# tensorplay.autograd.gradcheck.gradcheck

Source: https://www.tensorplay.cn/docs/generated/tensorplay.autograd.gradcheck.gradcheck.html

```python
tensorplay.autograd.gradcheck.gradcheck(func, inputs, *, eps: float = 1e-06, atol: float = 1e-05, rtol: float = 0.001, raise_exception: bool = True, nondet_tol: float = 0.0, check_undefined_grad: bool = True, check_grad_dtypes: bool = False, check_batched_grad: bool = False, check_batched_forward_grad: bool = False, check_forward_ad: bool = False, check_backward_ad: bool = True, fast_mode: bool = False, masked: bool | None = None) → bool
```

Check gradients computed via small finite differences against analytical
gradients wrt tensors in inputs that are of floating point or complex type
and with requires_grad=True.

The check between numerical and analytical gradients uses allclose().

For most of the complex functions we consider for optimization purposes, no notion of
Jacobian exists. Instead, gradcheck verifies if the numerical and analytical values of
the Wirtinger and Conjugate Wirtinger derivatives are consistent. Because the gradient
computation is done under the assumption that the overall function has a real-valued
output, we treat functions with complex output in a special way. For these functions,
gradcheck is applied to two real-valued functions corresponding to taking the real
components of the complex outputs for the first, and taking the imaginary components
of the complex outputs for the second.

> **Note**
>
> The default values are designed for input of double precision. This check will likely fail if input is of less precision, e.g., FloatTensor.

> **Note**
>
> Gradcheck may fail when evaluated on non-differentiable points because the numerically computed gradients via finite differencing may differ those computed analytically (not necessarily because either is incorrect).

> **Warning**
>
> If any checked tensor in input has overlapping memory, i.e., different indices pointing to the same memory address (e.g., from expand), this check will likely fail because the numerical gradients computed by point perturbation at such indices will change values at all other indices that share the same memory address.

Parameters:

- func (function) – a Python function that takes Tensor inputs and returns a Tensor or a tuple of Tensors

- inputs ([tuple](https://docs.python.org/3/builtins/stdtypes.html#tuple) of [Tensor](/docs/generated/tensorplay.Tensor.html#tensorplay.Tensor) or [Tensor](/docs/generated/tensorplay.Tensor.html#tensorplay.Tensor)) – inputs to the function

- eps ([float](https://docs.python.org/3/builtins/functions.html#float), optional) – perturbation for finite differences

- atol ([float](https://docs.python.org/3/builtins/functions.html#float), optional) – absolute tolerance

- rtol ([float](https://docs.python.org/3/builtins/functions.html#float), optional) – relative tolerance

- raise_exception ([bool](https://docs.python.org/3/builtins/functions.html#bool), optional) – indicating whether to raise an exception if the check fails. The exception gives more information about the exact nature of the failure. This is helpful when debugging gradchecks.

- nondet_tol ([float](https://docs.python.org/3/builtins/functions.html#float), optional) – tolerance for non-determinism. When running identical inputs through the differentiation, the results must either match exactly (default, 0.0) or be within this tolerance.

- check_undefined_grad ([bool](https://docs.python.org/3/builtins/functions.html#bool), optional) – if True, check if undefined output grads are supported and treated as zeros, for Tensor outputs.

- check_grad_dtypes ([bool](https://docs.python.org/3/builtins/functions.html#bool), optional) – if True, check that the gradient dtypes match the ones from the numerical computation. Defaults to False.

- check_batched_grad ([bool](https://docs.python.org/3/builtins/functions.html#bool), optional) – if True, check if we can compute batched gradients using tensorplay.vmap(). Defaults to False.

- check_batched_forward_grad ([bool](https://docs.python.org/3/builtins/functions.html#bool), optional) – if True, checks if we can compute batched forward gradients using forward ad and tensorplay.vmap(). Defaults to False.

- check_forward_ad ([bool](https://docs.python.org/3/builtins/functions.html#bool), optional) – if True, check that the gradients computed with forward mode AD match the numerical ones. Defaults to False.

- check_backward_ad ([bool](https://docs.python.org/3/builtins/functions.html#bool), optional) – if False, do not perform any checks that rely on backward mode AD to be implemented. Defaults to True.

- fast_mode ([bool](https://docs.python.org/3/builtins/functions.html#bool), optional) – if True, compare the jacobians projected onto random vectors instead of element by element, which costs one backward (or forward) pass per output instead of one per output element. Defaults to False.

- masked ([bool](https://docs.python.org/3/builtins/functions.html#bool), optional) – if True, the gradients of unspecified elements of sparse tensors are ignored. Defaults to False.

Returns:

True if all differences satisfy allclose condition