Apache MXNet Tutorials ========= Interested in getting started in a new CV area? Here are some tutorials to help get started. Note: For image classification or object detection tasks, feel free to explore tutorials in `AutoGluon MultiModalPredictor `_ with better support in PyTorch. Image Classification -------------------- .. container:: cards .. card:: :title: Pre-trained Models on CIFAR10 :link: ../build/examples_classification/demo_cifar10.html Basics on how to use pretrained models on CIFAR10 and apply to real images .. card:: :title: Training on CIFAR10 :link: ../build/examples_classification/dive_deep_cifar10.html Hands on classification model training on CIFAR10 .. card:: :title: Pre-trained Models on ImageNet :link: ../build/examples_classification/demo_imagenet.html Basics on how to use pretrained models on ImageNet and apply to real images .. card:: :title: Transfer Learning with Your Own Dataset :link: ../build/examples_classification/transfer_learning_minc.html Train on your own dataset with ImageNet pre-trained models. .. card:: :title: Training on ImageNet :link: ../build/examples_classification/dive_deep_imagenet.html Hands on classification model training on ImageNet Object Detection ---------------- .. container:: cards .. card:: :title: Pre-trained SSD Models :link: ../build/examples_detection/demo_ssd.html Detect objects in real-world images with pre-trained SSD models .. card:: :title: Training SSD on Pascal VOC Dataset :link: ../build/examples_detection/train_ssd_voc.html Hands on SSD model training on Pascal VOC Dataset .. card:: :title: Tips for SSD Model Training :link: ../build/examples_detection/train_ssd_advanced.html Training tips to boost your SSD Model performance. .. card:: :title: Pre-trained Faster R-CNN Models :link: ../build/examples_detection/demo_faster_rcnn.html Detect objects in real-world images with pre-trained Faster R-CNN models .. card:: :title: Training Faster R-CNN on Pascal VOC :link: ../build/examples_detection/train_faster_rcnn_voc.html End-to-end Faster R-CNN Training on Pascal VOC .. card:: :title: Pre-trained YOLO Models :link: ../build/examples_detection/demo_yolo.html Detect objects in real-world images with pre-trained YOLO models .. card:: :title: Training YOLOv3 on Pascal VOC :link: ../build/examples_detection/train_yolo_v3.html Hands on YOLOv3 model training on Pascal VOC Dataset .. card:: :title: Finetune a Pre-trained Model :link: ../build/examples_detection/finetune_detection.html Finetune a pre-trained model on your own dataset. .. card:: :title: Object Detection from Webcam :link: ../build/examples_detection/demo_webcam.html Run an object detection model from your webcam. .. card:: :title: Skip Finetuning by reusing part of pre-trained model :link: ../build/examples_detection/skip_fintune.html .. card:: :title: Object Detection on NVIDIA Jetson module :link: ../build/examples_detection/demo_jetson.html Instance Segmentation --------------------- .. container:: cards .. card:: :title: Pre-trained Mask R-CNN Models :link: ../build/examples_instance/demo_mask_rcnn.html Perform instance segmentation on real-world images with pre-trained Mask R-CNN models .. card:: :title: Training Mask R-CNN on MS COCO :link: ../build/examples_instance/train_mask_rcnn_coco.html Hands on Mask R-CNN model training on MS COCO dataset Semantic Segmentation --------------------- .. container:: cards .. card:: :title: Pre-trained FCN Models :link: ../build/examples_segmentation/demo_fcn.html Perform semantic segmentation on real-world images with pre-trained FCN models .. card:: :title: Training FCN on Pascal VOC :link: ../build/examples_segmentation/train_fcn.html Hands on FCN model training on Pascal VOC dataset .. card:: :title: Pre-trained PSPNet Models :link: ../build/examples_segmentation/demo_psp.html Perform semantic segmentation in real-world images with pre-trained PSPNet models .. card:: :title: Training PSPNet on ADE20K :link: ../build/examples_segmentation/train_psp.html Hands on Mask R-CNN model training on ADE20K dataset .. card:: :title: Pre-trained DeepLabV3 Models :link: ../build/examples_segmentation/demo_deeplab.html Perform instance segmentation in real-world images with pre-trained DeepLabV3 models .. card:: :title: Getting SOTA Results on Pascal VOC :link: ../build/examples_segmentation/voc_sota.html Hands on DeepLabV3 model training on Pascal VOC dataset, and achieves state-of-the-art accuracy. .. card:: :title: Pre-trained ICNet Models for Multi-Human Parsing :link: ../build/examples_segmentation/demo_icnet.html Perform semantic segmentation on real-world images with pre-trained ICNet models Pose Estimation --------------------- .. container:: cards .. card:: :title: Pre-trained Simple Pose Models :link: ../build/examples_pose/demo_simple_pose.html Estimate human pose in real-world images with pre-trained Simple Pose models .. card:: :title: Pre-trained AlphaPose Models :link: ../build/examples_pose/demo_alpha_pose.html Estimate human pose in real-world images with pre-trained AlphaPose models .. card:: :title: Estimate pose from your webcam :link: ../build/examples_pose/cam_demo.html Estimate human pose from your webcam video stream .. card:: :title: Dive deep into Training a Simple Pose Model on COCO Keypoints :link: ../build/examples_pose/dive_deep_simple_pose.html Train a pose estimation model on the COCO dataset Action Recognition --------------------- .. container:: cards .. card:: :title: Pre-trained TSN Models on UCF101 :link: ../build/examples_action_recognition/demo_tsn_ucf101.html Recognize human actions in real-world videos with pre-trained TSN models .. card:: :title: Training TSN models on UCF101 :link: ../build/examples_action_recognition/dive_deep_tsn_ucf101.html