mnistMuddle
handwritten-multi-digit-number-recognition
mnistMuddle | handwritten-multi-digit-number-recognition | |
---|---|---|
2 | 1 | |
3 | 21 | |
- | - | |
0.0 | 0.0 | |
almost 3 years ago | over 2 years ago | |
Jupyter Notebook | Jupyter Notebook | |
- | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
mnistMuddle
-
Basic Auto Encoder project - Generating poorly written digits [PyTorch]
yes, you are thinking in the right direction. I'm passing the input image to get the latent vector and then decoding it. For each of the 10 classes, I've also computed the average latent vector to represent that label cluster. Check this code here - LINK
-
[P] Basic Auto Encoder project - Generating poorly written digits (PyTorch)
Hi, looking for your thoughts and feedback I created this side project to play with latent domain. The aim was to transform an input image to something that looks somewhere between 2 digits. The repository below will give you a practical exposure to Auto Encoders, Latent Domain, PyTorch, Hosting on Streamlit. GitHub Repository - LINK
handwritten-multi-digit-number-recognition
-
I made a handwritten number recognizer
Github repo: https://github.com/kingyiusuen/handwritten-multi-digit-number-recognition
What are some alternatives?
first-order-model - This repository contains the source code for the paper First Order Motion Model for Image Animation
yolov3-tf2 - YoloV3 Implemented in Tensorflow 2.0
torchdyn - A PyTorch library entirely dedicated to neural differential equations, implicit models and related numerical methods
handwritten-digits-recognizer-webapp - This is my first experience with machine learning
neuralforecast - Scalable and user friendly neural :brain: forecasting algorithms.
apartment_recommender_streamlit_app - Streamlit App that recommends apartments in Seattle using the Airbnb kaggle dataset: https://www.kaggle.com/code/rdaldian/airbnb-content-based-recommendation-system/data?select=listings.csv
Handwritten-Optical-Character-Recognition - Responsive web app that can recognize handwritten characters drawn on canvas and perform arithmetic calculation.
NeMo - A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
cybersecurity-jina - Network Intrusion Dahsboard built with Jina and Streamlit
gan-vae-pretrained-pytorch - Pretrained GANs + VAEs + classifiers for MNIST/CIFAR in pytorch.