All Projects → khanhnamle1994 → Fashion Recommendation

khanhnamle1994 / Fashion Recommendation

A clothing retrieval and visual recommendation model for fashion images.

Programming Languages

python
139335 projects - #7 most used programming language
python3
1442 projects

Projects that are alternatives of or similar to Fashion Recommendation

Ditching Excel For Python
Functionalities in Excel translated to Python
Stars: ✭ 172 (-10.88%)
Mutual labels:  pandas, numpy
Andrew Ng Notes
This is Andrew NG Coursera Handwritten Notes.
Stars: ✭ 180 (-6.74%)
Mutual labels:  pandas, numpy
Machine Learning With Python
Practice and tutorial-style notebooks covering wide variety of machine learning techniques
Stars: ✭ 2,197 (+1038.34%)
Mutual labels:  pandas, numpy
Data Analysis
主要是爬虫与数据分析项目总结,外加建模与机器学习,模型的评估。
Stars: ✭ 142 (-26.42%)
Mutual labels:  pandas, numpy
Tensorflow Ml Nlp
텐서플로우와 머신러닝으로 시작하는 자연어처리(로지스틱회귀부터 트랜스포머 챗봇까지)
Stars: ✭ 176 (-8.81%)
Mutual labels:  pandas, numpy
Opendatawrangling
공공데이터 분석
Stars: ✭ 148 (-23.32%)
Mutual labels:  pandas, numpy
Cheatsheets.pdf
📚 Various cheatsheets in PDF
Stars: ✭ 159 (-17.62%)
Mutual labels:  pandas, numpy
Data Science For Marketing Analytics
Achieve your marketing goals with the data analytics power of Python
Stars: ✭ 127 (-34.2%)
Mutual labels:  pandas, numpy
Data Science Types
Mypy stubs, i.e., type information, for numpy, pandas and matplotlib
Stars: ✭ 180 (-6.74%)
Mutual labels:  pandas, numpy
Ta
Technical Analysis Library using Pandas and Numpy
Stars: ✭ 2,649 (+1272.54%)
Mutual labels:  pandas, numpy
Python Cheat Sheet
Python Cheat Sheet NumPy, Matplotlib
Stars: ✭ 1,739 (+801.04%)
Mutual labels:  pandas, numpy
Panthera
Data-frames & arrays on Clojure
Stars: ✭ 168 (-12.95%)
Mutual labels:  pandas, numpy
Ml Cheatsheet
A constantly updated python machine learning cheatsheet
Stars: ✭ 136 (-29.53%)
Mutual labels:  pandas, numpy
Stock Price Predictor
This project seeks to utilize Deep Learning models, Long-Short Term Memory (LSTM) Neural Network algorithm, to predict stock prices.
Stars: ✭ 146 (-24.35%)
Mutual labels:  pandas, numpy
Machine Learning Projects
This repository consists of all my Machine Learning Projects.
Stars: ✭ 135 (-30.05%)
Mutual labels:  pandas, numpy
Alphalens
Performance analysis of predictive (alpha) stock factors
Stars: ✭ 2,130 (+1003.63%)
Mutual labels:  pandas, numpy
Ni Pyt
Materiály k předmětu NI-PYT na FIT ČVUT
Stars: ✭ 112 (-41.97%)
Mutual labels:  pandas, numpy
Seaborn Tutorial
This repository is my attempt to help Data Science aspirants gain necessary Data Visualization skills required to progress in their career. It includes all the types of plot offered by Seaborn, applied on random datasets.
Stars: ✭ 114 (-40.93%)
Mutual labels:  pandas, numpy
Py
Repository to store sample python programs for python learning
Stars: ✭ 4,154 (+2052.33%)
Mutual labels:  pandas, numpy
Xarray
N-D labeled arrays and datasets in Python
Stars: ✭ 2,353 (+1119.17%)
Mutual labels:  pandas, numpy

Fashion Recommendation

In this project, I created an end-to-end solution for large-scale image classification and visual recommendation on fashion images. More specifically, my model can learn the important regions in an image and generate diverse recommendations based on such semantic similarity.

First, I built a clothing image classification model using a ResNet-based model. The feature layer of this model can capture fine-grained semantic clothing features like fabrics, styles and patterns of the clothes. Then, using such features, the model can recommend similar clothes to the input images using nearest neighbor search.

An accompanied blog post via FloydHub can be found at this link: Recommending Similar Fashion Images with Deep Learning

Dataset

DeepFashion is a large-scale clothes database that is quite popular in the research community. It contains over 800,000 diverse fashion images ranging from well-posed shop images to unconstrained consumer photos. It is annotated with rich information of clothing items. It also contains over 300,000 cross-pose/cross-domain image pairs.

More specifically, I used the images in the DeepFashion Attribute Prediction subset. It contains 289,222 number of clothes images, 50 number of clothing categories, and 1,000 number of clothing attributes. Each image is annotated by bounding box and clothing type.

AttributePrediction

Code

  1. preprocessing.py: This code is used to pre-process the dataset.
  2. hyper_parameters.py: This code is used to define all hyper-parameters regarding training.
  3. fashion_input.py: This code is used to pre-process the image further during training.
  4. simple_resnet.py: This code is used to define ResNet architecture.
  5. train_n_test.py: This code is used as the main training file.

Sample Results

1 - Romper Category

Romper

2 - Jacket Category

Jacket

3 - Blouse Shirt Category

BlouseShirt

Requirements

Run on FloydHub

Run on FloydHub

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].