in this simple python application yo can select and upload your image and it tell you which celebrity you are most like
-
Updated
Jan 28, 2023 - Jupyter Notebook
Keras is an open source, cross platform, and user friendly neural network library written in Python. It is capable of running on top of TensorFlow, Microsoft Cognitive Toolkit, R, Theano, and PlaidML.
in this simple python application yo can select and upload your image and it tell you which celebrity you are most like
image preprocessing applied to Keras dataset generator which is trainable in Tensorflow Keras model and its visualisation to check input image.
This is a simple classifier to classifying Cat vs Dog pictures with keras (Tensorflow)
Resources for Designing and Utilizing Neural Networks
Trains the flowers dataset to predict the class of 5 different flowers
This is a very Simple CAPTCHA Recognition model written in python with Keras and Tensorflow
OCR from scratch using Chars74 Dataset: http://www.ee.surrey.ac.uk/CVSSP/demos/chars74k/ applied to the case of Spanish car license plates or any other with format NNNNAAA. The hit rate is lower than that achieved by pytesseract: in a test with 21 images, 12 hits are reached while with pytesseract the hits are 17.
Keras for Tensorflow 2023
Using Keras' Stable Diffusion for generating city images using coordinates and a live weather API. (Keras Community Prize Winner 2022)
a project involving Deep Q-Networks (DQN) and Reinforcement Learning (RL) using Gym and Gridworld API
Code for implementation of language modelling using LSTM in Tensorflow
Gender Age Race Prediction Keras with Multiple Heads to The Model.
Simple application of VGG16 for the recognition of images, obtained from LFW, of a limited number of famous(15) with good performance (greater than 80%)
Image Recognition
Deep learning (neural nets) python pet-projects, including the most important methods/attributes to work with neural nets, train them and predict results
OCR from scratch using Kaggle dataset dwonloaded from https://www.kaggle.com/code/preatcher/ocr-training applied to the case of Spanish car license plates or any other with format NNNNAAA. The hit rate is lower than that achieved by pytesseract: in a test with 21 images, 16 hits are reached while with pytesseract the hits are 17
This repository contains Python code for generating a fire detection model and utilizing it to detect fire from user-uploaded images. The model architecture consists of convolutional and pooling layers, followed by fully connected layers. The repository includes scripts for training the model and predicting fire from uploaded images.
Created by François Chollet
Released March 27, 2015