Update app.py

app.py

@@ -3,32 +3,94 @@ import torch
 from PIL import Image
 import os
 
-from read import classify
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+class Net(nn.Module):
+    
+    def __init__(self):
+        super(Net, self).__init__()
+        self.conv1 = nn.Conv2d(3, 32, 5)
+        self.conv2 = nn.Conv2d(32, 64, 5)
+        self.conv3 = nn.Conv2d(64, 128, 5)
+        self.conv4 = nn.Conv2d(128, 256, 5)
+        self.conv5 = nn.Conv2d(256, 512, 5)
+
+        self.fc1 = None
+        self.fc2 = nn.Linear(512, 128)
+        self.fc3 = nn.Linear(128, 64)
+        self.fc4 = nn.Linear(64, 2)
+
+    def forward(self, x):
+        x = x.float()
+        """ x = F.relu(self.conv1(x))
+        x = F.relu(self.conv2(x))
+        x = F.max_pool2d(x, 2)
+        x = F.relu(self.conv3(x))
+        x = F.relu(self.conv4(x))
+        x = F.max_pool2d(x, 2)
+        x = F.relu(self.conv5(x))
+        x = F.max_pool2d(x, 2) """
+        
+        x = F.max_pool2d(F.relu(self.conv1(x)), 2)
+        x = F.max_pool2d(F.relu(self.conv2(x)), 2)
+        x = F.max_pool2d(F.relu(self.conv3(x)), 2)
+        x = F.max_pool2d(F.relu(self.conv4(x)), 2)
+        x = F.max_pool2d(F.relu(self.conv5(x)), 2)
+
+        #x = x.view(x.size(0), -1)
+        x = torch.flatten(x, 1)
+        
+        if self.fc1 is None:
+            self.fc1 = nn.Linear(x.shape[1], 512).to(x.device)
+        
+        x = F.relu(self.fc1(x))
+        x = F.relu(self.fc2(x))
+        x = F.relu(self.fc3(x))
+        x = self.fc4(x)
+        return x
+    
+    
+def classify(model, img, trans=None, classes=[], device=torch.device("cpu")):
+    try:
+        model = model.eval()
+        img = img.convert("RGB")
+        img = trans(img)
+        img = img.unsqueeze(0)
+        img = img.to(device)
+
+        output = model(img)
+        _, pred = torch.max(output, 1)
+        procent = torch.sigmoid(output)
+        
+        return f"It {classes[pred.item()].replace('_', ' ')}, I'm {procent[0][pred[0]]*100:.2f}% sure"
+    except Exception:
+        return "Something went wrong😕, please notify the developer with the following message: " + str(Exception)
 
 st.title("Pizza & Not Pizza")
 
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
-checkpoint = torch.load(os.path.join(os.getcwd(), "best.pth.tar"))
+checkpoint = torch.load("best.pth.tar", map_location=device)
 model = checkpoint["model"]
 classes = checkpoint["classes"]
 tran = checkpoint["transform"]
 
 # upload image
-while True:
-    uploaded_file = st.file_uploader("Choose an image...", type="jpg")
-    taking_picture = st.camera_input("Take a picture...")
-    
-    if uploaded_file is not None:
-        img = Image.open(uploaded_file)
-        st.image(img, caption="Uploaded Image.", use_column_width=True)
-        label = classify(model, img, tran, classes, device)
-        st.write(label)
-        
-    elif taking_picture is not None:
-        img = Image.open(taking_picture)
-        st.image(img, caption="Uploaded Image.", use_column_width=True)
-        label = classify(model, img, tran, classes, device)
-        st.write(label)
+uploaded_file = st.file_uploader("Choose an image...", type="jpg")
+taking_picture = st.camera_input("Take a picture...")
+
+if uploaded_file is not None:
+    img = Image.open(uploaded_file)
+    st.image(img, caption="Uploaded Image.", use_column_width=True)
+    label = classify(model, img, tran, classes, device)
+    st.write(label)
     
-    else:
-        pass
+elif taking_picture is not None:
+    img = Image.open(taking_picture)
+    st.image(img, caption="Uploaded Image.", use_column_width=True)
+    label = classify(model, img, tran, classes, device)
+    st.write(label)
+
+else:
+    pass