temp

app.py

@@ -6,11 +6,10 @@ from how.networks import how_net
 
 import fire_network
 
+import cv2
 
 # Possible Scales for multiscale inference
-    scales = [2.0, 1.414, 1.0, 0.707, 0.5, 0.353, 0.25] 
-    infer_opts = {"scales": scales, "features_num": 1000}
-
+scales = [2.0, 1.414, 1.0, 0.707, 0.5, 0.353, 0.25] 
 
 # Load net
 state = torch.load('fire.pth', map_location='cpu')
@@ -18,28 +17,42 @@ state['net_params']['pretrained'] = None # no need for imagenet pretrained model
 net = fire_network.init_network(**state['net_params']).to(device)
 net.load_state_dict(state['state_dict'])
 
-transforms_ = transforms.Compose([
+transform = transforms.Compose([
         transforms.Resize(1024),
         transforms.ToTensor(), 
         transforms.Normalize(**dict(zip(["mean", "std"], net.runtime['mean_std'])))
         ])
 
 
-# Wrapper
+# which sf
+sf_idx_ = [55, 14, 5, 4, 52, 57, 40, 9]
+
+
+col = plt.get_cmap('tab10')
+
 def generate_matching_superfeatures(im1, im2, scale=6):
     
-    # extract features
-    with torch.no_grad():
-            output1 = net.get_superfeatures(im1.to(device), scales=scales)
-            feats1 = output1[0]
-            attns1 = output1[1]
-            strenghts1 = output1[2]
+    im1_tensor = transform(im1)
+    im2_tensor = transform(im2)
 
-            output2 = net.get_superfeatures(im2.to(device), scales=scales)
-            feats2 = output2[0]
-            attns2 = output2[1]
-            strenghts2 = output2[2]
+    im1_cv = cv2.imread(im1)
+    im2_cv = cv2.imread(im2)
 
+    # extract features
+    with torch.no_grad():
+        output1 = net.get_superfeatures(im1.to(device), scales=scales)
+        feats1 = output1[0]
+        attns1 = output1[1]
+        strenghts1 = output1[2]
+
+        output2 = net.get_superfeatures(im2.to(device), scales=scales)
+        feats2 = output2[0]
+        attns2 = output2[1]
+        strenghts2 = output2[2]
+
+    print(feats1.shape)
+    print(attns1.shape)
+    print(strenghts1.shape)