Deep Learning models with vanilla & PyTorch implementations. Projects, Research, Theory and homeworks
-
Updated
Mar 9, 2019 - Jupyter Notebook
Deep Learning models with vanilla & PyTorch implementations. Projects, Research, Theory and homeworks
MNIST digit classification using Keras/ConvNet with data augmentation and adaptive learning rate
The goal of this project is to build a robust traffic signs classifier by the magical powers of deep neural networks and the the dataset provided by the German Traffic Signs Dataset.
Simple convolutional neural network (purely numpy) to classify the original MNIST dataset. My first project with a convnet. 🖼
Detection of autism through the machine learning and deep learning analysis of Magnetoencephalography scans.
Q-learning Neural Network learning to steer a car and avoid obstacles. Uses ConvNet library.
Hack Submitted in HackInTheNorth4 at IIIT Allahabad, India.
ConvNet Seq2Seq for Neural Machine Translation
Personnal collection of python3 snippets
Natural Language Processing(NLP) with Deep Learning in Keras . Course offered by Udemy . Created and taught by Carlos Quiros .
Classify images from the CIFAR-10 dataset using a Convolutional Neural Network, built with Tensorflow
MidNet Convolutional Neural Networks - detection, classification abnormalities and image processing tasks
ResNet is one of the most powerful deep neural networks which has achieved fantabulous performance results in the ILSVRC 2015 classification challenge. ResNet has achieved excellent generalization performance on other recognition tasks and won first place on ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation in ILSV…
ConvNet Library in Python using Numpy
LSTM Pose Machines for Video Human Pose Estimation - Implemented by PyTorch
CNN Model to Classify Playing Cards
Add a description, image, and links to the convnet topic page so that developers can more easily learn about it.
To associate your repository with the convnet topic, visit your repo's landing page and select "manage topics."