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。

Dynamic Routing Between Capsules

dwSun 2018-02-06 16:16
A capsule is a group of neurons whose activity vector represents the instantiation parameters of a specific type of entity such as an object or an object part. We use the length of the activity vector

Python学习记录笔记

晓宇咿呀呀 2019-06-15 15:21
学习一门语言 1、了解(特点、应用场景、历史) 2、目的(完成小程序) 3、安装环境 4、基本语法 5、数据存储(分子原子----二进制) 6、面向对象 7、高级特性 8、框架 9、项目 计算机,利用逻辑语言来模拟现实(分子、原子) 逻辑、动作

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

Bilinear CNNs for Fine-grained Visual Recognition

dwSun 2018-01-15 20:17
We present a simple and effective architecture for fine-grained visual recognition called Bilinear Convolutional Neural Networks (B-CNNs). These networks represent an image as a pooled outer product

人民币面值识别 热身赛经验分享

小康康 2019-05-31 20:30
RMB面值识别: 先明确这是一个图像分类问题,自然而然地就会想到经典的图像分类网络,比如结构较为简单的VGG,稍微复杂的Resnet和Dense,Inception 明确可以用到的模型后,再来看任务内容,识别人民币面值,从提供的数据集可以看到,其实肉眼是很容易区分开的,说明分类任务其实没那么复杂,经过卷积神经网络提取特征后,类间差异是比较大的,所以可以用Inception解决问题。 我最后采用了I
250 0 0

Rethinking the Inception Architecture for Computer Vision

辉仔 2018-01-10 11:10
Convolutional networks are at the core of most state-of-the-art computer vision solutions for a wide variety of tasks. Since 2014 very deep convolutional networks started to become mainstream, yieldin

Residual Attention Network for Image Classification

dwSun 2018-01-15 20:43
In this work, we propose "Residual Attention Network", a convolutional neural network using attention mechanism which can incorporate with state-of-art feed forward network architecture in an end-to-e

OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

辉仔 2018-01-10 10:21
We present an integrated framework for using Convolutional Networks for classification, localization and detection. We show how a multiscale and sliding window approach can be efficiently implemented

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
关注微信公众号