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

6 votes262 views1 answer
Display Max rows in a pandas dataframe
Python
0 vote257 views1 answer
Make a coo_matrix
Python
0 vote288 views1 answer
Python replace 0 in series
Python
1 vote263 views1 answer
Pandas aggregate dataframe
Python
62 votes272 views6 answers
Class python
Python
1 vote269 views1 answer
Why when I merge my label cluster with my dataframe i get more row
Python
1 vote292 views1 answer
Create zero array in python
Python
1 vote289 views2 answers
Ast python
Python
4 votes273 views2 answers
Make binary tree in python
Python
0 vote273 views1 answer
Draw pixel by pixel python
Python