn 1 deeplearning 1 autonomous-driving 1 yolov8 1 efficientdet 1 image-classification 1 example 1 cifar10-classification 1 transformer 1 gpt2 1 gpt-2 1 finbert 1 bert 1 yolov4 1 tiny-yolov4 1 salsanext 1 pointcloud-3d-detection 1 pandaset 1 automated-driving 1 deployment 1 text-detection-recognition 1 text-detection 1 seven-segments-display 1 seven-segment 1 ocr-recognition 1 ocr 1 industrial-automation 1 nerf 1 3d-reconstruction 1