Comments (10)
让学习后的模型去识别2015年的验证码,相似图过滤后认为有60K~张不同的图片,列出它自信度超过98%的图片,其中约有6K张。
一些有趣的错误
from easy12306.
能不能把真假识别器合并进来,让其有回答"我不知道这是什么"的能力。
从我的直觉上来说,我觉得这是至关重要的能力,因为模型是将整体图片区间(包括仅仅是噪音的图)映射到类别列表,然而显然整体空间的大量内容都是未知的。
一步步来,先试着生成英文验证码,让机器回答说:“不知道这是什么词”。
我觉得应该让机器自己学会如何回答"我不知道"。例如我根本不知道这世上还有多少知识是自己不知道的。
from easy12306.
https://www.pyimagesearch.com/2018/04/16/keras-and-convolutional-neural-networks-cnns/
尝试为我们的模型减减肥吧。
from easy12306.
能不能让机器仅仅根据无噪音的文字图学习,最终还能识别有噪音的文字图呢?
https://www.youtube.com/watch?v=XnyM3-xtxHs&list=PLJV_el3uVTsOK_ZK5L0Iv_EQoL1JefRL4
from easy12306.
准备绘画热力图
from keras.applications.vgg16 import preprocess_input, decode_predictions
- https://github.com/keras-team/keras-applications/blob/master/keras_applications/imagenet_utils.py
- tensorflow/models#517
from easy12306.
新一代的识别力度
[0.12332161949947161, 0.9914363235543496]
[0.07605954375682149, 0.9907580125487536]
[0.04957617516017413, 0.9917754790571477]
[0.05738099154772871, 0.9961845005935221]
[0.044536791779119844, 0.9945735119552315]
[0.061249691417495415, 0.995506189587926]
from easy12306.
这样如何?
依旧用哈希算法来查询图片类型,如果查不到相似的再让深度网络来识别。
from easy12306.
让机器根据哈希统计学结论来学习,之后冲洗哈希库,会怎样呢,哈希的识别力度会提升吗?
from easy12306.
能不能让深入学习后的机器开始怀疑训练集中某样本是错误的呢?不仅让机器根据训练集来学习,而且还要超越训练集。
我人工检测了深入学习后的机器在训练集上犯下的错误,总共统计学专家认定的错误有102个,而我认为其中只有4个是真正的错误,其余98个都是统计学的误差导致的。4个真正的错误中,有3个是统计学提供的答案本身也是错误的,而另一个则是犯下了严重的错误,统计学提供的是正确样本。
from easy12306.
统计出错,但机器能给出正确答案的例子:
这种图片是不是在我国很流行,因此非常容易获得?从而导致统计量上不去…
from easy12306.
Related Issues (20)
- 我下载你的数据,自己跑跟你在线接口差距这么大? HOT 1
- 人工提供的验证集image.test.npz没有啊,只有image.npz还用不了 HOT 1
- the model was *not* compiled. Compile it manually HOT 4
- 深度学习需要哪些基础知识? HOT 2
- 好想抛弃百度,让机器仅仅根据验证码本身来学习 HOT 24
- 杂乱的秒记 HOT 23
- tensorflow版本 HOT 8
- pretreatement.py的函数download_image()中url失效了,不知道还有没有更新。 HOT 2
- 程序员提高自我修养的技能
- 如何完整地跑一遍代码 HOT 19
- 百度网盘链接挂了
- error: (-215:Assertion failed) channels == 1 || channels == 3 || channels == 4 in function 'cv::imencode'
- 为啥在线调用都不成功 HOT 1
- 训练过程
- captcha.npz数据集生成问题 HOT 6
- 文字识别在texts.npy的评价指标 HOT 1
- OSError: SavedModel file does not exist at: model.h5/{saved_model.pbtxt|saved_model.pb} HOT 1
- cann't deploy your easy122306 successfully on my PC HOT 4
- 我把main.py改造成了 api,结果至少需要2s才能返回。。 HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from easy12306.