Upload app.py

app.py

@@ -0,0 +1,96 @@
+from ultralytics import YOLO
+import cv2
+import streamlit as st
+import os
+import numpy as np
+
+st.set_page_config(layout="wide")
+model = None
+user_inputs = {}
+
+with st.sidebar:
+    st.title("Calculate Product Costs from Images")
+    st.write("Simplify pricing with AI-powered image recognition and price summation.")
+    st.text("1.Upload Model (YOLO or etc.)\n2.Set The price (Default is 0)\n3.Upload An Image\n(Optional) 4.Set The Model Confidence")
+
+    model_file = st.file_uploader("Upload your model file (.pt)", type=["pt"])
+    
+    if model_file is not None:
+        # st.success(f"Model file '{model_file.name}' uploaded successfully!")
+        temp_model_path = os.path.join("./", model_file.name)
+        with open(temp_model_path, "wb") as f:
+            f.write(model_file.getbuffer())
+        st.success(f"Model file '{model_file.name}' uploaded and saved successfully!")
+        
+        try:
+            model = YOLO(temp_model_path)
+            st.success("Model loaded successfully!")
+            class_names = model.names
+
+            st.write("Enter The Prices:")
+            for idx, name in class_names.items():
+                user_input = st.text_input(f"Class {idx}: {name}", key=f"class_{idx}")
+                user_inputs[idx] = user_input
+
+            if 'collected_list' not in st.session_state:
+                st.session_state.collected_list = []
+
+            if st.button("Submit"):
+                st.write("Collected Inputs:")
+                st.session_state.collected_list = []
+                for idx in range(len(class_names)):
+                    if user_inputs[idx] == "":
+                        user_inputs[idx] = 0
+                    elif not user_inputs[idx].isdigit():
+                        user_inputs[idx] = 0
+                    st.session_state.collected_list.append(int(user_inputs[idx]))
+                st.write(st.session_state.collected_list)
+        except Exception as e:
+            st.error(f"Error loading model: {e}")
+    else:
+        st.warning("Please upload a model file that ends with .pt")
+        
+if model != None:
+    
+    st.subheader("Image Display")
+    image_placeholder = st.empty()
+
+    uploaded_image = st.file_uploader("Upload an image to display", type=["png", "jpg", "jpeg"], key="image")
+    conf_str = st.text_input(f"Model Confidence (Default is 0.5)")
+    if uploaded_image is not None:
+        file_bytes = np.asarray(bytearray(uploaded_image.read()), dtype=np.uint8)
+        img = cv2.imdecode(file_bytes, cv2.IMREAD_COLOR)
+        
+    if st.button("Predict The Image"):
+        if model is not None and uploaded_image is not None:
+            if st.session_state.collected_list != []:
+                try:
+                    conf_ = float(conf_str)
+                except Exception as e:
+                    if not isinstance(conf_str, float):
+                        conf_  = 0.5
+                        
+                results = model.predict(source=img, conf=conf_)
+                if 'sum_price' not in st.session_state:
+                    st.session_state.sum_price = 0
+                    
+                for result in results:
+                    for box in result.boxes:
+                        # Get box coordinates
+                        x1, y1, x2, y2 = box.xyxy[0].cpu().numpy().astype(int)
+                        cls = int(box.cls[0])
+                        conf = box.conf[0]
+                        st.write(f"{result.names[int(box.cls[0])]} : {st.session_state.collected_list[int(box.cls[0])]}")
+                        st.session_state.sum_price += st.session_state.collected_list[int(box.cls[0])]
+                        label = f"{result.names[int(box.cls[0])]}: {conf:.2f}"
+                        cv2.rectangle(img, (x1, y1), (x2, y2), (0, 255, 0), 2)
+                        cv2.putText(img, label, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (0, 255, 0), 2)
+            
+                st.subheader(f"Sum Price: {st.session_state.sum_price}")
+                st.image(img, channels="BGR", caption="Uploaded Image")
+                st.session_state.sum_price = 0
+            else:
+                st.warning("Please Submit The Price")
+        else:
+            st.warning("Please Upload an Image")
+