A simple python module to generate anchor (aka default/prior) boxes for object detection tasks.

Overview

PyBx

WIP

A simple python module to generate anchor (aka default/prior) boxes for object detection tasks. Calculated anchor boxes are returned as ndarrays in pascal_voc format by default.

Installation

pip install pybx

Usage

To calculate the anchor boxes for a single feature size and aspect ratio, given the image size:

from pybx import anchor

image_sz = (300, 300, 3)
feature_sz = (10, 10)
asp_ratio = 1/2.

anchor.bx(image_sz, feature_sz, asp_ratio)

To calculate anchor boxes for multiple feature sizes and aspect ratios:

feature_szs = [(10, 10), (8, 8)]
asp_ratios = [1., 1/2., 2.]

anchor.bxs(image_sz, feature_szs, asp_ratios)

More on visualising the anchor boxes here.

Todo

  • Wrapper class for boxes with vis.draw() method
  • Companion notebook
  • IOU check (return best overlap boxes)
  • Return masks
  • Unit tests
  • Specific tests
    • feature_sz of different aspect ratios
    • image_sz of different aspect ratios
  • Move to setup.py
Comments
  • Build and refactor [nbdev]

    Build and refactor [nbdev]

    A refactored version of pybx built using nbdev.

    Added:

    • documentation page: docs, README.md, example walkthrough file
    • GH workflow tests

    Breaking changes:

    • Need area() and valid() are now properties of BaseBx, so .area and .valid would suffice
    • utils methods refactored to utils and ops
    opened by thatgeeman 0
  • Walkthrough issue for PIL mode.

    Walkthrough issue for PIL mode.

    In the step: Ask VisBx to use random logits with logits=True

    vis.VisBx(image_sz=image_sz, logits=True, feature_sz=feature_sz).show(anchors, labels)
    

    Returns a key error: KeyError: ((1, 1, 3), '<i8') and TypeError: Cannot handle this data type: (1, 1, 3), <i8 with PIL.

    good first issue 
    opened by thatgeeman 0
  • Patch 4: Docs, Improvements, Bug fixes

    Patch 4: Docs, Improvements, Bug fixes

    • Refactored major sections of pybx.basics and the BxType
    • Backwards incompatible!
    • Detailed docstrings for all methods and classes
    • Directly visualize arrays in VisBx()
    • Visualize, iterate, __add__ operations for BaseBx
    • Helper function to set and return BxType (get_bx)
    • Several verbal assertions and bug fixes
    • Fixes #3 #2
    • [dev] Updated tests
    opened by thatgeeman 0
  • TypeError: 'BaseBx' object is not iterable

    TypeError: 'BaseBx' object is not iterable

    Describe the bug draw method of vis module tries to iterate over BaseBx during visualisation

    To Reproduce Steps to reproduce the behavior:

    anns = {'label': 5,
     'x_min': 87.0,
     'y_min': 196.0,
     'x_max': 1013.0,
     'y_max': 2129.0}
    
    from pybx.ops import make_array
    coords, label = make_array(anns)
    
    b = bbx(coords, label)
    vis.draw(img, b)
    
    opened by thatgeeman 0
  • implemented IOU for `BaseBx` and added unittests

    implemented IOU for `BaseBx` and added unittests

    Main commits

    • implemented intersection-over-union (IOU) for BaseBx
    • added unittests for all modules
    • Implemented classmethod and bbx() for BaseBx class to convert all types to BaseBx
    • ops now handles all type conversions (json-array, list-array)
    • bug fixes, best caught:
      • BaseBx method xywh() flipped w and h
      • read keys in order of voc_keys for json annotations)
    • updated README.md and nbs/
    opened by thatgeeman 0
  • Region proposals

    Region proposals

    Is your feature request related to a problem? Please describe. Rather than creating a bunch of anchor boxes based on geometry, create region proposals based on classic signal processing.

    opened by thatgeeman 0
  • Fix notebook (walkthrough)

    Fix notebook (walkthrough)

    Describe the bug

    • [ ] walkthrough link fails
    • [ ] Code import os bug

    To Reproduce Steps to reproduce the behavior:

    1. Go to '...'
    2. Click on '....'
    3. Scroll down to '....'
    4. See error

    Expected behavior A clear and concise description of what you expected to happen.

