SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Pix2Struct: fix wrong broadcast axis of attention mask in visual encoder (#23976)

Browse Source 
* fix wrong broadcast axis of attention mask in visual encoder

* fix slow tests

---------

Co-authored-by: younesbelkada <younesbelkada@gmail.com>
This commit is contained in:
Jungwoo Park
2023-06-06 00:47:29 +09:00
committed by GitHub
parent 7824fa431e
commit 44bd590a29
2 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/models/pix2struct/test_modeling_pix2struct.py
View File

@@ -757,12 +757,12 @@ class Pix2StructIntegrationTest(unittest.TestCase):
self.assertEqual(
processor.decode(predictions[0], skip_special_tokens=True),
"A picture of a stop sign with a red stop sign on it.",
"A picture of a stop sign with a red stop sign",
)
self.assertEqual(
processor.decode(predictions[1], skip_special_tokens=True),
"An photography of the Temple Bar and the Temple Bar.",
"An photography of the Temple Bar and other places in the city.",
)
def test_vqa_model(self):