Implementations of different loss-correction techniques to help deep models learn under class-conditional label noise.
-
Updated
Feb 15, 2021 - Python
Implementations of different loss-correction techniques to help deep models learn under class-conditional label noise.
Tensorflow Implementation of Visualization Regularizers for Neural Network based Image Recognition
Classification using a Multi-Layer Perceptron neural network from scratch
Comprehensive image classification for training multilayer perceptron (MLP), LeNet, LeNet5, conv2, conv4, conv6, VGG11, VGG13, VGG16, VGG19 with batch normalization, ResNet18, ResNet34, ResNet50, MobilNetV2 on MNIST, CIFAR10, CIFAR100, and ImageNet1K.
One-offs.
Implementation of optimization and regularization algorithms in deep neural networks from scratch
ResNet for CIFAR with Estimator API and tf.keras.Model class
An easy template for Cifar classification using Pytorch
Introduction to Convolutional Neural Network (CNN) and investigating the effects of its parameters on how the network works
Connection Reduction of DenseNet for Image Recognition
Cifar with Noisy from Human or Synthesis
A reproduction of Learning Efficient Convolutional Networks through Network Slimming
Experience CIFAR-Net, a streamlined Python solution for classifying CIFAR-10 images with precision. Train, test, and predict effortlessly using our efficient CNN architecture and automation scripts. Dive into diverse datasets, make accurate predictions, and redefine image classification with ease! 🌟
为了一劳永逸地解决 CIFAR 数据集模型训练问题,本文借鉴了多篇论文的模型训练代码,编写了基于 pytorch 的 CIFAR 数据集模型训练框架(在此我们简单的将该框架称为 CMTF)。在代码编写过程中,我发现 CMTF 可能对低性能的 GPU 设备更友好。CMTF 采用简单高效的训练配置,具有清晰的 log 风格,支持 VGG(VGG11、13、16、19及其带Batchnormal版本)和 ResNET(ResNet20、32、44、56、110)架构的训练。目前在CIFAR10上训练了 VGG16BN 和 ResNet20 模型上得到了checkpoint,获得了不低于一些学术论文的baseline精度。此外,CMTF 不需设置多卡并行计算,仅需简单操作即可添加新的模型结构
base backbone model
Implementaiton of BSC-Densenet-121 in Pytorch from research paper "Adding Binary Search Connections to Improve DenseNet Performance".
Some useful examples of Deep Learning (.py)
Add a description, image, and links to the cifar topic page so that developers can more easily learn about it.
To associate your repository with the cifar topic, visit your repo's landing page and select "manage topics."