第25月第9天 tf_tang_poems kaggle

1.neural-style

https://github.com/anishathalye/neural-style

wget http://www.vlfeat.org/matconvnet/models/beta16/imagenet-vgg-verydeep-19.mat

python neural_style.py --content examples/1-content.jpg --styles examples/1-style.jpg --output examples/myoutput.jpg --network ../neural-style-mat/imagenet-vgg-verydeep-19.mat

　　

https://www.cnblogs.com/lijingpeng/p/6009476.html

2.生成诗词和歌词

tensorflow 1.0
python3.5

https://github.com/charlesXu86/tf_tang_poems/

在开发过程，特别是clone项目时在PyCharm中经常出现Unresolved Reference问题，对于有强迫症的人来说，简直不可忍受。

1. 进入PyCharm->Preferences->Build,Excution,Deployment->Console->Python Console勾选上Add source roots to PYTHONPATH;
2. 进入PyCharm->Preferences->Project->Project Structure,通过选中某一目录右键添加sources;
3. 点击Apply和OK即可.

https://blog.csdn.net/haiyanggeng/article/details/79215819

3.kaggle

https://github.com/lijingpeng/kaggle

https://www.cnblogs.com/lijingpeng/p/6009476.html

代码运行

regr = RandomForestRegressor(n_estimators=50,max_depth=None,min_samples_split=1,random_state=0)

regr = regr.fit(features_train,ratings_train)

解决方法是: 将第一行中的min_samples_split=1 改为 min_samples_split=1.0

cv=StratifiedShuffleSplit( n_splits=10, test_size=0.2, train_size=None)).fit(train_data, label)