(l-onnx-doc-Mish)=

# Mish


(l-onnx-op-mish-22)=

## Mish - 22

### Version

- **name**: [Mish (GitHub)](https://github.com/onnx/onnx/blob/main/docs/Operators.md#Mish)
- **domain**: `main`
- **since_version**: `22`
- **function**: `True`
- **support_level**: `SupportType.COMMON`
- **shape inference**: `True`

This version of the operator has been available
**since version 22**.

### Summary

Mish: A Self Regularized Non-Monotonic Neural Activation Function.

Perform the linear unit element-wise on the input tensor X using formula:

```
mish(x) = x * tanh(softplus(x)) = x * tanh(ln(1 + e^{x}))
```

#### Function Body

The function definition for this operator.

```
<
  domain: "",
  opset_import: ["" : 22]
>
Mish (X) => (Y)
{
   Softplus_X = Softplus (X)
   TanHSoftplusX = Tanh (Softplus_X)
   Y = Mul (X, TanHSoftplusX)
}
```

### Inputs

- **X** (heterogeneous) - **T**:

  Input tensor

### Outputs

- **Y** (heterogeneous) - **T**:

  Output tensor

### Type Constraints

* **T** in ( `tensor(bfloat16)`, `tensor(double)`, `tensor(float)`, `tensor(float16)` ):

  Constrain input X and output types to float tensors.

```{toctree}
text_diff_Mish_18_22
```

(l-onnx-op-mish-18)=

## Mish - 18

### Version

- **name**: [Mish (GitHub)](https://github.com/onnx/onnx/blob/main/docs/Operators.md#Mish)
- **domain**: `main`
- **since_version**: `18`
- **function**: `True`
- **support_level**: `SupportType.COMMON`
- **shape inference**: `True`

This version of the operator has been available
**since version 18**.

### Summary

Mish: A Self Regularized Non-Monotonic Neural Activation Function.

Perform the linear unit element-wise on the input tensor X using formula:

```
mish(x) = x * tanh(softplus(x)) = x * tanh(ln(1 + e^{x}))
```

#### Function Body

The function definition for this operator.

```
<
  domain: "",
  opset_import: ["" : 18]
>
Mish (X) => (Y)
{
   Softplus_X = Softplus (X)
   TanHSoftplusX = Tanh (Softplus_X)
   Y = Mul (X, TanHSoftplusX)
}
```

### Inputs

- **X** (heterogeneous) - **T**:

  Input tensor

### Outputs

- **Y** (heterogeneous) - **T**:

  Output tensor

### Type Constraints

* **T** in ( `tensor(double)`, `tensor(float)`, `tensor(float16)` ):

  Constrain input X and output types to float tensors.