A CV toolkit for my papers.

How to use Cross Replica / Synchronized Batchnorm in Pytorch

A Re-implementation of Fixed-update Initialization

MXNet Gluon Synchronized Batch Normalization Preview

Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers https://arxiv.org/abs/1802.00124

My solutions for Assignments of CS231n: Convolutional Neural Networks for Visual Recognition

Deep learning projects including applications (face recognition, neural style transfer, autonomous driving, sign language reading, music generation, translation, speech recognition and NLP) and theories (CNNs, RNNs, LSTM, Adam, Dropout, BatchNorm, Xavier/He initialization, hyperparameter tuning, regularization, optimization, Residual Networks). Deep Learning Specialization by Andrew Ng, deeplearning.ai

Review materials for the TWiML Study Group. Contains annotated versions of the original Jupyter noteboooks (look for names like *_jcat.ipynb ), slide decks from weekly Zoom meetups, etc.

Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks

Synchronized BatchNorm in PyTorch 1.0

VGG16 architecture with BatchNorm

Unveiling the Layers: Neural Networks from first principles

Solutions for Andrej Karpathy's "Neural Networks: Zero to Hero" course

Cross-platform mobile Neural network C library for training and inference on the device. CPU only. It fits for time-series data.

Playground repository to highlight the problem of BatchNorm layers for an blog article

remove batchnorm when deploy mxnet model

MNIST Classification using Neural Network and Back Propagation. Written in Python and depends only on Numpy

Code to fold batch norm layer of a DNN model in pytorch

Partial transfusion: on the expressive influence of trainable batch norm parameters for transfer learning. TL;DR: Fine-tuning only the batch norm affine parameters leads to similar performance as to fine-tuning all of the model parameters

Implementation of a Fully Connected Neural Network, Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN) from Scratch, using NumPy.

fuse batch normalization layer and con layer in CNN

No description provided.

Digit recognition neural network using the MNIST dataset. Features include a full gui, convolution, pooling, momentum, nesterov momentum, RMSProp, batch normalization, and deep networks.

This repository contains different implementation of deep learning model using Numpy.

Neural network with momentum and batchnorm (MNIST classification example)

A C# WGAN.

Built CNN model with different no. of layers with added dropout on MNIST data

MXNet implementation of Filter Response Normalization Layer (FRN) published in CVPR2020

Implement GAN (Generative Adversarial Network) on MNIST dataset. Vary the hyperparameters and analyze the corresponding results.

I implemented a classifier using batchnorm provided by tensorflow slim and analyzed the results using tensorboard.