How to use 'keras confusion matrix' in Python
Every line of 'keras confusion matrix' code snippets is scanned for vulnerabilities by our powerful machine learning engine that combs millions of open source libraries, ensuring your Python code is secure.
By copying the Snyk Code Snippets you agree to
this disclaimer
16 @property 17 def numpy(self): 18 return self._matrix.numpy()
Important
Use secure code every time
Secure your code as it's written. Use Snyk Code to scan source code in minutes – no build needed – and fix issues immediately. Enable Snyk Code
4 def th_confusion_matrix(y_true: torch.Tensor, y_pred: torch.Tensor, num_classes=None): 5 """ 6 7 Args: 8 y_true: 1-D tensor of shape [n_samples] 9 y_pred: 1-D tensor of shape [n_samples] 10 num_classes: scalar 11 Returns: 12 13 """ 14 size = [num_classes + 1, num_classes + 1] if num_classes is not None else None 15 y_true = y_true.float() 16 y_pred = y_pred.float() 17 if size is None: 18 cm = torch.sparse_coo_tensor(indices=torch.stack([y_true, y_pred], dim=0), values=torch.ones_like(y_pred)) 19 else: 20 cm = torch.sparse_coo_tensor(indices=torch.stack([y_true, y_pred], dim=0), values=torch.ones_like(y_pred), 21 size=size) 22 return cm.to_dense()[1:, 1:]