Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[LLaVa-NeXT] Small fixes #30841

Merged
merged 2 commits into from
May 16, 2024
Merged

[LLaVa-NeXT] Small fixes #30841

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
abba16d
First draft
NielsRogge May 15, 2024
c7dc0f4
Update docstring
NielsRogge May 15, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 8 additions & 6 deletions src/transformers/models/llava_next/image_processing_llava_next.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,8 +156,8 @@ class LlavaNextImageProcessor(BaseImageProcessor):
number of channels in the image. Can be overridden by the `image_std` parameter in the `preprocess` method.
Can be overridden by the `image_std` parameter in the `preprocess` method.
do_pad (`bool`, *optional*, defaults to `True`):
Whether to pad the image. If `True` will pad the images in the batch to the largest image in the batch
and create a pixel mask. Padding will be applied to the bottom and right of the image with zeros.
Whether to pad the image. If `True`, will pad the patch dimension of the images in the batch to the largest
number of patches in the batch. Padding will be applied to the bottom and right with zeros.
do_convert_rgb (`bool`, *optional*, defaults to `True`):
Whether to convert the image to RGB.
"""
Expand Down Expand Up @@ -203,6 +203,7 @@ def __init__(
self.do_normalize = do_normalize
self.image_mean = image_mean if image_mean is not None else OPENAI_CLIP_MEAN
self.image_std = image_std if image_std is not None else OPENAI_CLIP_STD
self.do_pad = do_pad
self.do_convert_rgb = do_convert_rgb

# Copied from transformers.models.clip.image_processing_clip.CLIPImageProcessor.resize with CLIP->LLaVa
Expand Down Expand Up @@ -572,7 +573,7 @@ def preprocess(
do_normalize: bool = None,
image_mean: Optional[Union[float, List[float]]] = None,
image_std: Optional[Union[float, List[float]]] = None,
do_pad: Optional[bool] = True,
do_pad: Optional[bool] = None,
do_convert_rgb: bool = None,
return_tensors: Optional[Union[str, TensorType]] = None,
data_format: Optional[ChannelDimension] = ChannelDimension.FIRST,
Expand Down Expand Up @@ -609,9 +610,9 @@ def preprocess(
image_std (`float` or `List[float]`, *optional*, defaults to `self.image_std`):
Image standard deviation to use for normalization. Only has an effect if `do_normalize` is set to
`True`.
do_pad (`bool`, *optional*, defaults to self.do_pad):
Whether to pad the image. If `True` will pad the images in the batch to the largest image in the batch
and create a pixel mask. Padding will be applied to the bottom and right of the image with zeros.
do_pad (`bool`, *optional*, defaults to `self.do_pad`):
Whether to pad the image. If `True`, will pad the patch dimension of the images in the batch to the largest
number of patches in the batch. Padding will be applied to the bottom and right with zeros.
do_convert_rgb (`bool`, *optional*, defaults to `self.do_convert_rgb`):
Whether to convert the image to RGB.
return_tensors (`str` or `TensorType`, *optional*):
Expand Down Expand Up @@ -647,6 +648,7 @@ def preprocess(
do_normalize = do_normalize if do_normalize is not None else self.do_normalize
image_mean = image_mean if image_mean is not None else self.image_mean
image_std = image_std if image_std is not None else self.image_std
do_pad = do_pad if do_pad is not None else self.do_pad
do_convert_rgb = do_convert_rgb if do_convert_rgb is not None else self.do_convert_rgb

images = make_list_of_images(images)
Expand Down
Loading