Skip to main content

A package used in DNN trainning in ATLAS analysis

Project description

Python package use cuda to normalize input variables using cuda package in ATLAS analysis

Function use to do Guassian Normalization: Mean: $$\mu_{i}=\frac{\sum x_{i}\times w_{i}}{\sum w_{i}}$$ Variance: $$\sigma_{i}=\frac{\sum (x_{i}-\mu_{i})^{2}\times w_{i}}{\frac{N-1}{N}\times\sum w_{i}}$$ Normalized input feature: $$\bar{x_{i}}=\frac{x_{i}-\mu_{i}}{\sigma_{i}}$$

Main function: guass_normal((1),(2),(3))


(1):Numpy array contain all input features you want to normalize. (2):Numpy array used to calculate each feature's mean and variance. (3):1-d Numpy array contains each events weight in (2)

(1) and (2) must have the same number of columns.

cuda_cut((1),(2),(3)): Used to calculate event yield after applying DNN cut.

Input: (1): 1-d numpy array include the variable you want to cut. (2): 1-d numpy array include event weight. (3): cut threshold

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

cuda_guass_normal-1.13.tar.gz (2.9 kB view hashes)

Uploaded source

Built Distribution

cuda_guass_normal-1.13-py3-none-any.whl (7.5 kB view hashes)

Uploaded py3

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page