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 vote286 views1 answer
Push to pypi
Python
16 votes239 views5 answers
Fibonacci series
Python
0 vote274 views1 answer
Django collectstatic with auto yes
Python Django
0 vote232 views1 answer
Extract nonzero array elements python
Python
0 vote226 views1 answer
What is a console in pythonanywhere
Python
0 vote240 views1 answer
Tensorfow list devices
Python
3 votes260 views2 answers
Python find location of module
Python
0 vote248 views1 answer
How to find number of categories in python
Python
0 vote235 views1 answer
Procfile heroku python example
Python
13 votes251 views4 answers
Python get screen size
Python