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 vote331 views1 answer
Pandas corr get couple value
Python
0 vote331 views1 answer
How to use list compression with conditional formatting
Python
0 vote329 views1 answer
Open word from python
Python
0 vote302 views1 answer
Access field values of form django
Python
12 votes342 views4 answers
Merge three dataframes pandas based on column
Python
3 votes292 views1 answer
Datetime.timedelta months
Python
1 vote347 views1 answer
How do i print when my bot is ready in discord.py
Python
2 votes295 views1 answer
Pandas series select first value
Python
1 vote338 views2 answers
Merge a list of dictionaries python
Python
2 votes294 views1 answer
Timedelta year python
Python