def test_inference_no_head(self):
model = MaskFormerModel.from_pretrained(
self.model_checkpoints).to(torch_device)
feature_extractor = self.default_feature_extractor
image = prepare_img()
inputs = feature_extractor(image, return_tensors="pt").to(torch_device)
inputs_shape = inputs["pixel_values"].shape
# check size is divisible by 32
self.assertTrue((inputs_shape[-1] % 32) == 0
and (inputs_shape[-2] % 32) == 0)
# check size
self.assertEqual(inputs_shape, (1, 3, 800, 1088))
with torch.no_grad():
outputs = model(**inputs)
expected_slice_hidden_state = torch.tensor([[-0.0482, 0.9228, 0.4951],
[-0.2547, 0.8017, 0.8527],
[-0.0069, 0.3385, -0.0089]
]).to(torch_device)
self.assertTrue(
torch.allclose(outputs.encoder_last_hidden_state[0, 0, :3, :3],
expected_slice_hidden_state,
atol=TOLERANCE))
expected_slice_hidden_state = torch.tensor(
[[-0.8422, -0.8434, -0.9718], [-1.0144, -0.5565, -0.4195],
[-1.0038, -0.4484, -0.1961]]).to(torch_device)
self.assertTrue(
torch.allclose(outputs.pixel_decoder_last_hidden_state[0,
0, :3, :3],
expected_slice_hidden_state,
atol=TOLERANCE))
expected_slice_hidden_state = torch.tensor([[0.2852, -0.0159, 0.9735],
[0.6254, 0.1858, 0.8529],
[-0.0680, -0.4116,
1.8413]]).to(torch_device)
self.assertTrue(
torch.allclose(
outputs.transformer_decoder_last_hidden_state[0, :3, :3],
expected_slice_hidden_state,
atol=TOLERANCE))
def test_model_from_pretrained(self):
for model_name in ["facebook/maskformer-swin-small-coco"]:
model = MaskFormerModel.from_pretrained(model_name)
self.assertIsNotNone(model)