    Screenshots If applicable, add screenshots to help explain your problem.

    Desktop (please complete the following information):

    • OS: [e.g. iOS]
    • Browser [e.g. chrome, safari]
    • Version [e.g. 22]

    Smartphone (please complete the following information):

    • Device: [e.g. iPhone6]
    • OS: [e.g. iOS8.1]
    • Browser [e.g. stock browser, safari]
    • Version [e.g. 22]

    Additional context Add any other context about the problem here.

    opened by thatgeeman 0
  • Missing sidebar in documentation page

    Missing sidebar in documentation page

    Describe the bug A clear and concise description of what the bug is.

    To Reproduce Steps to reproduce the behavior:

    1. Go to '...'
    2. Click on '....'
    3. Scroll down to '....'
    4. See error

    Expected behavior A clear and concise description of what you expected to happen.

    Screenshots If applicable, add screenshots to help explain your problem.

    Desktop (please complete the following information):

    • OS: [e.g. iOS]
    • Browser [e.g. chrome, safari]
    • Version [e.g. 22]

    Smartphone (please complete the following information):

    • Device: [e.g. iPhone6]
    • OS: [e.g. iOS8.1]
    • Browser [e.g. stock browser, safari]
    • Version [e.g. 22]

    Additional context Add any other context about the problem here.

    opened by thatgeeman 0
Releases(v0.3.0)
  • v0.3.0(Nov 20, 2022)

    A refactored version of pybx built using nbdev.

    Added:

    • documentation page: docs, README.md, example walkthrough file
    • GH workflow tests

    Breaking changes:

    • Need area() and valid() are now properties of BaseBx, so .area and .valid would suffice
    • utils methods refactored to utils and ops
    Source code(tar.gz)
    Source code(zip)
  • v0.2.1(Jan 21, 2022)

    What's Changed

    • Patch 5: Minor fixes by @thatgeeman in https://github.com/thatgeeman/pybx/pull/5
    • Patch 4: Docs, Improvements, Bug fixes by @thatgeeman in https://github.com/thatgeeman/pybx/pull/4

    Full Changelog: https://github.com/thatgeeman/pybx/compare/v0.1.4...v0.2.1

    Source code(tar.gz)
    Source code(zip)
  • v0.1.4(Jan 18, 2022)

    What's Changed

    • implemented IOU for BaseBx and added unittests by @thatgeeman in https://github.com/thatgeeman/pybx/pull/1

    New Contributors

    • @thatgeeman made their first contribution in https://github.com/thatgeeman/pybx/pull/1

    Full Changelog: https://github.com/thatgeeman/pybx/compare/v0.1.3...v0.1.4

    Source code(tar.gz)
    Source code(zip)
Owner
thatgeeman
Physics PhD. Previously @CharlesSadron @CNRS @unistra. Computer Vision.
thatgeeman
SingleVC performs any-to-one VC, which is an important component of MediumVC project.

SingleVC performs any-to-one VC, which is an important component of MediumVC project. Here is the official implementation of the paper, MediumVC.

谷下雨 26 Dec 28, 2022
A Python package for generating concise, high-quality summaries of a probability distribution

GoodPoints A Python package for generating concise, high-quality summaries of a probability distribution GoodPoints is a collection of tools for compr

Microsoft 28 Oct 10, 2022
Skipgram Negative Sampling in PyTorch

PyTorch SGNS Word2Vec's SkipGramNegativeSampling in Python. Yet another but quite general negative sampling loss implemented in PyTorch. It can be use

Jamie J. Seol 287 Dec 14, 2022
An Open Source Machine Learning Framework for Everyone

Documentation TensorFlow is an end-to-end open source platform for machine learning. It has a comprehensive, flexible ecosystem of tools, libraries, a

170.1k Jan 04, 2023
PyTorch implementation of the paper: Long-tail Learning via Logit Adjustment

logit-adj-pytorch PyTorch implementation of the paper: Long-tail Learning via Logit Adjustment This code implements the paper: Long-tail Learning via

