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 vote159 views1 answer
Python pass string with spaces as argument
Python
0 vote177 views1 answer
Hash python png
Python
2 votes171 views1 answer
8 ball responses list python
Python
22 votes153 views2 answers
Python remove last element from list
Python
0 vote175 views1 answer
One2many add tuple
Python
20 votes160 views6 answers
List input python
Python
0 vote169 views1 answer
Python global variable unboundlocalerror
Python
0 vote161 views1 answer
Break input loop
Python
0 vote207 views1 answer
Matplotlib pyplot comment on plot
Python
29 votes350 views4 answers
Basic flask app python
Python Flask