Torch split classes stratified

X = np.random.randn(1000, 2)
y = np.random.randint(0, 10, size=1000)

X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.1, stratify=y)
np.unique(y_train, return_counts=True)
np.unique(y_val, return_counts=True)

train_dataset = Dataset(X_train, y_train, ...)
train_loader = DataLoader(train_dataset, ...)

Source: discuss.pytorch.org

Similar codes

5 votes172 views1 answer
Rolling average df
Python
4 votes181 views4 answers
Foreach loop in python
Python
0 vote164 views1 answer
Python how to get project location
Python
0 vote174 views1 answer
Google sheet api python
Python
0 vote203 views1 answer
Mean =[0,0] covariance = [[1,0],[0,100]] ds = np.random.multivariate_normal(mean,covariance,500) dframe = pd.DataFrame(ds, columns=['col1', 'col2']) fig = sns.kdeplot(dframe).get_figure() fig.savefig('kde1.png')
Python
4 votes168 views1 answer
Python check if value in string
Python
0 vote148 views1 answer
Django multiple search fields
Python
1 vote199 views1 answer
Requirements.py for flask
Python Flask
2 votes186 views3 answers
Area of a circle in python
Python
1 vote208 views1 answer
Managin media django
Python Django