GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → Russell91 → Reinspect

Russell91 / Reinspect

End to end detection in crowded scenes

Labels

jupyter-notebook

Projects that are alternatives of or similar to Reinspect

Poppy Humanoid
Poppy Humanoid is an open-source and 3D printed humanoid robot. Optimized for research and education purposes, its modularity allows for a wide range of applications and experimentations.
Stars: ✭ 419 (-1.18%)
Mutual labels:  jupyter-notebook
Python 3 Data Analysis Basics
Python 3 與數據分析概要
Stars: ✭ 420 (-0.94%)
Mutual labels:  jupyter-notebook
Deep Learning Resources
由淺入深的深度學習資源 Collection of deep learning materials for everyone
Stars: ✭ 422 (-0.47%)
Mutual labels:  jupyter-notebook
Hands On Nltk Tutorial
The hands-on NLTK tutorial for NLP in Python
Stars: ✭ 419 (-1.18%)
Mutual labels:  jupyter-notebook
Stat479 Machine Learning Fs18
Course material for STAT 479: Machine Learning (FS 2018) at University Wisconsin-Madison
Stars: ✭ 421 (-0.71%)
Mutual labels:  jupyter-notebook
Bert Japanese
BERT with SentencePiece for Japanese text.
Stars: ✭ 422 (-0.47%)
Mutual labels:  jupyter-notebook
Single Parameter Fit
Real numbers, data science and chaos: How to fit any dataset with a single parameter
Stars: ✭ 419 (-1.18%)
Mutual labels:  jupyter-notebook
Cn Deep Learning
Stars: ✭ 423 (-0.24%)
Mutual labels:  jupyter-notebook
Sentimentanalysis
文本情感分析
Stars: ✭ 421 (-0.71%)
Mutual labels:  jupyter-notebook
6s083
Materials for MIT 6.S083 / 18.S190: Computational thinking with Julia + application to the COVID-19 pandemic
Stars: ✭ 422 (-0.47%)
Mutual labels:  jupyter-notebook
Cs231n
斯坦福 cs231n 作业代码实践
Stars: ✭ 419 (-1.18%)
Mutual labels:  jupyter-notebook
Financepy
A Python Finance Library that focuses on the pricing and risk-management of Financial Derivatives, including fixed-income, equity, FX and credit derivatives.
Stars: ✭ 416 (-1.89%)
Mutual labels:  jupyter-notebook
Cifar10 Fast
Stars: ✭ 421 (-0.71%)
Mutual labels:  jupyter-notebook
Pilot
进入编程世界的第一课
Stars: ✭ 421 (-0.71%)
Mutual labels:  jupyter-notebook
Random Forest Importances
Code to compute permutation and drop-column importances in Python scikit-learn models
Stars: ✭ 422 (-0.47%)
Mutual labels:  jupyter-notebook
Aipnd
Code and associated files for the AI Programming with Python Nanodegree Program
Stars: ✭ 417 (-1.65%)
Mutual labels:  jupyter-notebook
Vit Pytorch
Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)
Stars: ✭ 413 (-2.59%)
Mutual labels:  jupyter-notebook
Self Driving Car Nd
Udacity's Self-Driving Car Nanodegree project files and notes.
Stars: ✭ 424 (+0%)
Mutual labels:  jupyter-notebook
Steal
STEAL - Learning Semantic Boundaries from Noisy Annotations (CVPR 2019)
Stars: ✭ 424 (+0%)
Mutual labels:  jupyter-notebook
Pytablewriter
pytablewriter is a Python library to write a table in various formats: CSV / Elasticsearch / HTML / JavaScript / JSON / LaTeX / LDJSON / LTSV / Markdown / MediaWiki / NumPy / Excel / Pandas / Python / reStructuredText / SQLite / TOML / TSV.
Stars: ✭ 422 (-0.47%)
Mutual labels:  jupyter-notebook
View All Similar Projects ➔

ReInspect

ReInspect is an neural network extension to Overfeat-GoogLeNet in Caffe. For the Tensorflow version, see TensorBox. It is designed for high performance object detection in images with heavily overlapping instances. See the paper for details or the video for a demonstration.

Installation & Demo

$ # install the apollocaffe pull request on caffe. see apollocaffe.com
$ git clone http://github.com/russell91/reinspect
$ cd reinspect
$ make eval

Running make eval will download the data and start a notebook to visualize the performance of the model. If you want to train the model from scratch, you can use

$ make train

Running on your own data

The easiest way to run on your own data is to resize your images to 480x640 and provide labels for each object in each image with the idl text files.

Once you have verified that you can train on 480x640 images, you can also modify the image width and height options in config.json. We recommend you choose an image size which is an integer multiple of 32, and then modify the (15, 20) grid to (image_height / 32, image_width / 32).

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].