使用 Python 和 PyTorch 进行现代计算机视觉和深度学习

您还未登录,请点击这里登录

上一讲： 5. Training of Segmentation Models

下一讲： 3. Visualize Segmentation Results and Generate RGB Segmented Map

视频列表

1. Introduction
1. Introduction to Course
2. What is Computer Vision & its Applications
1. Introduction to Computer Vision and its Real-world Applications
2. Major Computer Vision Tasks
3. Deep Convolutional Neural Networks (CNN) for Computer Vision
1. Introduction to Convolutional Neural Networks (CNN)
4. Setting-up Google Colab for Writing Python Code
1. Introduction to Google Colab for Python Coding
2. Connect Google Colab with Google Drive
5. Image Classification Task of Computer Vision
1. Introduction to Single and Multi-label Image Classification
6. Pretrained Models for Single and Multi-Label Image Classification
1. Introduction to Pretrained Models
2. Deep Learning ResNet and AlexNet Architectures
3. Access Data from Google Drive to Colab
4. Data Preprocessing for Image Classification
5. Single-Label Image Classification using ResNet and AlexNet PreTrained Models
7. Multi-Label Image Classification using Deep Learning Models
7. Transfer Learning for Image Classification
1. Introduction to Transfer Learning
2. Dataset, Data Augmentation, and Dataloaders
4. FineTuning Deep ResNet Model
5. HyperParameteres Optimization for Model
6. Training Deep ResNet Model
7. Fixed Feature Extractraction using ResNet
8. Model Optimization, Training and Results Visualization
8. Semantic Segmentation Task Of Computer Vision
1. Introduction to Semantic Image Segmentation
2. Semantic Segmentation Real-World Applications
9. Deep Learning Architectures For Segmentation (UNet, PSPNet, PAN)
1. Pyramid Scene Parsing Network (PSPNet) For Segmentation
2. UNet Architecture For Segmentation
3. Pyramid Attention Network (PAN)
4. Multi-Task Contextual Network (MTCNet)
10. Segmentation Datasets, Annotations, Data Augmentation & Data Loading
1. Datasets for Semantic Segmentation
2. Data Annotations Tool for Semantic Segmentation
3. Data Loading with PyTorch Customized Dataset Class
5. Data Augmentation using Albumentations with Different Transformations
7. Learn To Implement Data Loaders In Pytorch
11. Performance Metrics (IOU) For Segmentation Models Evaluation
1. Performance Metrics (IOU, Pixel Accuracy, Precision, Recall, Fscore)
12. Encoders and Decoders For Segmentation In PyTorch
1. Transfer Learning And Pretrained Deep Resnet Architecture
2. Encoders for Segmentation with PyTorch Liberary
3. Decoders for Segmentation in PyTorch Liberary
13. Implementation, Optimization and Training Of Segmentation Models
1. Implement Segmentation Models (UNet, PSPNet, DeepLab, PAN, and UNet++)
3. Learn To Optimize Hyperparameters For Segmentation Models
5. Training of Segmentation Models
14. Test Models and Visualize Segmentation Results
1. Test Models and Calculate IOU,Pixel Accuracy,Fscore
3. Visualize Segmentation Results and Generate RGB Segmented Map
15. Complete Code and Dataset for Semantic Segmentation
1. Final Code Review
16. Object Detection Task Of Computer Vision
1. Object Detection and its Applications
17. Deep Learning Architectures for Object Detection (R-CNN Family)
1. Deep Convolutional Neural Network (VGG, ResNet, GoogleNet)
2. RCNN Deep Learning Architectures for Object Detection
3. Fast RCNN Deep Learning Architectures for Object Detection
4. Faster RCNN Deep Learning Architectures for Object Detection
18. Detectron2 for Ojbect Detection
1. Detectron2 for Ojbect Detection with PyTorch
2. Perform Object Detection using Detectron2 Pretrained Models
19. Training, Evaluating and Visualizing Object Detection on Custom Dataset
1. Custom Dataset for Object Detection
3. Train, Evaluate Object Detection Models & Visualizing Results on Custom Dataset
21. Instance Segmentation Task of Computer Vision
1. What is Instance Segmentation
22. Mask RCNN for Instance Segmentation
1. Mask RCNN for Instance Segmentation
23. Training, Evaluating and Visualizing Instance Segmentation on Custom Dataset
1. Train, Evaluate Instance Segmentation Model & Visualizing Results on Custom Data