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

Revert changes in logit size for semantic segmentation models (#15722)

Browse Source 
* Revert changes in logit size for semantic segmentation models

* Address review comments
This commit is contained in:
Sylvain Gugger
2022-02-24 15:52:52 +01:00
committed by GitHub
parent d1fcc90abf
commit 35ecf99cc4
7 changed files with 50 additions and 101 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
tests/beit/test_modeling_beit.py
View File

@@ -162,11 +162,11 @@ class BeitModelTester:
model.eval()
result = model(pixel_values)
self.parent.assertEqual(
result.logits.shape, (self.batch_size, self.num_labels, self.image_size, self.image_size)
result.logits.shape, (self.batch_size, self.num_labels, self.image_size * 2, self.image_size * 2)
)
result = model(pixel_values, labels=pixel_labels)
self.parent.assertEqual(
result.logits.shape, (self.batch_size, self.num_labels, self.image_size, self.image_size)
result.logits.shape, (self.batch_size, self.num_labels, self.image_size * 2, self.image_size * 2)
)
def prepare_config_and_inputs_for_common(self):
@@ -533,14 +533,14 @@ class BeitModelIntegrationTest(unittest.TestCase):
logits = outputs.logits
# verify the logits
expected_shape = torch.Size((1, 150, 640, 640))
expected_shape = torch.Size((1, 150, 160, 160))
self.assertEqual(logits.shape, expected_shape)
expected_slice = torch.tensor(
[
[[-4.9225, -4.9225, -4.6066], [-4.9225, -4.9225, -4.6066], [-4.6675, -4.6675, -4.3617]],
[[-5.8168, -5.8168, -5.5163], [-5.8168, -5.8168, -5.5163], [-5.5728, -5.5728, -5.2842]],
[[-0.0078, -0.0078, 0.4926], [-0.0078, -0.0078, 0.4926], [0.3664, 0.3664, 0.8309]],
[[-4.9225, -2.3954, -3.0522], [-2.8822, -1.0046, -1.7561], [-2.9549, -1.3228, -2.1347]],
[[-5.8168, -3.4129, -4.0778], [-3.8651, -2.2214, -3.0277], [-3.8356, -2.4643, -3.3535]],
[[-0.0078, 3.9952, 4.0754], [2.9856, 4.6944, 5.0035], [3.2413, 4.7813, 4.9969]],
]
).to(torch_device)

20
tests/segformer/test_modeling_segformer.py
View File

@@ -135,11 +135,11 @@ class SegformerModelTester:
model.eval()
result = model(pixel_values)
self.parent.assertEqual(
result.logits.shape, (self.batch_size, self.num_labels, self.image_size, self.image_size)
result.logits.shape, (self.batch_size, self.num_labels, self.image_size // 4, self.image_size // 4)
)
result = model(pixel_values, labels=labels)
self.parent.assertEqual(
result.logits.shape, (self.batch_size, self.num_labels, self.image_size, self.image_size)
result.logits.shape, (self.batch_size, self.num_labels, self.image_size // 4, self.image_size // 4)
)
def prepare_config_and_inputs_for_common(self):
@@ -363,14 +363,14 @@ class SegformerModelIntegrationTest(unittest.TestCase):
with torch.no_grad():
outputs = model(pixel_values)
expected_shape = torch.Size((1, model.config.num_labels, 512, 512))
expected_shape = torch.Size((1, model.config.num_labels, 128, 128))
self.assertEqual(outputs.logits.shape, expected_shape)
expected_slice = torch.tensor(
[
[[-4.6309, -4.6309, -4.7425], [-4.6309, -4.6309, -4.7425], [-4.7011, -4.7011, -4.8136]],
[[-12.1391, -12.1391, -12.2858], [-12.1391, -12.1391, -12.2858], [-12.2309, -12.2309, -12.3758]],
[[-12.5134, -12.5134, -12.6328], [-12.5134, -12.5134, -12.6328], [-12.5576, -12.5576, -12.6865]],
[[-4.6310, -5.5232, -6.2356], [-5.1921, -6.1444, -6.5996], [-5.4424, -6.2790, -6.7574]],
[[-12.1391, -13.3122, -13.9554], [-12.8732, -13.9352, -14.3563], [-12.9438, -13.8226, -14.2513]],
[[-12.5134, -13.4686, -14.4915], [-12.8669, -14.4343, -14.7758], [-13.2523, -14.5819, -15.0694]],
]
).to(torch_device)
self.assertTrue(torch.allclose(outputs.logits[0, :3, :3, :3], expected_slice, atol=1e-4))
@@ -392,14 +392,14 @@ class SegformerModelIntegrationTest(unittest.TestCase):
with torch.no_grad():
outputs = model(pixel_values)
expected_shape = torch.Size((1, model.config.num_labels, 512, 512))
expected_shape = torch.Size((1, model.config.num_labels, 128, 128))
self.assertEqual(outputs.logits.shape, expected_shape)
expected_slice = torch.tensor(
[
[[-13.5729, -13.5729, -13.6149], [-13.5729, -13.5729, -13.6149], [-13.6697, -13.6697, -13.7224]],
[[-17.1638, -17.1638, -17.0022], [-17.1638, -17.1638, -17.0022], [-17.1754, -17.1754, -17.0358]],
[[-3.6452, -3.6452, -3.5670], [-3.6452, -3.6452, -3.5670], [-3.5744, -3.5744, -3.5079]],
[[-13.5748, -13.9111, -12.6500], [-14.3500, -15.3683, -14.2328], [-14.7532, -16.0424, -15.6087]],
[[-17.1651, -15.8725, -12.9653], [-17.2580, -17.3718, -14.8223], [-16.6058, -16.8783, -16.7452]],
[[-3.6456, -3.0209, -1.4203], [-3.0797, -3.1959, -2.0000], [-1.8757, -1.9217, -1.6997]],
]
).to(torch_device)
self.assertTrue(torch.allclose(outputs.logits[0, :3, :3, :3], expected_slice, atol=1e-1))