Activation Maps (Layers Outputs) and Gradients in Keras.

Keras implementation of a ResNet-CAM model

Object classification with CIFAR-10 using transfer learning

ASCII summary for simple sequential models in Keras

Using various CNN techniques on the MNIST dataset

Utilities for Keras - Deep Learning library

Neural network visualization toolkit for tf.keras

Dynamic visualization training service in Jupyter Notebook for Keras tf.keras and others.

Easy way to visualize convolutional neural networks, through two visualizations : Reason & MaxOut. Final version : web app.

Recognition of the images includes train and tests based on Python.

Dogs-vs-Cats image classification

📉 Visualize Your Deep Learning Training in Static Graphics

An IPython notebook demonstrating the process of Transfer Learning using pre-trained Convolutional Neural Networks with Keras on the popular CIFAR-10 Image Classification dataset.

Breast cancer is the most common form of cancer in women, and invasive ductal carcinoma (IDC) is the most common form of breast cancer. Accurately identifying and categorizing breast cancer subtypes is an important clinical task, and automated methods can be used to save time and reduce error. The goal of this script is to identify IDC when it is present in otherwise unlabeled histopathology images. The dataset consists of approximately five thousand 50x50 pixel RGB digital images of H&E-stained breast histopathology samples that are labeled as either IDC or non-IDC. These numpy arrays are small patches that were extracted from digital images of breast tissue samples. The breast tissue contains many cells but only some of them are cancerous. Patches that are labeled "1" contain cells that are characteristic of invasive ductal carcinoma. For more information about the data, see https://www.ncbi.nlm.nih.gov/pubmed/27563488 and http://spie.org/Publications/Proceedings/Paper/10.1117/12.2043872.

📺 A Python library for pruning and visualizing Keras Neural Networks' structure and weights

Visualization techiques for deep learning neural networks using Keras

This is a model that has been trained on historical data obtained from Yahoo Finance. The data set comprises of all data records starting from the launch date of this stock in India (1996). This model aims to pick up key trends in the stock price fluctuations based on Time Series mapping. It is able to render predictions for the upcoming time period. The accuracy as obtained on the training data-set is about 90 percent and it successfully demonstrates key trends. It can be simulated on any stock in the market provided their historical data is made available. (One could use the yfinance API or download manually). Keras is used extensively along with Tensorflow for training. The model features 100 epochs of Base size 64. The training time depends on the hardware being used by the user. It is advisable to be performed on Google Colaboratory. For any issues/suggestions write to somshankar97@gmail.com

A Deep Learning Automation Framework Library based on keras, sklearn for the automation of the machine learning and deeplearning algorithms training.testing,metrics,comparative analysis and visualisations

Keras Total Visualization project

Project 3 of Term 1 in the Udacity Self Driving Car Nanodegree

This is a repository for the code and various numpy files that going along with the face recognition project.

A keras implementation of DCGAN to generate Pokèmon sprites.

FitsBook Python Library. Tool for generating real-time machine learning training statistics and storing model histories. Direct integration with Keras Framework.

Fitsbook React WebApp. Tool for generating real-time machine learning training statistics and storing model histories. Direct integration with Keras.

In this project I have used Advanced DeepLearning techniques with keras to predict the probability of win and lose of college basketball tournaments.