i also write code properly and some times i am copying form this code but always shows the AttributeError: 'numpy.ndarray' object has no attribute 'to'

[vivek152oo3]

/# Make predictions with the model
untrained_preds = model_0(X_test.to(device))
print(f"Length of predictions: {len(untrained_preds)}, Shape: {untrained_preds.shape}")
print(f"Length of test samples: {len(y_test)}, Shape: {y_test.shape}")
print(f"\nFirst 10 predictions:\n{untrained_preds[:10]}")
print(f"\nFirst 10 test labels:\n{y_test[:10]}")

output
AttributeError Traceback (most recent call last)
in <cell line: 2>()
1 # Make predictions with the model
----> 2 untrained_preds = model_0(X_test.to(device))
3 print(f"Length of predictions: {len(untrained_preds)}, Shape: {untrained_preds.shape}")
4 print(f"Length of test samples: {len(y_test)}, Shape: {y_test.shape}")
5 print(f"\nFirst 10 predictions:\n{untrained_preds[:10]}")

AttributeError: 'numpy.ndarray' object has no attribute 'to'

i am dont understand what type error

[Perian-Yan]

Hi,
I think X_test is ndarray istead of tensor here. You can run X_test.dtype to see its type.
To convert from numpy.ndarray to tensor, you can use torch.from_numpy().
Hope this helps 😄