Skip to main content

Useful machine-learning related stuff.

Project description

Typical usage often looks like this:

#!/usr/bin/env python
import ml_utils as mlu
mlu.imutils.resize_keep_aspect(img_arr):

Some functions for supporting machine learning, generally and caffe-specific. Currently just a dump, ideally will clean up and add install.py, examples etc

caffe - python layers for

  • image read (file or lmdb) - single / multi label, pixel level labels
  • on-the-fly augmentation
  • support for pixel-level segmentation (read mask as label, etc)
  • controlling and reporting acc/loss of solver with solver.step

image processing

  • image augmentation - including bounding boxes and pixel level
  • acccuracy/precision/recall reporting for single label, multilabel , bounding box, and pixel level
  • utilities e.g. read from anywhere (url/db/local file/img array)
  • grabcut

read/write various file formats

  • lmdb, hd5
  • yolo
  • deepfashion
  • tamara berg
  • ILSRVC
  • etc

tagging tools

  • multilabel
  • pixel level

Project details


Release history Release notifications

Download files

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

Filename, size & hash SHA256 hash help File type Python version Upload date
nn_utils-0.1.0-py2.py3-none-any.whl (326.8 kB) Copy SHA256 hash SHA256 Wheel py2.py3 Mar 19, 2018
nn_utils-0.1.0.tar.gz (155.2 kB) Copy SHA256 hash SHA256 Source None Mar 19, 2018

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page