OpenMOSS-Team
/

MOSS-VL-Instruct-0708

Video-Text-to-Text

feature-extraction

Video-Understanding

Image-Understanding

vision-language

Model card Files Files and versions

CCCCyx commited on about 3 hours ago

Commit

e59a15d

·

verified ·

1 Parent(s): c0d80c1

Update processing_moss_vl.py

Files changed (1) hide show

processing_moss_vl.py +2 -2

processing_moss_vl.py CHANGED Viewed

@@ -56,7 +56,7 @@ class MossVLImageProcessorFast(Qwen2VLImageProcessorFast):
         images: list["torch.Tensor"],
         do_resize: bool,
         size: SizeDict,
-        interpolation: Optional["F.InterpolationMode"],
         do_rescale: bool,
         rescale_factor: float,
         do_normalize: bool,
@@ -115,7 +115,7 @@ class MossVLImageProcessorFast(Qwen2VLImageProcessorFast):
                 stacked_images = self.resize(
                     image=stacked_images,
                     size=SizeDict(height=resized_height, width=resized_width),
-                    interpolation=interpolation,
                 )
             resized_images_grouped[shape] = stacked_images
         resized_images = reorder_images(resized_images_grouped, grouped_images_index)

         images: list["torch.Tensor"],
         do_resize: bool,
         size: SizeDict,
+        resample: Optional["F.InterpolationMode"],
         do_rescale: bool,
         rescale_factor: float,
         do_normalize: bool,
                 stacked_images = self.resize(
                     image=stacked_images,
                     size=SizeDict(height=resized_height, width=resized_width),
+                    resample=resample,
                 )
             resized_images_grouped[shape] = stacked_images
         resized_images = reorder_images(resized_images_grouped, grouped_images_index)