这是之前我和我的组员参与Tiny-mind 手写汉字识别大赛的一个项目， 主要实现了用Resnet或VGG16作为Backbone来训练一个分类任务以及基于opencv的一些图片数据集增强，最终我们组的成绩为TOP-5准确率99.19， 排名5/700。这个项目也可以用于其他的图片分类任务，整个网络框架是基于Tensorflow实现的

InceptionV3, InceptionV4, Inception-Resnet pretrained models for Torch7 and PyTorch

ResNet Implementation in TensorFlow

An (re-)implementation of DeepLab v2 (ResNet-101) in TensorFlow for semantic image segmentation on the PASCAL VOC 2012 dataset.

A ResNet(ResNet18, ResNet34, ResNet50, ResNet101, ResNet152) implementation using TensorFlow-2.0.

Simple Tensorflow implementation of pre-activation ResNet18, 34, 50, 101, 152

ResNet-18 TensorFlow Implementation including conversion of torch .t7 weights into tensorflow ckpt

Re-implement Kaiming He's deep residual networks in tensorflow. Can be trained with cifar10.

DeepLab-ResNet rebuilt in TensorFlow