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 vote266 views1 answer
Add x=y line to scatter plot python
Python
2 votes226 views1 answer
Np logical_or
Python
0 vote197 views1 answer
Check if environment variable exists
Python
2 votes255 views1 answer
Make a script run itself again python
Python
16 votes242 views4 answers
Python remove last instance of a list
Python
5 votes221 views4 answers
Dropna for specific column pandas
Python
0 vote232 views1 answer
Using django model translation with django rest
Python
0 vote221 views1 answer
Python soma números
Python
0 vote258 views1 answer
Django queryset group by sum
Python Django
8 votes226 views2 answers
Python count files directory
Python