人工智能『AI』

Alec Radford’s animations for optimization algorithms[FW]

没有评论

Alec Radford has created some great animations comparing optimization algorithms SGD, Momentum, NAG, Adagrad, Adadelta, RMSprop (unfortunately no Adam) on low dimensional problems. Also check out his presentation on RNNs.

“Noisy moons: This is logistic regression on noisy moons dataset from sklearn which shows the smoothing effects of momentum based techniques (which also results in over shooting and correction). The error surface is visualized as an average over the whole dataset empirically, but the trajectories show the dynamics of minibatches on noisy data. The bottom chart is an accuracy plot.”

“Beale’s function: Due to the large initial gradient, velocity based techniques shoot off and bounce around – adagrad almost goes unstable for the same reason. Algos that scale gradients/step sizes like adadelta and RMSProp proceed more like accelerated SGD and handle large gradients with more stability.”

Continue Reading

人工智能『AI』

jupyter notebook 调整字体 以及matplotlib显示中文

没有评论

原生的jupyter theme看起来比较蛋疼，尤其是字体和字号。为了修改这个配置可以安装 jupyter theme。

项目链接： https://github.com/dunovank/jupyter-themes 如果不喜欢英文可以参考这个链接：https://www.jianshu.com/p/6de5f6cce06d

上面的样式对应的配置命令：
jt  -f fira -fs 11 -cellw 90% -ofs 11 -dfs 11 -T -t solarizedl

除此之外matplotlib 默认不支持中文显示，主要是字体问题，可以通过下面的代码配置来让matplotlib 支持中文

from matplotlib import pyplot as plt
%matplotlib inline
font = {'family' : 'MicroSoft YaHei',
'weight' : 'bold',
'size' : 10}
plt.rc("font", **font)

实际效果，另外还可以使用altair ，altair 默认支持中文显示 https://altair-viz.github.io

人工智能『AI』

基于RandomForestClassifier的titanic生存概率分析

没有评论

The Challenge

The sinking of the Titanic is one of the most infamous shipwrecks in history.

On April 15, 1912, during her maiden voyage, the widely considered “unsinkable” RMS Titanic sank after colliding with an iceberg. Unfortunately, there weren’t enough lifeboats for everyone onboard, resulting in the death of 1502 out of 2224 passengers and crew.

While there was some element of luck involved in surviving, it seems some groups of people were more likely to survive than others.

In this challenge, we ask you to build a predictive model that answers the question: “what sorts of people were more likely to survive?” using passenger data (ie name, age, gender, socio-economic class, etc).

这个是kaggle上的一个基础项目，目的是探测泰坦尼克号上的人员的生存概率，项目地址：https://www.kaggle.com/c/titanic

网上基于这个项目其实可以找到各种各样的解决方案，我也尝试了不同的做法。但是实际的效果并不是十分好，个人尝试最好的成绩是0.78468，一次是基于深度神经网络，另外一次就是基于当前的随机森林的模型。

另外还可以看到一系列score为1的提交，这些不知道是怎么做到的，真是太tm牛了~~

Continue Reading

人工智能『AI』

CUDNN_STATUS_NOT_INITIALIZED

一条评论

自从装好tensorflow-gpu 之后其实一直没怎么用，今天跑代码的时候才发现安装的有问题：

测试代码如下：

from sklearn.datasets import load_sample_image
import matplotlib.pyplot as plt
import numpy as np
import tensorflow as tf

if __name__ == '__main__':
    # Load sample images
    china = load_sample_image("china.jpg")
    flower = load_sample_image("flower.jpg")
    dataset = np.array([china, flower], dtype=np.float32)
    batch_size, height, width, channels = dataset.shape
    # Create 2 filters
    filters = np.zeros(shape=(7, 7, channels, 2), dtype=np.float32)
    filters[:, 3, :, 0] = 1 # vertical line
    filters[3, :, :, 1] = 1 # horizontal line
    # Create a graph with input X plus a convolutional layer applying the 2 filters
    X = tf.placeholder(tf.float32, shape=(None, height, width, channels))
    convolution = tf.nn.conv2d(X, filters, strides=[1,2,2,1], padding="SAME")
    with tf.Session() as sess:
        output = sess.run(convolution, feed_dict={X: dataset})
    plt.imshow(output[0, :, :, 1], cmap="gray") # plot 1st image's 2nd feature map
    plt.show()
Continue Reading

人工智能『AI』

Win10 Tensorflow-gpu 不完全安装手册

没有评论

网上随便搜一下就会发现关于Tensorflow-gpu的安装文章非常的多，但是写的都比较简略。并且官网的文档写的也比较的简略，并且google 官网上文档对于windows版本的也非常简略。

官网列出的硬件软件需求如下：

硬件要求

系统支持以下支持 GPU 的设备：

软件要求

必须在系统中安装以下 NVIDIA® 软件：

除此之外就没有更多的信息了，在官方的pip安装说明页面中可以看到windows版本的其实对于python是有要求的，官方支持的版本如下：

Continue Reading
Close Menu