reformat

hloc/extractors/dedode.py

@@ -64,8 +64,8 @@ class DeDoDe(BaseModel):
         # load the model
         weights_detector = torch.load(model_detector_path, map_location="cpu")
         weights_descriptor = torch.load(model_descriptor_path, map_location="cpu")
-        self.detector = dedode_detector_L(weights=weights_detector, device = device)
-        self.descriptor = dedode_descriptor_B(weights=weights_descriptor, device = device)
+        self.detector = dedode_detector_L(weights=weights_detector, device=device)
+        self.descriptor = dedode_descriptor_B(weights=weights_descriptor, device=device)
         logger.info(f"Load DeDoDe model done.")
 
     def _forward(self, data):

third_party/ASpanFormer/src/ASpanFormer/aspan_module/transformer.py

@@ -6,6 +6,7 @@ from .attention import FullAttention, HierachicalAttention, layernorm2d
 
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
+
 class messageLayer_ini(nn.Module):
     def __init__(self, d_model, d_flow, d_value, nhead):
         super().__init__()

third_party/ASpanFormer/src/ASpanFormer/aspanformer.py

@@ -15,6 +15,7 @@ from .utils.fine_matching import FineMatching
 
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
+
 class ASpanFormer(nn.Module):
     def __init__(self, config):
         super().__init__()
@@ -160,7 +161,7 @@ class ASpanFormer(nn.Module):
             train_res_h / data["image1"].shape[2],
             train_res_w / data["image1"].shape[3],
         ]
-        
+
         data["online_resize_scale0"], data["online_resize_scale1"] = (
             torch.tensor([w0 / data["image0"].shape[3], h0 / data["image0"].shape[2]])[
                 None

third_party/SGMNet/sgmnet/match_model.py

@@ -5,6 +5,7 @@ eps = 1e-8
 
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
+
 def sinkhorn(M, r, c, iteration):
     p = torch.softmax(M, dim=-1)
     u = torch.ones_like(r)