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

🚨🚨🚨 [eomt] make EoMT compatible with pipeline (#39122)

Browse Source 
* Make EoMT compatible with pipeline

* Implicit patch offsets

* remove patch offsets from arg

* Modify tests

* Update example

* fix proc testcase

* Add few more args

* add pipeline test suite

* fix

* docstring fixes

* add pipeline test

* changes w.r.t review

* 🙈 MB

* should fix device mismatch

* debug

* Fixes device mismatch

* use decorator

* we can split mlp

* expected values update

---------

Co-authored-by: NielsRogge <48327001+NielsRogge@users.noreply.github.com>
This commit is contained in:
Yaswanth Gali
2025-07-02 16:55:26 +05:30
committed by GitHub
parent 4d5822e65d
commit b61023a1b7
7 changed files with 113 additions and 92 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
tests/models/eomt/test_image_processing_eomt.py
View File

@@ -84,10 +84,11 @@ class EomtImageProcessingTester:
"num_labels": self.num_labels,
}
def prepare_fake_eomt_outputs(self, batch_size):
def prepare_fake_eomt_outputs(self, batch_size, patch_offsets=None):
return EomtForUniversalSegmentationOutput(
masks_queries_logits=torch.randn((batch_size, self.num_queries, self.height, self.width)),
class_queries_logits=torch.randn((batch_size, self.num_queries, self.num_classes + 1)),
patch_offsets=patch_offsets,
)
def prepare_image_inputs(self, equal_resolution=False, numpify=False, torchify=False):
@@ -263,13 +264,13 @@ class EomtImageProcessingTest(ImageProcessingTestMixin, unittest.TestCase):
image = Image.open(requests.get("http://images.cocodataset.org/val2017/000000039769.jpg", stream=True).raw)
inputs = processor(images=image, do_split_image=True, return_tensors="pt")
patch_offsets = inputs.pop("patch_offsets")
patch_offsets = inputs["patch_offsets"]
original_sizes = [image.size[::-1]]
target_sizes = [image.size[::-1]]
# For semantic segmentation, the BS of output is 2 coz, two patches are created for the image.
outputs = self.image_processor_tester.prepare_fake_eomt_outputs(inputs["pixel_values"].shape[0])
segmentation = processor.post_process_semantic_segmentation(outputs, patch_offsets, original_sizes)
outputs = self.image_processor_tester.prepare_fake_eomt_outputs(inputs["pixel_values"].shape[0], patch_offsets)
segmentation = processor.post_process_semantic_segmentation(outputs, target_sizes)
self.assertEqual(segmentation[0].shape, (image.height, image.width))