Fix tapas scatter (#20149)

* First draft

* Remove scatter dependency

* Add require_torch

* update vectorized sum test, add clone call

* remove artifacts

* fix style

* fix style v2

* remove "scatter" mentions from the code base

* fix isort error

Co-authored-by: Niels Rogge <nielsrogge@Nielss-MacBook-Pro.local>
Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>

tests/deepspeed/test_model_zoo.py

@@ -130,8 +130,7 @@ SPEECH_TO_TEXT_TINY = "hf-internal-testing/tiny-random-speech_to_text"
 # models with low usage, unstable API, things about to change - do nothing about the following until someone runs into a problem
 TAPAS_TINY = "hf-internal-testing/tiny-random-tapas"
 # additional notes on tapas
-# 1. requires torch_scatter - skip if it's not installed?
-# 2. "Table must be of type pd.DataFrame" failure
+# 1. "Table must be of type pd.DataFrame" failure
 
 
 # TODO: new models to add:

tests/models/auto/test_modeling_auto.py

@@ -28,7 +28,6 @@ from transformers.testing_utils import (
     DUMMY_UNKNOWN_IDENTIFIER,
     SMALL_MODEL_IDENTIFIER,
     RequestCounter,
-    require_scatter,
     require_torch,
     slow,
 )
@@ -197,7 +196,6 @@ class AutoModelTest(unittest.TestCase):
             self.assertIsInstance(model, BertForQuestionAnswering)
 
     @slow
-    @require_scatter
     def test_table_question_answering_model_from_pretrained(self):
         for model_name in TAPAS_PRETRAINED_MODEL_ARCHIVE_LIST[5:6]:
             config = AutoConfig.from_pretrained(model_name)

tests/models/layoutxlm/test_tokenization_layoutxlm.py

@@ -32,7 +32,6 @@ from transformers.testing_utils import (
     get_tests_dir,
     is_pt_tf_cross_test,
     require_pandas,
-    require_scatter,
     require_sentencepiece,
     require_tokenizers,
     require_torch,
@@ -1176,7 +1175,6 @@ class LayoutXLMTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
 
     @require_torch
     @slow
-    @require_scatter
     def test_torch_encode_plus_sent_to_model(self):
         import torch
 

tests/models/tapas/test_modeling_tapas.py

@@ -32,13 +32,7 @@ from transformers import (
     is_torch_available,
 )
 from transformers.models.auto import get_values
-from transformers.testing_utils import (
-    require_scatter,
-    require_tensorflow_probability,
-    require_torch,
-    slow,
-    torch_device,
-)
+from transformers.testing_utils import require_tensorflow_probability, require_torch, slow, torch_device
 from transformers.utils import cached_property
 
 from ...test_configuration_common import ConfigTester
@@ -414,7 +408,6 @@ class TapasModelTester:
 
 
 @require_torch
-@require_scatter
 class TapasModelTest(ModelTesterMixin, unittest.TestCase):
 
     all_model_classes = (
@@ -553,7 +546,6 @@ def prepare_tapas_batch_inputs_for_training():
 
 
 @require_torch
-@require_scatter
 class TapasModelIntegrationTest(unittest.TestCase):
     @cached_property
     def default_tokenizer(self):
@@ -907,7 +899,7 @@ class TapasModelIntegrationTest(unittest.TestCase):
 # Below: tests for Tapas utilities which are defined in modeling_tapas.py.
 # These are based on segmented_tensor_test.py of the original implementation.
 # URL: https://github.com/google-research/tapas/blob/master/tapas/models/segmented_tensor_test.py
-@require_scatter
+@require_torch
 class TapasUtilitiesTest(unittest.TestCase):
     def _prepare_tables(self):
         """Prepares two tables, both with three distinct rows.
@@ -1064,11 +1056,11 @@ class TapasUtilitiesTest(unittest.TestCase):
 
     def test_reduce_sum_vectorized(self):
         values = torch.as_tensor([[1.0, 2.0, 3.0], [2.0, 3.0, 4.0], [3.0, 4.0, 5.0]])
-        index = IndexMap(indices=torch.as_tensor([0, 0, 1]), num_segments=2, batch_dims=0)
+        index = IndexMap(indices=torch.as_tensor([[0, 0, 1]]), num_segments=2, batch_dims=0)
         sums, new_index = reduce_sum(values, index)
 
