Create demo v1

app.py

@@ -1,7 +1,76 @@
+#%%
 import gradio as gr
+from PIL import Image
+from torchvision import transforms
+from siamese_nn import Siamese_nn
+import torch, os
+import torch.nn.functional as F
 
-def greet(name):
-    return "Hello " + name + "!!"
+model = Siamese_nn()
+weights = torch.load('trained_model')
+model.load_state_dict(weights)
+model.eval()
+#%%
+file_list = os.listdir('data')
+examples = []
+usersIndexes = []
+for x in file_list:
+    if x[0:2] not in usersIndexes:
+        usersIndexes.append(x[0:2])
+    
+for user in usersIndexes:
+    usersImages = [x for x in file_list if str(user) in x]
+    notUsersImages = [x for x in file_list if str(user) not in x]
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-iface.launch()
+    for userImage in usersImages:
+        for userImageCopy in usersImages:
+            examples.append([userImage, userImageCopy, 0])
+            for notUser in notUsersImages:
+                examples.append([userImage, notUser, 1])
+
+#%%
+def predict(input1, input2, label=None):
+    img1_PIL = Image.open(f'data/{input1}')
+    img2_PIL = Image.open(f'data/{input2}')
+    img1 = transforms.ToTensor()(img1_PIL).unsqueeze(0)
+    img2 = transforms.ToTensor()(img2_PIL).unsqueeze(0)
+
+    for el in examples:
+        if input1 == input2:
+            label = 0
+            break
+        if input1 in el and input2 in el:
+            label = el[2]        
+    
+    with torch.no_grad():
+        out1, out2 = model(img1, img2)
+        pred = F.pairwise_distance(out1, out2)
+        if pred < 0.6:
+            decision = f'Access granted, confidence: {pred.item():4f}'
+        else:
+            decision = f'Access denied, confidence: {pred.item():4f}'
+        return img1_PIL, img2_PIL, decision, label 
+
+#%%
+with gr.Blocks() as demo:
+    drop1 =  gr.Dropdown(
+    choices=file_list,
+    label='First image',
+    scale=0
+    )
+    drop2 = gr.Dropdown(
+    choices=file_list,
+    label='Second image',
+    scale=0     
+    )
+    with gr.Row():
+        img1 = gr.Image(value=f'data/{examples[0][0]}', height=153, width=136, interactive=False, scale=0, label='image1')
+        img2 = gr.Image(value=f'data/{examples[0][0]}', height=153, width=136, interactive=False, scale=0, label='image2')
+        label = gr.Label(label='0 means images represent the same fingerprint')
+    output = gr.Label(value=predict(*examples[0])[2], label='Prediction')
+
+    drop1.change(fn=predict, inputs=[drop1, drop2], outputs=[img1, img2, output, label])
+    drop2.change(fn=predict, inputs=[drop1, drop2], outputs=[img1, img2, output, label])
+    demo.launch()
+
+# %%