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

1 vote131 views1 answer
Edge driver selenium python
Python
0 vote138 views1 answer
Taking a list of strings as input, our matching function returns the count of the number of strings whose first and last chars of the string are the same. Also, only consider strings with length of 2 or more. python
Python
19 votes146 views5 answers
Conda tensorflow
Python
3 votes173 views1 answer
How to remove integer from string in python
Python
0 vote136 views1 answer
Selenium how to handle element not found python
Python
125 votes143 views6 answers
How to change column name in pandas
Python
0 vote134 views1 answer
Filter list of tuples python
Python
0 vote138 views1 answer
Append time complexity python
Python
0 vote164 views1 answer
Matplotlib.pyplot imshow size
Python
1 vote140 views2 answers
Pandas docs
Python