A CV toolkit for my papers.
-
Updated
Jun 2, 2024 - Python
A CV toolkit for my papers.
Solutions for Andrej Karpathy's "Neural Networks: Zero to Hero" course
Implementation of a Fully Connected Neural Network, Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN) from Scratch, using NumPy.
A set of experiments inspired by the paper "Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs" by Jonathan Frankle, David J. Schwab, Ari S. Morcos
Implement GAN (Generative Adversarial Network) on MNIST dataset. Vary the hyperparameters and analyze the corresponding results.
Batch normalization from scratch on LeNet using tensorflow.keras on mnist dataset. The goal is to learn and characterize batch normalization's impact on the NN performance.
Playground repository to highlight the problem of BatchNorm layers for an blog article
Cross-platform mobile Neural network C library for training and inference on the device. CPU only. It fits for time-series data.
As part of a bigger work, this work focuses on implementing MLPs and Batch Normalization with Numpy and Python only.
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
Code to fold batch norm layer of a DNN model in pytorch
MXNet implementation of Filter Response Normalization Layer (FRN) published in CVPR2020
Digit recognition neural network using the MNIST dataset. Features include a full gui, convolution, pooling, momentum, nesterov momentum, RMSProp, batch normalization, and deep networks.
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
Add a description, image, and links to the batchnorm topic page so that developers can more easily learn about it.
To associate your repository with the batchnorm topic, visit your repo's landing page and select "manage topics."