人民币面值识别(附源码)-InceptionResNetV2

李劳(Felix) 2019-06-02 15:26
人民币面值识别, InceptionResNetV2

深入卷积神经网络背后的数学原理

AI科技大本营 2019-04-23 11:27
本文对卷积神经网络的数学原理进行了介绍

SE-Inception v3架构的模型搭建(keras代码实现)

Mark 2018-09-28 16:47
2017年ImagNet冠军架构得主的精髓之处SENet架构(Squeeze And Excitation),关于细节处不再多说,只是该架构的基本结构图,和代码实现。并且代码实现此处是googleNet的Inception v3架构为基础加上SE的结构。

pytorch应用之——纸币识别(一)

飞翔 2019-05-31 17:22
这里数据集一共有39620张,而且背景单一,所以纸币面值的识别不是一个很难的问题。我用resnet18(自己稍微改了一些结构,影响不大)去训练这个数据集,迭代24次可以达到99.96%的精度。

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

jixiaohui 2018-01-10 14:52
We present a class of efficient models called MobileNets for mobile and embedded vision applications. MobileNets are based on a streamlined architecture that uses depth-wise separable convolutions to

TinyMind人民币编码识别挑战赛-经验分享

mind_programmonkey 2019-05-31 20:54
简单卷积神经网络实现人民币实现

TinyMind人民币编码识别挑战赛-热身赛分享

腾古 2019-05-31 17:16
采用VGG-16网络达到100%准确度

【经验分享】TinyMind 多标签图像分类竞赛小试牛刀——by:for the dream

stawary 2018-08-21 18:45
TinyMind 多标签图像分类竞赛从处理到提交流程

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

辉仔 2018-01-10 10:49
Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the trai

Fully Convolutional Networks for Semantic Segmentation

辉仔 2018-01-10 10:46
Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, exceed the state-of-the-a
关注微信公众号