
API Reference
Quick search
code
Show Source
Install Tutorial API Community Contribute GitHub
gluoncv
Table Of Contents
  • Installation
  • Model Zookeyboard_arrow_down
    • Classification
    • Detection
    • Segmentation
    • Pose Estimation
    • Action Recognition
    • Depth Prediction
  • Apache MXNet Tutorialskeyboard_arrow_down
    • Image Classificationkeyboard_arrow_down
      • 1. Getting Started with Pre-trained Model on CIFAR10
      • 2. Dive Deep into Training with CIFAR10
      • 3. Getting Started with Pre-trained Models on ImageNet
      • 4. Transfer Learning with Your Own Image Dataset
      • 5. Train Your Own Model on ImageNet
    • Object Detectionkeyboard_arrow_down
      • 01. Predict with pre-trained SSD models
      • 02. Predict with pre-trained Faster RCNN models
      • 03. Predict with pre-trained YOLO models
      • 04. Train SSD on Pascal VOC dataset
      • 05. Deep dive into SSD training: 3 tips to boost performance
      • 06. Train Faster-RCNN end-to-end on PASCAL VOC
      • 07. Train YOLOv3 on PASCAL VOC
      • 08. Finetune a pretrained detection model
      • 09. Run an object detection model on your webcam
      • 10. Skip Finetuning by reusing part of pre-trained model
      • 11. Predict with pre-trained CenterNet models
      • 12. Run an object detection model on NVIDIA Jetson module
    • Instance Segmentationkeyboard_arrow_down
      • 1. Predict with pre-trained Mask RCNN models
      • 2. Train Mask RCNN end-to-end on MS COCO
    • Semantic Segmentationkeyboard_arrow_down
      • 1. Getting Started with FCN Pre-trained Models
      • 2. Test with PSPNet Pre-trained Models
      • 3. Test with DeepLabV3 Pre-trained Models
      • 4. Train FCN on Pascal VOC Dataset
      • 5. Train PSPNet on ADE20K Dataset
      • 6. Reproducing SoTA on Pascal VOC Dataset
      • 7. Test with ICNet Pre-trained Models for Multi-Human Parsing
    • Pose Estimationkeyboard_arrow_down
      • 1. Predict with pre-trained Simple Pose Estimation models
      • 2. Predict with pre-trained AlphaPose Estimation models
      • 3. Estimate pose from your webcam
      • 4. Dive deep into Training a Simple Pose Model on COCO Keypoints
    • Action Recognitionkeyboard_arrow_down
      • 1. Getting Started with Pre-trained TSN Models on UCF101
      • 10. Introducing Decord: an efficient video reader
      • 2. Dive Deep into Training TSN mdoels on UCF101
      • 3. Getting Started with Pre-trained I3D Models on Kinetcis400
      • 4. Dive Deep into Training I3D mdoels on Kinetcis400
      • 5. Getting Started with Pre-trained SlowFast Models on Kinetcis400
      • 6. Dive Deep into Training SlowFast mdoels on Kinetcis400
      • 7. Fine-tuning SOTA video models on your own dataset
      • 8. Extracting video features from pre-trained models
      • 9. Inference on your own videos using pre-trained models
    • Object Trackingkeyboard_arrow_down
      • 01. Single object tracking with pre-trained SiamRPN models
      • 02. Train SiamRPN on COCO、VID、DET、Youtube_bb
      • 03. Multiple object tracking with pre-trained SMOT models
    • Depth Predictionkeyboard_arrow_down
      • 01. Predict depth from a single image with pre-trained Monodepth2 models
      • 02. Predict depth from an image sequence or a video with pre-trained Monodepth2 models
      • 03. Monodepth2 training on KITTI dataset
      • 04. Testing PoseNet from image sequences with pre-trained Monodepth2 Pose models
    • Prepare Datasetskeyboard_arrow_down
      • Prepare ADE20K dataset.
      • Prepare COCO datasets
      • Prepare COCO datasets
      • Prepare Cityscapes dataset.
