Existing deep convolutional neural networks (CNNs) require a fixed-size (e.g., 224224) input image. This requirement is “artificial” and may reduce the recognition accuracy for the images or sub-images of an arbitrary size/scale. In this work, we eq
再思考计算机视觉的Inception结构 Rethinking the inception architecture for computer vision (2016) 作者C. Szegedy et al. 摘要：对于多种任务来说，卷及网络处于最先进的计算机视觉解决方案的核心。自2014年以来，超深度卷积网络开始成为主流，在各种benchmark中产生了巨大的收获。虽然对大多数任务来说，增加的模型大小和计算成本往往转化为直接增益（只要提供足够的标记数据用于训练），计算效率和低参数计数仍然是
Rethinking the Inception Architecture for Computer Vision 重新思考计算机视觉的初始架构 Christian Szegedy， Vincent Vanhoucke， Sergey Ioffe， Jonathon Shlens， Zbigniew Wojna （2015年12月2日提交（v1），最近于2015 年12月11日修订（本版本v3）） 卷积网络是大多数最先进的计算机视觉解决方案的核心，用于各种各样的任务。自2014年以来，非常深入
We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0%
Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functio
图像视觉领域的深度学习资料，手把手教你搭建自己的神经网络，让你从实践中深入浅出地学习各种经典神经网络知识。亲试不错，分享之！Deep learning for Computer Vision with
Python
Starter Bundle
Dr. Adrian rosebrock
Ist Edition(1. 1.0)
Copyright(c2017AdrianRosebrock,PylmageSearch.com
PUBLISHED BY PYIMAGESEARCH
PYIMAGESE
Deep Residual Networks
Deep Learning Gets Way DeeperIntroduction
Introduction
Deep residual Networks (resEts
Deep Residual Learning for Image Recognition". CVPR 2016 (next week)
A simple and clean framework of training very"deep nets
State-of-the-ar