         # We use np.testing.assert_allclose rather than Tensorflow's assertAllClose
-        np.testing.assert_allclose(sums.numpy(), [[3.0, 5.0, 7.0], [3.0, 4.0, 5.0]])
+        np.testing.assert_allclose(sums.numpy(), [3.0, 3.0])
         # We use np.testing.assert_array_equal rather than Tensorflow's assertAllEqual
         np.testing.assert_array_equal(new_index.indices.numpy(), [0, 1])
         np.testing.assert_array_equal(new_index.num_segments.numpy(), 2)

tests/models/tapas/test_tokenization_tapas.py

@@ -35,7 +35,6 @@ from transformers.models.tapas.tokenization_tapas import (
 from transformers.testing_utils import (
     is_pt_tf_cross_test,
     require_pandas,
-    require_scatter,
     require_tensorflow_probability,
     require_tokenizers,
     require_torch,
@@ -1031,7 +1030,6 @@ class TapasTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
 
     @require_torch
     @slow
-    @require_scatter
     def test_torch_encode_plus_sent_to_model(self):
         import torch
 

tests/pipelines/test_pipelines_common.py

@@ -50,7 +50,6 @@ from transformers.testing_utils import (
     RequestCounter,
     is_staging_test,
     nested_simplify,
-    require_scatter,
     require_tensorflow_probability,
     require_tf,
     require_torch,
@@ -749,7 +748,6 @@ class PipelineUtilsTest(unittest.TestCase):
 
     @slow
     @require_torch
-    @require_scatter
     def test_load_default_pipelines_pt_table_qa(self):
         import torch
 

tests/pipelines/test_pipelines_table_question_answering.py

@@ -22,14 +22,7 @@ from transformers import (
     TFAutoModelForTableQuestionAnswering,
     pipeline,
 )
-from transformers.testing_utils import (
-    require_pandas,
-    require_tensorflow_probability,
-    require_tf,
-    require_torch,
-    require_torch_scatter,
-    slow,
-)
+from transformers.testing_utils import require_pandas, require_tensorflow_probability, require_tf, require_torch, slow
 
 from .test_pipelines_common import PipelineTestCaseMeta
 
@@ -145,7 +138,6 @@ class TQAPipelineTests(unittest.TestCase, metaclass=PipelineTestCaseMeta):
             )
 
     @require_torch
-    @require_torch_scatter
     def test_small_model_pt(self):
         model_id = "lysandre/tiny-tapas-random-wtq"
         model = AutoModelForTableQuestionAnswering.from_pretrained(model_id)
@@ -248,7 +240,6 @@ class TQAPipelineTests(unittest.TestCase, metaclass=PipelineTestCaseMeta):
             )
 
     @require_torch
-    @require_torch_scatter
     def test_slow_tokenizer_sqa_pt(self):
         model_id = "lysandre/tiny-tapas-random-sqa"
         model = AutoModelForTableQuestionAnswering.from_pretrained(model_id)
@@ -490,7 +481,6 @@ class TQAPipelineTests(unittest.TestCase, metaclass=PipelineTestCaseMeta):
             )
 
     @slow
-    @require_torch_scatter
     def test_integration_wtq_pt(self):
         table_querier = pipeline("table-question-answering")
 
@@ -584,7 +574,6 @@ class TQAPipelineTests(unittest.TestCase, metaclass=PipelineTestCaseMeta):
         self.assertListEqual(results, expected_results)
 
     @slow
-    @require_torch_scatter
     def test_integration_sqa_pt(self):
         table_querier = pipeline(
             "table-question-answering",