eazygrad¶
Top-level API¶
Tensor Object¶
Tensor Creation¶
Create a tensor from a Python scalar, list, or NumPy array. |
|
Create a tensor that shares storage with an existing NumPy array. |
|
Return a tensor filled with samples from the standard normal distribution. |
|
Return a tensor filled with samples from a uniform distribution. |
|
Return a tensor filled with ones. |
|
Return a tensor filled with zeros. |
Optimization¶
Autograd Control¶
Decorator that disables gradient tracking inside a function. |
|
Context manager that temporarily disables gradient tracking. |