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

0 vote191 views1 answer
Destructuring in for loops python
Python
0 vote181 views1 answer
Rnadom number python
Python
0 vote224 views1 answer
Flask on gevent over https
Python Flask
-2 votes170 views1 answer
Python same values in two lists
Python
2 votes199 views1 answer
Lower upper in pytho
Python
1 vote180 views1 answer
Django queryset first element
Python
0 vote211 views1 answer
Form valid django created by
Python Django
0 vote174 views1 answer
Extract all namespace from xml file python
Python
0 vote175 views1 answer
What is type
Python
0 vote168 views7 answers
Online python compailer
Python