face recognition

app/Hackathon_setup/face_recognition.py

@@ -159,12 +159,12 @@ def get_similarity(img1, img2):
 
 def get_face_class(img1):
 
-    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
     BASE_DIR = os.path.dirname(os.path.abspath(__file__))
 
     # 1 Load the Decision Tree classifier
     # clf_path = os.path.join(BASE_DIR, "decision_tree_model.sav")
-    clf_path = os.path.join(BASE_DIR, "face_knn.sav")
+    clf_path = os.path.join(BASE_DIR, "SVC_3.sav")
     clf = joblib.load(clf_path)
 
     scaler_path = os.path.join(BASE_DIR, "standar_scaler.sav")
@@ -177,7 +177,7 @@ def get_face_class(img1):
     myModel.load_state_dict(ckpt['net_dict'])
     myModel.eval()
 
-    img_tensor = trnscm(img1).unsqueeze(0)
+    img_tensor = transform1(img1).unsqueeze(0)
 
     with torch.no_grad():
         embedding = myModel.forward_once(img_tensor)
@@ -185,7 +185,7 @@ def get_face_class(img1):
     pred_label = clf.predict(scaler.transform(embedding))[0]
 
     class_names = ['Aayush', 'Aditya', 'Vikram']
-    return f"{class_names[pred_label]} {pred_label}"
+    return f"{class_names[pred_label]} {pred_label} {embedding}"
 
 
 # def get_face_class(img1):

app/Hackathon_setup/face_recognition_model.py

@@ -17,6 +17,9 @@ trnscm = transforms.Compose([
     transforms.Normalize(mean=[0.5], std=[0.5])
 ])
 
+transform1 = transforms.Compose([transforms.Grayscale(num_output_channels = 1),
+                                 transforms.Resize((100,100)), transforms.ToTensor()])
+
 ##Example Network
 class Siamese(torch.nn.Module):
     def __init__(self):