A scratch implementation of Convolutional Neural Network in Python using only numpy and validated over CIFAR-10 & MNIST Dataset

A high level deep learning library for Convolutional Neural Networks,GANs and more, made from scratch(numpy/cupy implementation).

Implementing Neural Networks for Computer Vision in autonomous vehicles and robotics for classification, pattern recognition, control. Using Python, numpy, tensorflow. From basics to complex project

An implementation of a convolutional network in Python using only numpy and comparing the results on MNIST with a similar torch model.

This is the Convolutional Neural Network (CNN) implementation with a single convolution layer from scratch using Numpy library. The image dataset on which classification is done is MNIST. It is able to classify with more than 97% classification accuracy after training for just 1 epoch.

This is a simple CNN CPU, GPU implementation where the model can be submitted as a Dictionary for the CPU and GPU version.

Vectorized CNN implementation from scratch using only numpy

Lab assignments including the implementation of convolutional neural network from scratch using numpy only

An efficient numpy-based CNN library with PyTorch-style APIs

Photo sharing and photo storage services like to have location data for each photo that is uploaded. With the location data, these services can build advanced features, such as automatic suggestion of relevant tags or automatic photo organization, which help provide a compelling user experience.

Trying implementation of convolutional neural network (CNN) from scratch. Only using numpy.

ML Sessional of BUET CSE Dept

The app takes image input from the user and accurately classifies the landmark in the image. It gives the top 5 possible landmark names with the probability.