diff --git a/.github/workflows/self-scheduled.yml b/.github/workflows/self-scheduled.yml
index 0fd3cb2722..5cf6f793ec 100644
--- a/.github/workflows/self-scheduled.yml
+++ b/.github/workflows/self-scheduled.yml
@@ -37,6 +37,7 @@ jobs:
           pip install --upgrade pip
           pip install .[integrations,sklearn,testing,onnxruntime,sentencepiece,torch-speech,vision,timm]
           pip install https://github.com/kpu/kenlm/archive/master.zip
+          python -m pip install 'git+https://github.com/facebookresearch/detectron2.git'
 
       - name: Are GPUs recognized by our DL frameworks
         run: |
@@ -241,6 +242,7 @@ jobs:
           pip install --upgrade pip
           pip install .[integrations,sklearn,testing,onnxruntime,sentencepiece,torch-speech,vision,timm]
           pip install https://github.com/kpu/kenlm/archive/master.zip
+          python -m pip install 'git+https://github.com/facebookresearch/detectron2.git'
 
       - name: Are GPUs recognized by our DL frameworks
         run: |
diff --git a/tests/test_modeling_layoutlmv2.py b/tests/test_modeling_layoutlmv2.py
index cbcb6f5139..94e274e8a1 100644
--- a/tests/test_modeling_layoutlmv2.py
+++ b/tests/test_modeling_layoutlmv2.py
@@ -478,11 +478,11 @@ class LayoutLMv2ModelTest(ModelTesterMixin, unittest.TestCase):
 def prepare_layoutlmv2_batch_inputs():
     # Here we prepare a batch of 2 sequences to test a LayoutLMv2 forward pass on:
     # fmt: off
-    input_ids = torch.tensor([[101,1019,1014,1016,1037,12849,4747,1004,14246,2278,5439,4524,5002,2930,2193,2930,4341,3208,1005,1055,2171,2848,11300,3531,102],[101,4070,4034,7020,1024,3058,1015,1013,2861,1013,6070,19274,2772,6205,27814,16147,16147,4343,2047,10283,10969,14389,1012,2338,102]],device=torch_device)  # noqa: E231
-    bbox = torch.tensor([[[0,0,0,0],[423,237,440,251],[427,272,441,287],[419,115,437,129],[961,885,992,912],[256,38,330,58],[256,38,330,58],[336,42,353,57],[360,39,401,56],[360,39,401,56],[411,39,471,59],[479,41,528,59],[533,39,630,60],[67,113,134,131],[141,115,209,132],[68,149,133,166],[141,149,187,164],[195,148,287,165],[195,148,287,165],[195,148,287,165],[295,148,349,165],[441,149,492,166],[497,149,546,164],[64,201,125,218],[1000,1000,1000,1000]],[[0,0,0,0],[662,150,754,166],[665,199,742,211],[519,213,554,228],[519,213,554,228],[134,433,187,454],[130,467,204,480],[130,467,204,480],[130,467,204,480],[130,467,204,480],[130,467,204,480],[314,469,376,482],[504,684,582,706],[941,825,973,900],[941,825,973,900],[941,825,973,900],[941,825,973,900],[610,749,652,765],[130,659,168,672],[176,657,237,672],[238,657,312,672],[443,653,628,672],[443,653,628,672],[716,301,825,317],[1000,1000,1000,1000]]],device=torch_device)  # noqa: E231
+    input_ids = torch.tensor([[101,1019,1014,1016,1037,12849,4747,1004,14246,2278,5439,4524,5002,2930,2193,2930,4341,3208,1005,1055,2171,2848,11300,3531,102],[101,4070,4034,7020,1024,3058,1015,1013,2861,1013,6070,19274,2772,6205,27814,16147,16147,4343,2047,10283,10969,14389,1012,2338,102]])  # noqa: E231
+    bbox = torch.tensor([[[0,0,0,0],[423,237,440,251],[427,272,441,287],[419,115,437,129],[961,885,992,912],[256,38,330,58],[256,38,330,58],[336,42,353,57],[360,39,401,56],[360,39,401,56],[411,39,471,59],[479,41,528,59],[533,39,630,60],[67,113,134,131],[141,115,209,132],[68,149,133,166],[141,149,187,164],[195,148,287,165],[195,148,287,165],[195,148,287,165],[295,148,349,165],[441,149,492,166],[497,149,546,164],[64,201,125,218],[1000,1000,1000,1000]],[[0,0,0,0],[662,150,754,166],[665,199,742,211],[519,213,554,228],[519,213,554,228],[134,433,187,454],[130,467,204,480],[130,467,204,480],[130,467,204,480],[130,467,204,480],[130,467,204,480],[314,469,376,482],[504,684,582,706],[941,825,973,900],[941,825,973,900],[941,825,973,900],[941,825,973,900],[610,749,652,765],[130,659,168,672],[176,657,237,672],[238,657,312,672],[443,653,628,672],[443,653,628,672],[716,301,825,317],[1000,1000,1000,1000]]])  # noqa: E231
     image = ImageList(torch.randn((2,3,224,224)), image_sizes=[(224,224), (224,224)])  # noqa: E231
-    attention_mask = torch.tensor([[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],],device=torch_device)  # noqa: E231
-    token_type_ids = torch.tensor([[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0]],device=torch_device)  # noqa: E231
+    attention_mask = torch.tensor([[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],])  # noqa: E231
+    token_type_ids = torch.tensor([[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0]])  # noqa: E231
     # fmt: on
 
     return input_ids, bbox, image, attention_mask, token_type_ids
@@ -505,11 +505,11 @@ class LayoutLMv2ModelIntegrationTest(unittest.TestCase):
 
         # forward pass
         outputs = model(
-            input_ids=input_ids,
-            bbox=bbox,
-            image=image,
-            attention_mask=attention_mask,
-            token_type_ids=token_type_ids,
+            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