Chamuditha Jayanga 53 Dec 23, 2022
Code release for ICCV 2021 paper "Anticipative Video Transformer"

Anticipative Video Transformer Ranked first in the Action Anticipation task of the CVPR 2021 EPIC-Kitchens Challenge! (entry: AVT-FB-UT) [project page

Facebook Research 123 Dec 13, 2022
Repo 4 basic seminar §How to make human machine readable"

WORK IN PROGRESS... Notebooks from the Seminar: Human Machine Readable WS21/22 Introduction into programming Georg Trogemann, Christian Heck, Mattis

experimental-informatics 3 May 29, 2022
Code I use to automatically update my videos' metadata on YouTube

mCodingYouTube This repository contains the code I use to automatically update my videos' metadata on YouTube, including: titles, descriptions, tags,

James Murphy 19 Oct 07, 2022
这是一个mobilenet-yolov4-lite的库,把yolov4主干网络修改成了mobilenet,修改了Panet的卷积组成,使参数量大幅度缩小。

YOLOV4:You Only Look Once目标检测模型-修改mobilenet系列主干网络-在Keras当中的实现 2021年2月8日更新: 加入letterbox_image的选项,关闭letterbox_image后网络的map一般可以得到提升。

Bubbliiiing 65 Dec 01, 2022
JAX + dataclasses

jax_dataclasses jax_dataclasses provides a wrapper around dataclasses.dataclass for use in JAX, which enables automatic support for: Pytree registrati

Brent Yi 35 Dec 21, 2022
Codes for TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization.

TS-CAM: Token Semantic Coupled Attention Map for Weakly SupervisedObject Localization This is the official implementaion of paper TS-CAM: Token Semant

vasgaowei 112 Jan 02, 2023
TCPNet - Temporal-attentive-Covariance-Pooling-Networks-for-Video-Recognition

Temporal-attentive-Covariance-Pooling-Networks-for-Video-Recognition This is an implementation of TCPNet. Introduction For video recognition task, a g

Zilin Gao 21 Dec 08, 2022
Fibonacci Method Gradient Descent

An implementation of the Fibonacci method for gradient descent, featuring a TKinter GUI for inputting the function / parameters to be examined and a matplotlib plot of the function and results.

Emma 1 Jan 28, 2022
Dogs classification with Deep Metric Learning using some popular losses

Tsinghua Dogs classification with Deep Metric Learning 1. Introduction Tsinghua Dogs dataset Tsinghua Dogs is a fine-grained classification dataset fo

QuocThangNguyen 45 Nov 09, 2022
CondenseNet V2: Sparse Feature Reactivation for Deep Networks

CondenseNetV2 This repository is the official Pytorch implementation for "CondenseNet V2: Sparse Feature Reactivation for Deep Networks" paper by Le Y

Haojun Jiang 74 Dec 12, 2022
Practical Blind Denoising via Swin-Conv-UNet and Data Synthesis

Practical Blind Denoising via Swin-Conv-UNet and Data Synthesis [Paper] [Online Demo] The following results are obtained by our SCUNet with purely syn

Kai Zhang 312 Jan 07, 2023
Source code for our paper "Empathetic Response Generation with State Management"

Source code for our paper "Empathetic Response Generation with State Management" this repository is maintained by both Jun Gao and Yuhan Liu Model Ove

Yuhan Liu 3 Oct 08, 2022
Wordle Env: A Daily Word Environment for Reinforcement Learning

Wordle Env: A Daily Word Environment for Reinforcement Learning Setup Steps: git pull [email&#

2 Mar 28, 2022
Caffe: a fast open framework for deep learning.

Caffe Caffe is a deep learning framework made with expression, speed, and modularity in mind. It is developed by Berkeley AI Research (BAIR)/The Berke

Berkeley Vision and Learning Center 33k Dec 28, 2022
Lucid Sonic Dreams syncs GAN-generated visuals to music.

Lucid Sonic Dreams Lucid Sonic Dreams syncs GAN-generated visuals to music. By default, it uses NVLabs StyleGAN2, with pre-trained models lifted from

731 Jan 02, 2023