      • Prepare ILSVRC 2015 DET dataset
      • Prepare ILSVRC 2015 VId dataset
      • Prepare Multi-Human Parsing V1 dataset
      • Prepare OTB 2015 dataset
      • Prepare PASCAL VOC datasets
      • Prepare Youtube_bb dataset
      • Prepare custom datasets for object detection
      • Prepare the 20BN-something-something Dataset V2
      • Prepare the HMDB51 Dataset
      • Prepare the ImageNet dataset
      • Prepare the Kinetics400 dataset
      • Prepare the UCF101 dataset
      • Prepare your dataset in ImageRecord format
    • Auto Modulekeyboard_arrow_down
      • 01. Load web datasets with GluonCV Auto Module
      • 02. Train Image Classification with Auto Estimator
      • 03. Train classifier or detector with HPO using GluonCV Auto task
    • Distributed Trainingkeyboard_arrow_down
      • 1. Distributed training of deep video models
    • Deploymentkeyboard_arrow_down
      • 1. Export trained GluonCV network to JSON
      • 2. GluonCV C++ Inference Demo
      • 3. Inference with Quantized Models
  • PyTorch Tutorialskeyboard_arrow_down
    • Action Recognitionkeyboard_arrow_down
      • 1. Getting Started with Pre-trained I3D Models on Kinetcis400
      • 2. Fine-tuning SOTA video models on your own dataset
      • 3. Extracting video features from pre-trained models
      • 4. Computing FLOPS, latency and fps of a model
      • 5. DistributedDataParallel (DDP) Framework
  • API Referencekeyboard_arrow_down
    • gluoncv.data
    • gluoncv.data.batchify
    • gluoncv.data.transforms
    • gluoncv.model_zoo
    • gluoncv.nn
    • gluoncv.loss
    • gluoncv.utils
  • Communitykeyboard_arrow_down
    • Community
    • Contribute to GluonCV
  • Slides
gluoncv
Table Of Contents
  • Installation
  • Model Zookeyboard_arrow_down
    • Classification
    • Detection
    • Segmentation
    • Pose Estimation
    • Action Recognition
    • Depth Prediction
  • Apache MXNet Tutorialskeyboard_arrow_down
    • Image Classificationkeyboard_arrow_down
      • 1. Getting Started with Pre-trained Model on CIFAR10
      • 2. Dive Deep into Training with CIFAR10
      • 3. Getting Started with Pre-trained Models on ImageNet
      • 4. Transfer Learning with Your Own Image Dataset
      • 5. Train Your Own Model on ImageNet
    • Object Detectionkeyboard_arrow_down
      • 01. Predict with pre-trained SSD models
      • 02. Predict with pre-trained Faster RCNN models
      • 03. Predict with pre-trained YOLO models
      • 04. Train SSD on Pascal VOC dataset
      • 05. Deep dive into SSD training: 3 tips to boost performance
      • 06. Train Faster-RCNN end-to-end on PASCAL VOC
      • 07. Train YOLOv3 on PASCAL VOC
      • 08. Finetune a pretrained detection model
      • 09. Run an object detection model on your webcam
      • 10. Skip Finetuning by reusing part of pre-trained model
      • 11. Predict with pre-trained CenterNet models
      • 12. Run an object detection model on NVIDIA Jetson module
    • Instance Segmentationkeyboard_arrow_down
      • 1. Predict with pre-trained Mask RCNN models
      • 2. Train Mask RCNN end-to-end on MS COCO
    • Semantic Segmentationkeyboard_arrow_down
      • 1. Getting Started with FCN Pre-trained Models
      • 2. Test with PSPNet Pre-trained Models
      • 3. Test with DeepLabV3 Pre-trained Models
      • 4. Train FCN on Pascal VOC Dataset
      • 5. Train PSPNet on ADE20K Dataset
      • 6. Reproducing SoTA on Pascal VOC Dataset
      • 7. Test with ICNet Pre-trained Models for Multi-Human Parsing
    • Pose Estimationkeyboard_arrow_down
