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 vote167 views1 answer
Program to add first and last digit of a number in python
Python
2 votes115 views10 answers
Python turtle tutorial
Python
1 vote124 views1 answer
Print(DATA.popitem())
Python
4 votes152 views3 answers
Django Change Password
Python Django
0 vote144 views1 answer
Run multiple function with multiprocessing python
Python
-1 vote132 views2 answers
Encode url
Python
0 vote141 views1 answer
After groupby how to add values in two rows to a list
Python
0 vote151 views1 answer
Alan watts
Python
0 vote130 views2 answers
Dataframe change specicf values in column
Python
1 vote133 views1 answer
How to convert tuple into list in python
Python