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 vote263 views1 answer
Python json nan
Python
1 vote244 views2 answers
How to find rows with missing data in pandas
Python
5 votes256 views2 answers
How to empty a text file in python
Python
4 votes277 views2 answers
Pil python image
Python
0 vote245 views1 answer
Dataframe to ftp
Python
4 votes278 views4 answers
Median in python
Python
1 vote265 views1 answer
Slicing lexicographically pandas
Python
0 vote282 views1 answer
Doomsday fuel foobar
Python
1 vote256 views2 answers
Get index of element in numpy array python
Python
42 votes269 views3 answers
Python get command line arguments
Python