UsefulLinks
Computer Science
Artificial Intelligence
Deep Learning
PyTorch Library
1. Introduction to PyTorch
2. Tensors: The Foundation
3. Tensor Operations and Manipulation
4. Automatic Differentiation
5. Neural Network Construction
6. Data Handling and Processing
7. Model Training and Optimization
8. Model Persistence and Deployment
9. Advanced PyTorch Features
10. PyTorch Ecosystem Integration
6.
Data Handling and Processing
6.1.
Dataset Abstraction
6.1.1.
Dataset Types
6.1.1.1.
Map-style Datasets
6.1.1.2.
Iterable-style Datasets
6.1.2.
Dataset Interface
6.1.2.1.
len Method
6.1.2.2.
getitem Method
6.1.2.3.
Iterator Protocol
6.1.3.
Custom Dataset Creation
6.1.3.1.
File-based Datasets
6.1.3.2.
In-memory Datasets
6.1.3.3.
Streaming Datasets
6.1.4.
Dataset Composition
6.1.4.1.
Concatenating Datasets
6.1.4.2.
Subset Creation
6.1.4.3.
Dataset Splitting
6.2.
DataLoader Functionality
6.2.1.
Batch Processing
6.2.1.1.
Batch Size Configuration
6.2.1.2.
Automatic Batching
6.2.1.3.
Variable-length Sequences
6.2.2.
Data Shuffling
6.2.2.1.
Random Sampling
6.2.2.2.
Reproducible Shuffling
6.2.2.3.
Stratified Sampling
6.2.3.
Parallel Data Loading
6.2.3.1.
Multi-process Loading
6.2.3.2.
Worker Process Management
6.2.3.3.
Memory Sharing Considerations
6.2.4.
Custom Collation
6.2.4.1.
collate_fn Parameter
6.2.4.2.
Handling Irregular Data
6.2.4.3.
Padding Strategies
6.2.5.
Memory Optimization
6.2.5.1.
Pin Memory for GPU Transfer
6.2.5.2.
Prefetching Strategies
6.2.5.3.
Memory-mapped Files
6.3.
Data Preprocessing
6.3.1.
Transformation Pipelines
6.3.1.1.
Transform Composition
6.3.1.2.
Conditional Transforms
6.3.1.3.
Random Transforms
6.3.2.
Normalization Techniques
6.3.2.1.
Statistical Normalization
6.3.2.2.
Min-max Scaling
6.3.2.3.
Standardization
6.3.3.
Data Augmentation
6.3.3.1.
Geometric Transformations
6.3.3.2.
Color Space Modifications
6.3.3.3.
Noise Addition
6.3.4.
Missing Data Handling
6.3.4.1.
Imputation Strategies
6.3.4.2.
Masking Techniques
6.3.4.3.
Robust Processing
6.4.
Specialized Data Types
6.4.1.
Image Data Processing
6.4.1.1.
PIL Integration
6.4.1.2.
OpenCV Compatibility
6.4.1.3.
Multi-channel Images
6.4.2.
Text Data Processing
6.4.2.1.
Tokenization
6.4.2.2.
Vocabulary Management
6.4.2.3.
Sequence Padding
6.4.3.
Audio Data Processing
6.4.3.1.
Waveform Handling
6.4.3.2.
Spectrogram Generation
6.4.3.3.
Feature Extraction
6.4.4.
Time Series Data
6.4.4.1.
Windowing Techniques
6.4.4.2.
Temporal Alignment
6.4.4.3.
Missing Value Interpolation
Previous
5. Neural Network Construction
Go to top
Next
7. Model Training and Optimization