def test_inference_no_head(self):
model = LayoutLMv2Model.from_pretrained(
"microsoft/layoutlmv2-base-uncased").to(torch_device)
(
input_ids,
bbox,
image,
attention_mask,
token_type_ids,
) = prepare_layoutlmv2_batch_inputs()
# forward pass
outputs = model(
input_ids=input_ids.to(torch_device),
bbox=bbox.to(torch_device),
image=image.to(torch_device),
attention_mask=attention_mask.to(torch_device),
token_type_ids=token_type_ids.to(torch_device),
)
# verify the sequence output
expected_shape = torch.Size((
2,
input_ids.shape[1] + model.config.image_feature_pool_shape[0] *
model.config.image_feature_pool_shape[1],
model.config.hidden_size,
))
self.assertEqual(outputs.last_hidden_state.shape, expected_shape)
expected_slice = torch.tensor(
[[-0.1087, 0.0727, -0.3075], [0.0799, -0.0427, -0.0751],
[-0.0367, 0.0480, -0.1358]],
device=torch_device)
self.assertTrue(
torch.allclose(outputs.last_hidden_state[0, :3, :3],
expected_slice,
atol=1e-3))
# verify the pooled output
expected_shape = torch.Size((2, model.config.hidden_size))
self.assertEqual(outputs.pooler_output.shape, expected_shape)
def test_model_from_pretrained(self):
for model_name in LAYOUTLMV2_PRETRAINED_MODEL_ARCHIVE_LIST[:1]:
model = LayoutLMv2Model.from_pretrained(model_name)
self.assertIsNotNone(model)
