Kai (Kazuya Ito)

`NEAREST_EXACT` and `BICUBIC` work against the doc of `AutoAugment()`

2

### 🐛 Describe the bug [The doc](https://docs.pytorch.org/vision/main/generated/torchvision.transforms.v2.AutoAugment.html) of `AutoAugment()` says that only `NEAREST` and `BILINEAR` are supported: > Parameters: > ... > - interpolation (InterpolationMode, optional) – ... If input...

`NEAREST_EXACT` and `BICUBIC` work against the doc of `TrivialAugmentWide()`

2

### 🐛 Describe the bug [The doc](https://docs.pytorch.org/vision/main/generated/torchvision.transforms.v2.TrivialAugmentWide.html) of `TrivialAugmentWide()` says that only `NEAREST` and `BILINEAR` are supported: > Parameters: > ... > - interpolation (InterpolationMode, optional) – ... If input...

`NEAREST_EXACT` and `BICUBIC` work against the doc of `RandAugment()`

2

### 🐛 Describe the bug [The doc](https://docs.pytorch.org/vision/master/generated/torchvision.transforms.v2.RandAugment.html) of `RandAugment()` says that only `NEAREST` and `BILINEAR` are supported: > Parameters: > ... > - interpolation (InterpolationMode, optional) – ... If input...

`BICUBIC` works against the doc of `ElasticTransform()`

2

### 🐛 Describe the bug [The doc](https://pytorch.org/vision/main/generated/torchvision.transforms.v2.ElasticTransform.html) of `ElasticTransform()` says that only `NEAREST` and `BILINEAR` are supported: > Parameters: > ... > - interpolation (InterpolationMode, optional) – ... If input...

`interpolation` parameter of `AugMix()` wrongly explains `Default is InterpolationMode.NEAREST` instead of `InterpolationMode.BILINEAR`

2

### 📚 The doc issue According to [the source code](https://docs.pytorch.org/vision/main/_modules/torchvision/transforms/v2/_auto_augment.html#AugMix) of `AugMix()`, the default type of `interpolation` parameter is `BILINEAR` as shown below: ```python def __init__( self, severity: int =...

Setting `0` and `1` to `p` argument of `RandomAutocontrast()` gets the same results

2

### 🐛 Describe the bug Setting `0` and `1` to `p` argument of [RandomAutocontrast()](https://pytorch.org/vision/main/generated/torchvision.transforms.v2.RandomAutocontrast.html) gets the same results as shown below: ```python from torchvision.datasets import OxfordIIITPet from torchvision.transforms.v2 import RandomAutocontrast...

Setting a list of no transforms to `transforms` argument of `RandomApply()` gets the indirect error message

1

### 📚 The doc issue Setting a list of no transforms to `transforms` argument of [RandomApply()](https://pytorch.org/vision/main/generated/torchvision.transforms.v2.RandomApply.html) gets the indirect error message as shown below. *You can see [this issue](https://github.com/pytorch/vision/issues/9023) as...

The explanation for `all_ops` parameter of `AugMix()` is not clear enough.

1

### 📚 The doc issue [The doc](https://pytorch.org/vision/main/generated/torchvision.transforms.v2.AugMix.html) of `AugMix()` explains `all_ops` parameter as shown below but it's not clear enough: > Parameters: > ... > - all_ops ([bool](https://docs.python.org/3/library/functions.html#bool), optional) –...

Setting a float value to `magnitude` argument of `RandAugment()` gets the wrong error message

1

### 🐛 Describe the bug Setting a float value to `magnitude` argument of [RandAugment()](https://pytorch.org/vision/master/generated/torchvision.transforms.v2.RandAugment.html) gets the wrong error message as shown below: ```python from torchvision.datasets import OxfordIIITPet from torchvision.transforms.v2 import...

Setting `-5` and `5` to `sharpness_factor` argument of `RandomAdjustSharpness()` sharpens and blurs images respectively

1

### 📚 The doc issue [The doc](https://pytorch.org/vision/main/generated/torchvision.transforms.v2.RandomAdjustSharpness.html) of `RandomAdjustSharpness()` says below: > Adjust the sharpness of the image or video with a given probability. > ... > Parameters: > -...