使用tensorflow对Mnist数据集进行字体识别

最新推荐文章于 2023-06-06 10:51:53 发布

a_step_further

最新推荐文章于 2023-06-06 10:51:53 发布

阅读量849

点赞数

分类专栏：菜鸟练习本

本文链接：https://blog.csdn.net/a_step_further/article/details/54917576

版权

菜鸟练习本专栏收录该内容

8 篇文章 0 订阅

订阅专栏

上代码：

#!/usr/bin/env python
#coding:utf-8

import tensorflow
import pandas as pd
import skflow

train = pd.read_csv('~/Mnist/train.csv')
X_train = train.drop('label',1)
y_train = train['label']

classifier = skflow.TensorFlowLinearClassifier(n_classes=10,batch_size=100,steps=1000,learning_rate=0.01)
classifier.fit(X_train,y_train)
linear_y_predict = classifier.predict(X_test)


#save results for submission onto Kaggle
linear_submission = pd.DataFrame({'ImageId':range(1,28001),'label':linear_y_predict})
linear_submission.to_csv('~/Mnist/linear_submission.csv',index=False)