riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-31 02:02:21 +06:00
Code Issues Actions 23 Packages Projects Releases Wiki Activity

fix variable undefined bug when return_tensors is not specified in llava processing (#34953)

Browse Source 
* fix variable undefined bug when return_tensors is not specified in llava processor

* improve readability
This commit is contained in:
Weize Chen 2024-12-02 18:44:42 +08:00 committed by GitHub
parent 3480cbb97e
commit 9ab8c5b503
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 6 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/transformers/models/llava_next/processing_llava_next.py
View File

@ -165,7 +165,8 @@ class LlavaNextProcessor(ProcessorMixin):
image_size = next(image_sizes)
if not isinstance(image_size, (list, tuple)):
# cast to list to avoid numerical precision errors when calculating unpadding
orig_height, orig_width = image_size.tolist()
image_size = image_size.tolist()
orig_height, orig_width = image_size
num_image_tokens = self._get_number_of_features(orig_height, orig_width, height, width)
if self.vision_feature_select_strategy == "default":
num_image_tokens -= self.num_additional_image_tokens

3
src/transformers/models/llava_next_video/processing_llava_next_video.py
View File

@ -192,7 +192,8 @@ class LlavaNextVideoProcessor(ProcessorMixin):
image_size = next(image_sizes)
if not isinstance(image_size, (list, tuple)):
# cast to list to avoid numerical precision errors when calculating unpadding
orig_height, orig_width = image_size.tolist()
image_size = image_size.tolist()
orig_height, orig_width = image_size
num_image_tokens = self._get_number_of_features(orig_height, orig_width, height, width)
if self.vision_feature_select_strategy == "default":
num_image_tokens -= self.num_additional_image_tokens

3
src/transformers/models/llava_onevision/processing_llava_onevision.py
View File

@ -191,7 +191,8 @@ class LlavaOnevisionProcessor(ProcessorMixin):
original_size = image_size_list[0] if num_frames != 1 else image_size_list
if not isinstance(original_size, (list, tuple)):
# cast to list to avoid numerical precision errors when calculating unpadding
orig_height, orig_width = original_size.tolist()
original_size = original_size.tolist()
orig_height, orig_width = original_size
num_image_tokens = self._get_number_of_features(orig_height, orig_width, height, width)
if self.vision_feature_select_strategy == "default":
num_image_tokens -= 1