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

16
docs/source/en/model_doc/eomt.md
View File

@@ -74,20 +74,16 @@ inputs = processor(
return_tensors="pt",
)
# Remove Patch Offsets from inputs — only used later for post-processing.
patch_offsets = inputs.pop("patch_offsets")
with torch.inference_mode():
outputs = model(**inputs)
# Prepare the original image size in the format (height, width)
original_image_sizes = [(image.height, image.width)]
target_sizes = [(image.height, image.width)]
# Post-process the model outputs to get final segmentation prediction
preds = processor.post_process_semantic_segmentation(
outputs,
patch_offsets=patch_offsets,
original_image_sizes=original_image_sizes,
target_sizes=target_sizes,
)
# Visualize the segmentation mask
@@ -130,12 +126,12 @@ with torch.inference_mode():
outputs = model(**inputs)
# Prepare the original image size in the format (height, width)
original_image_sizes = [(image.height, image.width)]
target_sizes = [(image.height, image.width)]
# Post-process the model outputs to get final segmentation prediction
preds = processor.post_process_instance_segmentation(
outputs,
original_image_sizes=original_image_sizes,
target_sizes=target_sizes,
)
# Visualize the segmentation mask
@@ -173,12 +169,12 @@ with torch.inference_mode():
outputs = model(**inputs)
# Prepare the original image size in the format (height, width)
original_image_sizes = [(image.height, image.width)]
target_sizes = [(image.height, image.width)]
# Post-process the model outputs to get final segmentation prediction
preds = processor.post_process_panoptic_segmentation(
outputs,
original_image_sizes=original_image_sizes,
target_sizes=target_sizes,
)
# Visualize the panoptic segmentation mask