Hands on TSN action recognition model training on UCF101 dataset .. card:: :title: Pre-trained I3D Models on Kinetics400 :link: ../build/examples_action_recognition/demo_i3d_kinetics400.html Recognize human actions in real-world videos with pre-trained I3D models .. card:: :title: Training I3D Models on Kinetics400 :link: ../build/examples_action_recognition/dive_deep_i3d_kinetics400.html Hands on I3D action recognition model training on Kinetics400 dataset .. card:: :title: Pre-trained SlowFast Models on Kinetics400 :link: ../build/examples_action_recognition/demo_slowfast_kinetics400.html Recognize human actions in real-world videos with pre-trained SlowFast models .. card:: :title: Training SlowFast Models on Kinetics400 :link: ../build/examples_action_recognition/dive_deep_slowfast_kinetics400.html Hands on SlowFast action recognition model training on Kinetics400 dataset .. card:: :title: Fine-tuning video mdoels on Your Own Dataset :link: ../build/examples_action_recognition/finetune_custom.html Hands on SOTA video models fine-tuning on your own dataset .. card:: :title: Extracting video features from pre-trained models :link: ../build/examples_action_recognition/feat_custom.html Extracting video features from pre-trained models on your own videos .. card:: :title: Inference on your own videos using pre-trained models :link: ../build/examples_action_recognition/demo_custom.html Inference on your own videos using pre-trained models and save the predictions. .. card:: :title: Introducing Decord: an efficient video reader :link: ../build/examples_action_recognition/decord_loader.html An efficient and flexible video reader for training deep video neural networks. Object Tracking --------------------- .. container:: cards .. card:: :title: Pre-trained Siam RPN Models :link: ../build/examples_tracking/demo_SiamRPN.html Estimate Single Object Tracking in real-world video with pre-trained Object Tracking models. .. card:: :title: Dive Deep into Training SiamRPN Models :link: ../build/examples_tracking/train_siamrpn.html SiamRPN training on VID、DET、COCO、Youtube_bb and test on Otb2015 .. card:: :title: Pre-trained SMOT Models :link: ../build/examples_tracking/demo_smot.html Perform Multi-Object Tracking in real-world video with pre-trained SMOT models. Depth Prediction --------------------- .. container:: cards .. card:: :title: Pre-trained Monodepth2 Models :link: ../build/examples_depth/demo_monodepth2.html Predict depth from a single image using Monodepth2. .. card:: :title: Pre-trained Monodepth2 Models :link: ../build/examples_depth/videos_monodepth2.html Predict depth from an image sequence or a video using Monodepth2. .. card:: :title: Dive Deep into Training Monodepth2 Models :link: ../build/examples_depth/train_monodepth2.html Monodepth2 training on KITTI dataset. .. card:: :title: Dive Deep into Testing Pretrained PoseNet Models :link: ../build/examples_depth/test_monodepth2_posenet.html Monodepth2 PoseNet testing on KITTI dataset. Dataset Preparation ------------------- .. container:: cards .. card:: :title: Prepare ADE20K Dataset :link: ../build/examples_datasets/ade20k.html .. card:: :title: Prepare MS COCO Dataset :link: ../build/examples_datasets/mscoco.html .. card:: :title: Prepare Cityscapes Dataset :link: ../build/examples_datasets/cityscapes.html .. card:: :title: Prepare Pascal VOC Dataset :link: ../build/examples_datasets/pascal_voc.html .. card:: :title: Prepare Custom Dataset for Object Detection :link: ../build/examples_datasets/detection_custom.html .. card:: :title: Prepare ImageNet Dataset :link: ../build/examples_datasets/imagenet.html .. card:: :title: Prepare ImageNet Dataset in ImageRecord Format :link: ../build/examples_datasets/recordio.html .. card:: :title: Prepare UCF101 Dataset :link: ../build/examples_datasets/ucf101.html .. card:: :title: Prepare Kinetics400 Dataset :link: ../build/examples_datasets/kinetics400.html .. card:: :title: Prepare Something-Something-V2 Dataset :link: ../build/examples_datasets/somethingsomethingv2.html .. card:: :title: Prepare HMDB51 Dataset :link: ../build/examples_datasets/hmdb51.html .. card:: :title: Prepare Multi-Human Parsing V1 Dataset :link: ../build/examples_datasets/mhp_v1.html Auto Module ----------- .. container:: cards .. card:: :title: Example of loading web data into gluoncv.auto :link: ../build/examples_auto_module/demo_auto_data.html .. card:: :title: Train image classifier with auto estimator :link: ../build/examples_auto_module/train_image_classifier_basic.html .. card:: :title: Train Object Detection model with auto module :link: ../build/examples_auto_module/demo_auto_detection.html Distributed Training -------------------- .. container:: cards .. card:: :title: Distributed training of deep video models: SlowFast :link: ../build/examples_distributed/distributed_slowfast.html Hands on distributed training of SlowFast models on Kinetics400 dataset. Deployment ---------- .. container:: cards .. card:: :title: Export Models into JSON :link: ../build/examples_deployment/export_network.html .. card:: :title: C++ Inference with GluonCV :link: ../build/examples_deployment/cpp_inference.html .. card:: :title: Inference with Quantized Models :link: ../build/examples_deployment/int8_inference.html .. toctree:: :hidden: :maxdepth: 2 ../build/examples_classification/index ../build/examples_detection/index ../build/examples_instance/index ../build/examples_segmentation/index ../build/examples_pose/index ../build/examples_action_recognition/index ../build/examples_tracking/index ../build/examples_depth/index ../build/examples_datasets/index ../build/examples_auto_module/index ../build/examples_distributed/index ../build/examples_deployment/index