【Python】利用skorch进行深度学习

最新推荐文章于 2024-07-03 12:00:00 发布

春风惹人醉

最新推荐文章于 2024-07-03 12:00:00 发布

阅读量2.2k

点赞数 2

文章标签：深度学习 python 神经网络 pytorch 人工智能

本文链接：https://blog.csdn.net/godsuner/article/details/116736449

版权

【Python】利用skorch进行深度学习

利用pytorch能够很好地进行私人定制的深度学习，然而torch中的张量总是感觉充满神秘色彩，导致很多时候要进行很久的debug。具有numpy和sklearn特色的skorch应运而生。本文浅尝辄止，仅给出一个实际案例和代码。**

import skorch
from skorch import NeuralNetRegressor

from sklearn.model_selection import RandomizedSearchCV

import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F


class MyModule(nn.Module):
    def __init__(self,num_units=10,nonlin=F.relu,drop=.5):
        super(MyModule,self).__init__()
        
        self.module = nn.Sequential(
            nn.Linear(7,num_units),
            nn.LeakyReLU(),
            nn.Dropout(p=drop),
            nn.Linear(num_units,1),
        )
        
    def forward(self,X):
        X = self.module(X)
        return X
    
    
    
sknet = NeuralNetRegressor(
    MyModule,
    criterion=nn.MSELoss,
    max_epochs=10,
    optimizer=optim.Adam,
    optimizer__lr = .005
)

lr = (10**np.random.uniform(-5,-2.5,1000)).tolist()
params = {
    'optimizer__lr': lr,
    'max_epochs':[300,400,500],
    'module__num_units': [14,20,28,36,42],
    'module__drop' : [0,.1,.2,.3,.4]
}

gs = RandomizedSearchCV(net,params,refit=True,cv=3,scoring='neg_mean_squared_error',n_iter=100)