One layer SoftMax Classifier, "Handwriting recognition"
- 2019 年 10 月 7 日
- 筆記
import lib needed¶
In [1]:
from PIL import Image import numpy as np import matplotlib.pyplot as plt import re from glob import glob
begin, load data¶
In [2]:
def load_data(train_path='train/',test_path='test/'): train_list=glob(r'train/*.png') pattern = re.compile(r'num(d).png') train_id = np.array([float(pattern.search(img_name).groups()[0]) for img_name in train_list]) train_data=np.concatenate([np.array(Image.open(img_name)).reshape(1,784) for img_name in train_list],axis=0).astype(np.float) test_list=glob(r'test/*.png') test_id=np.array([float(pattern.search(img_name).groups()[0]) for img_name in test_list]) test_data=np.concatenate([np.array(Image.open(img_name)).reshape(1,784) for img_name in test_list],axis=0).astype(np.float) return train_id,train_data,test_id,test_data
load data, print the shape of data¶
In [3]:
train_id,train_data,test_id,test_data=load_data() train_id.shape,train_data.shape,test_id.shape,test_data.shape
Out[3]:
In [5]:
train_val=np.zeros((train_id.shape[0],10)) for i in range(train_id.shape[0]): train_val[i,train_id[i].astype('int')]=1
split data into minibatches¶
In [6]:
mini_batch_num=100 mini_batch_size=600
define function need, such as softmax, propagation,back_propagation¶
In [7]:
def softmax(x): x=x-np.max(x) #using softmax(x)=softmax(x+c) exp_x=np.exp(x) softmax_x=exp_x/sum(np.exp(x)) return softmax_x
if you want to know more about softmax, https://segmentfault.com/a/1190000010039529?utm_source=tag-newest is recommended to you
use cross entrophy to compute loss, this is part of propagation¶
In [8]:
def propa(train_x,train_y,W,b): #propagation yt=softmax(np.dot(train_x,W)+b) loss=-np.sum(train_y.T.dot(np.log(yt))) #cross entrophy dy=(yt-train_y).T return dy,loss
if you wan to know more about softmax’s cross entrophy, https://blog.csdn.net/lilong117194/article/details/81542667 is recommended to you
update W¶
In [9]:
def back_propa(train_data,train_id,W,b,alpha,data_size): for i in range(data_size): dy,loss=propa(train_data[i,:],train_id[i,:],W,b) dy=dy.reshape(1,10) p=train_data[i,:] p=p.reshape(784,1) dW=alpha*np.dot(p,dy) W-=dW return W,loss
initialize W and b¶
In [14]:
W=np.zeros((784,10)) b=1
loop and update, also print accurancy of our traindataset¶
In [16]:
for i in range(mini_batch_num): for iteration in range(20): lb=(mini_batch_size*i) ub=(mini_batch_size*(i+1)) mini_batch_data=train_data[lb:ub,:] mini_batch_id=train_val[lb:ub,:] W,loss=back_propa(mini_batch_data,mini_batch_id,W,b,0.01,600) count=0 for j in range(600): if np.argmax(softmax(train_data[j,:].dot(W)))==train_id[j].astype('int'): count+=1 acc=count/600 if i%10==0: print('batch={},acc={}'.format(i+1,acc))
predict in the test dataset¶
In [17]:
for j in range(test_id.shape[0]): if np.argmax(softmax(test_data[j,:].dot(W)))==test_id[j].astype('int'): count+=1 acc=count/test_id.shape[0] print(acc)
