pavaris-pm / dog-breed-classification-webapp Goto Github PK

Dog Breed Classification utilizing DetectionTransformer & ConvNext / Convolutional AutoEncoder architecture deployed as Web Application Demo 🪖🎖️

Home Page: https://oppai-dog-breed-classification-webapp-for-deployment.streamlit.app/

License: MIT License

Python 98.81% Shell 1.19%

dog-breed-classification-webapp's Introduction

"Whenever there is a hard job to be done, assign it to a lazy man; he is sure to find an easy way of doing it"

🌱 I’m currently learning Knowledge Graph-based Natural Language Processing
🚀 I’m looking to collaborate on Research projects related to Natural Language Processing and Computer Vision
💬 Ask me about Financial Investment would be a plus
📫 How to reach me [email protected]
⚡ Fun fact I'm a weeb who is mainly interested in Manga, Anime, and Cosplayers

Open Source Contributions Achievement 🏆 🌏

Languages and Tools:

Work Experience ♟️ [will be added soon]

Machine Learning and Deep learning experiences 🤖 [Last Update: January 2023]

Image processing and Computer Vision

Topic	Dataset	Description	Year	Code
👨‍ Object Detection	Face Images and videos	Developed program to detect human face and eyes using OpenCV library with HaarCascade Classfiers	2022	Deployment repo
⚕️ Image Classification & Image Localization	Optical Coherence Tomography image (Private)	Fine-tuned VGG16, ResNet18, AlexNet, and GoogleNet models to classify and localize patients who have Diabetic Retinopathy (DR) disease	2022	Coming soon
👨‍💻 Image Classification	CIFAR-10	Trained Convoluton Neural Network (CNN) model to classify images from CIFAR-10 dataset	2022	Deployment repo

Natural Language Processing (NLP)

Topic	Dataset	Description	Year	Code
🌍 Machine Translation	KDE4	Fine-tuned transformer-align model to translate from thai to another language using huggingface's transformers	2023	Deployment repo
🎞️ Sentiment Analysis	GLUE-SST2	Fine-tuned DistilBERT base uncased model from huggingface for sentiment analysis from movie reviews and human annotations of their sentiment	2022	Deployment repo

Data Science and Big Data Analytics

Topic	Dataset	Description	Year	Code
🏠 Asset Prediction	Thai questionaire (Private)	Using XGBoost and LightGBM to predict Thai people asset based on their general information	2022	Coming soon
🎓 Data Visualization	The Essense school data (Private)	Created statistical report based on student's data provided by The Essense school using Looker studio (Google Data Studio)	2022	Coming soon

IoTs and Robotics

Topic	Dataset	Description	Year	Code
🌡️ Temperature Prediction	Utu-noi sensors (Private)	Apply CatBoost and PyCaret to predict temperature based on data collected from Utu-noi sensors	2022	Coming soon

Competitions ♟️ [will be added soon]

My Personal Stats

No activity tracked

My Blog posts

https://medium.com/@AimAlg/ให้ทุกการค้นหาสะดวกขึ้นด้วย-search-engine-chatgpt-คอมโบสุดเทพแห่งโลกอนาคตที่น่าจับตามอง-ce526d13a09e

https://medium.com/@AimAlg/ทำไม-numpy-array-ถึงน่าใช้กว่า-list-ในงานประเภท-data-science-part-1-67742ad0b5ac

Connect with me:

dog-breed-classification-webapp's People

Contributors

Stargazers

Watchers

Forkers

ryunumchon toydnychristini supermind-c

dog-breed-classification-webapp's Issues

make training process of the model can be done/duplicate through shell script

as mentioned in #4 that seems like i've faced a problem with loading the model weight, the path was founded already but the weight file seems like it is corrupted or something, the weight can be download in colab but cannot in codespace. According to that, one of the easiest solution is to building a shell script to be executed so that everything can be done in single environment. Note that any suggestion is welcome 💯

optimize the speed during inference of web application

as stated in #7 we will see that it will re-init the model everytime we upload new image, which is time-consuming since the ConvNext itself is very large. Consider optimize the speed by downloading everything first before making an inference at the end would much help a lot 💯

train a classifier model using `ConvNext` to classify dog breeds by @pavaris-pm

For all contributors here @supermind-c @ToydnyChristini @RyuNumchon 📢 ❗

Even it seems to be great on 92% validation accuracy with ConvNext architecture, @supermind-c has made a visualization of my torch training loop, and seems like my code for display the training statistics (e.g. training acc, training loss) is wrong in the colab notebook. Since it is my logical error not a syntax error, i will fix it and give you a link in this separated PR so that you won't be confused with #1 which is the main issues🔥

Any `Bug` occured in Web Application

since this is our first dog-breed-classification website , this issue are opened for all users who come up into our website and test our model by uploading external images. Note that if you have found any error, feel free to leave a comment here about what you've found. I will fix it as soon as i heard them from you!

in case of urgent work, please kindly @pavaris-pm to the loop, so that i will reply much faster!

Feature Requests [WIP] 🦖

add custom component (e.g. probability distribution) in order to decorate our website by @pavaris-pm
train a classifier model using Convolutional AutoEncoder (CAE) to classify dog breeds by @pavaris-pm
#6 by @pavaris-pm for code implementation, co-authored with @supermind-c for bug fixing and model training
#5 by @pavaris-pm
Push ConvNext to Huggingface Hub by @supermind-c
format and setup code of conduct (code refactorization for wrong import & NonType of input/output specification) by @pavaris-pm
add unit testing for test-driven-development
optimize the speed during inference of web application, and solve the problem found in #7 by @supermind-c with newly deployed webapp in new domain website

etc ... (tag me and explain an error you've found)

For Contributors

Clearly note here that a PR also welcome, let's contribute to this project onward !
You can contribute to this project by

Fork this repo
Clone the repository
add a feature or fix bug in the source code
Made a PR, then, add @pavaris-pm to review your code (do not forget to link to this issue)