YouTip--
- Home
- HTML
- JavaScript
- CSS
- Vue
- React
- Python3
- Java
- C
- C++
- C#
- AI
- Go
- SQL
- Linux
- VS Code
- Bootstrap
- Git
- Local Bookmarks
PyTorch Tutorial
PyTorch TutorialPyTorch IntroductionPyTorch InstallationPyTorch BasicsPyTorch TensorsPyTorch Neural Networks BasicsPyTorch First Neural NetworkPyTorch Data Processing and LoadingPyTorch Linear RegressionPyTorch Convolutional Neural NetworksPyTorch Recurrent Neural NetworksPyTorch DatasetsPyTorch Data TransformationsPyTorch torchPyTorch torch.nnTransformer ModelPyTorch TransformerPyTorch torch.optimPyTorch torchvisionPyTorch Model DeploymentPyTorch Model Saving and LoadingPyTorch Image ClassificationPyTorch Text Sentiment AnalysisPyTorch AutogradPyTorch GPU / CUDA AccelerationPyTorch Loss FunctionsPyTorch Learning Rate SchedulerPyTorch Transfer LearningPyTorch Batch NormalizationPyTorch LSTM / GRUPyTorch EmbeddingPyTorch GANPyTorch AutoencoderPyTorch Model Evaluation and DebuggingPyTorch torchtextPyTorch Mixed Precision TrainingPyTorch TorchScript/ONNX ExportPyTorch Distributed TrainingPyTorch Attention Mechanism
PyTorch torch.nn Reference Manual
PyTorch torch.bucketize Function
PyTorch torch Reference Manual
torch.bucketize is a PyTorch function for bucket sort indexing. It maps input values to corresponding bucket indices based on boundary arrays using binary search. Commonly used for discretizing continuous values or binning operations.
Function Definition
torch.bucketize(input, boundaries, right=False, out_int32=False, **kwargs)
Usage Examples
Example
import torch
# Basic usage: Bucket Sort Index
boundaries = torch.tensor([0,1,2,3,4])
values = torch.tensor([0.5,1.5,2.5,3.5,0.2,2.0])
result = torch.bucketize(values, boundaries)
print("Boundaries:", boundaries)
print("Values:", values)
print("Bucket Indices:", result)
# Output: tensor([1, 2, 3, 4, 0, 2])
# right=True indicates right-closed intervals
result_right = torch.bucketize(values, boundaries, right=True)
print("right=True Bucket Indices:", result_right)
# Output: tensor([0, 1, 2, 3, 0, 1])
# Multi-dimensional input
values = torch.tensor([[0.5,1.5],[2.5,3.5]])
result = torch.bucketize(values, boundaries)
print("Multi-dimensional Input Result:", result)