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 vote148 views1 answer
Transformer un dictionnaire en liste python
Python
0 vote192 views1 answer
Two input string sum in django
Python Django
6 votes145 views2 answers
Python 2d array append
Python
0 vote166 views1 answer
Python slice second element of list of lists
Python
0 vote150 views1 answer
How to write a table from 1 to 10 with for loop in fython in 3 lines
Python
3 votes155 views2 answers
How to print anything in python
Python
0 vote107 views1 answer
Python main.py
Python
1 vote150 views1 answer
Mypy ignore line
Python
3 votes189 views1 answer
Disable csrf for one url django
Python
39 votes147 views2 answers
Python file from path
Python