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 vote293 views1 answer
Can we use python functions in node
Python
16 votes235 views8 answers
Curl in python
Python
2 votes266 views2 answers
.encode python
Python
17 votes281 views2 answers
Python calculate factorial
Python
0 vote333 views1 answer
Django.com
Python Django
6 votes282 views1 answer
Python append a file and read
Python
1 vote527 views2 answers
SyntaxError: Non-UTF-8 code starting with
Python
0 vote345 views1 answer
Python frozenset()
Python
1 vote307 views2 answers
ImportError: No module named easydict
Python
0 vote295 views1 answer
How to define number in python
Python