      • 1. Predict with pre-trained Simple Pose Estimation models
      • 2. Predict with pre-trained AlphaPose Estimation models
      • 3. Estimate pose from your webcam
      • 4. Dive deep into Training a Simple Pose Model on COCO Keypoints
    • Action Recognitionkeyboard_arrow_down
      • 1. Getting Started with Pre-trained TSN Models on UCF101
      • 10. Introducing Decord: an efficient video reader
      • 2. Dive Deep into Training TSN mdoels on UCF101
      • 3. Getting Started with Pre-trained I3D Models on Kinetcis400
      • 4. Dive Deep into Training I3D mdoels on Kinetcis400
      • 5. Getting Started with Pre-trained SlowFast Models on Kinetcis400
      • 6. Dive Deep into Training SlowFast mdoels on Kinetcis400
      • 7. Fine-tuning SOTA video models on your own dataset
      • 8. Extracting video features from pre-trained models
      • 9. Inference on your own videos using pre-trained models
    • Object Trackingkeyboard_arrow_down
      • 01. Single object tracking with pre-trained SiamRPN models
      • 02. Train SiamRPN on COCO、VID、DET、Youtube_bb
      • 03. Multiple object tracking with pre-trained SMOT models
    • Depth Predictionkeyboard_arrow_down
      • 01. Predict depth from a single image with pre-trained Monodepth2 models
      • 02. Predict depth from an image sequence or a video with pre-trained Monodepth2 models
      • 03. Monodepth2 training on KITTI dataset
      • 04. Testing PoseNet from image sequences with pre-trained Monodepth2 Pose models
    • Prepare Datasetskeyboard_arrow_down
      • Prepare ADE20K dataset.
      • Prepare COCO datasets
      • Prepare COCO datasets
      • Prepare Cityscapes dataset.
      • Prepare ILSVRC 2015 DET dataset
      • Prepare ILSVRC 2015 VId dataset
      • Prepare Multi-Human Parsing V1 dataset
      • Prepare OTB 2015 dataset
      • Prepare PASCAL VOC datasets
      • Prepare Youtube_bb dataset
      • Prepare custom datasets for object detection
      • Prepare the 20BN-something-something Dataset V2
      • Prepare the HMDB51 Dataset
      • Prepare the ImageNet dataset
      • Prepare the Kinetics400 dataset
      • Prepare the UCF101 dataset
      • Prepare your dataset in ImageRecord format
    • Auto Modulekeyboard_arrow_down
      • 01. Load web datasets with GluonCV Auto Module
      • 02. Train Image Classification with Auto Estimator
      • 03. Train classifier or detector with HPO using GluonCV Auto task
    • Distributed Trainingkeyboard_arrow_down
      • 1. Distributed training of deep video models
    • Deploymentkeyboard_arrow_down
      • 1. Export trained GluonCV network to JSON
      • 2. GluonCV C++ Inference Demo
      • 3. Inference with Quantized Models
  • PyTorch Tutorialskeyboard_arrow_down
    • Action Recognitionkeyboard_arrow_down
      • 1. Getting Started with Pre-trained I3D Models on Kinetcis400
      • 2. Fine-tuning SOTA video models on your own dataset
      • 3. Extracting video features from pre-trained models
      • 4. Computing FLOPS, latency and fps of a model
      • 5. DistributedDataParallel (DDP) Framework
  • API Referencekeyboard_arrow_down
    • gluoncv.data
    • gluoncv.data.batchify
    • gluoncv.data.transforms
    • gluoncv.model_zoo
    • gluoncv.nn
    • gluoncv.loss
    • gluoncv.utils
  • Communitykeyboard_arrow_down
    • Community
    • Contribute to GluonCV
  • Slides

API Reference¶

  • gluoncv.data
  • gluoncv.data.batchify
  • gluoncv.data.transforms
  • gluoncv.model_zoo
  • gluoncv.nn
  • gluoncv.loss
  • gluoncv.utils
Previous
5. DistributedDataParallel (DDP) Framework
Next
gluoncv.data