Update src/streamlit_app.py

src/streamlit_app.py

@@ -15,146 +15,110 @@ import sys
 sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
 
 from models.experimental import attempt_load
-from utils.general import check_img_size, check_requirements, check_imshow, non_max_suppression, apply_classifier, \
-    scale_coords, xyxy2xywh, strip_optimizer, set_logging, increment_path
+from utils.general import check_img_size, non_max_suppression, scale_coords
 from utils.plots import plot_one_box
 
 def letterbox(img, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True, stride=32):
-    # Resize and pad image while meeting stride-multiple constraints
     shape = img.shape[:2]  # current shape [height, width]
     if isinstance(new_shape, int):
         new_shape = (new_shape, new_shape)
 
-    # Scale ratio (new / old)
     r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
-    if not scaleup:  # only scale down, do not scale up (for better test mAP)
+    if not scaleup:
         r = min(r, 1.0)
 
-    # Compute padding
-    ratio = r, r  # width, height ratios
+    ratio = r, r
     new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
-    dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1]  # wh padding
-    if auto:  # minimum rectangle
-        dw, dh = np.mod(dw, stride), np.mod(dh, stride)  # wh padding
-    elif scaleFill:  # stretch
+    dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1]
+    if auto:
+        dw, dh = np.mod(dw, stride), np.mod(dh, stride)
+    elif scaleFill:
         dw, dh = 0.0, 0.0
         new_unpad = (new_shape[1], new_shape[0])
-        ratio = new_shape[1] / shape[1], new_shape[0] / shape[0]  # width, height ratios
+        ratio = new_shape[1] / shape[1], new_shape[0] / shape[0]
 
-    dw /= 2  # divide padding into 2 sides
+    dw /= 2
     dh /= 2
 
-    if shape[::-1] != new_unpad:  # resize
+    if shape[::-1] != new_unpad:
         img = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR)
     top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
     left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
-    img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color)  # add border
+    img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color)
     return img, ratio, (dw, dh)
 
-def detect_modify(img0, model, conf=0.4, imgsz=640, conf_thres = 0.25, iou_thres=0.45):
+def detect_modify(img0, model, device, conf=0.4, imgsz=640, conf_thres=0.25, iou_thres=0.45):
     st.image(img0, caption="Your image", use_column_width=True)
 
-    stride = int(model.stride.max())  # model stride
-    imgsz = check_img_size(imgsz, s=stride)  # check img_size
+    stride = int(model.stride.max())
+    imgsz = check_img_size(imgsz, s=stride)
 
-    # Padded resize
     img0 = cv2.cvtColor(np.asarray(img0), cv2.COLOR_RGB2BGR)
     img = letterbox(img0, imgsz, stride=stride)[0]
-    # Convert
-    img = img[:, :, ::-1].transpose(2, 0, 1)  # BGR to RGB, to 3x416x416
+    img = img[:, :, ::-1].transpose(2, 0, 1)
     img = np.ascontiguousarray(img)
 
-    
-    # Get names and colors
     names = model.module.names if hasattr(model, 'module') else model.names
     colors = [[random.randint(0, 255) for _ in range(3)] for _ in names]
 
-    # Run inference
-    old_img_w = old_img_h = imgsz
-    old_img_b = 1
-
-    t0 = time.time()
-    img = torch.from_numpy(img).to(device)
-    # img /= 255.0  # 0 - 255 to 0.0 - 1.0
-    img = img/255.0
+    img = torch.from_numpy(img).to(device).float() / 255.0
     if img.ndimension() == 3:
         img = img.unsqueeze(0)
 
-    # Inference
-    # t1 = time_synchronized()
-    with torch.no_grad():   # Calculating gradients would cause a GPU memory leak
+    with torch.no_grad():
         pred = model(img)[0]
-    # t2 = time_synchronized()
 
-    # Apply NMS
     pred = non_max_suppression(pred, conf_thres, iou_thres)
-    # t3 = time_synchronized()
 
-    # Process detections
-    # for i, det in enumerate(pred):  # detections per image
-        
-    gn = torch.tensor(img0.shape)[[1, 0, 1, 0]]  # normalization gain whwh
+    gn = torch.tensor(img0.shape)[[1, 0, 1, 0]]
 
     det = pred[0]
     if len(det):
-        # Rescale boxes from img_size to im0 size
         det[:, :4] = scale_coords(img.shape[2:], det[:, :4], img0.shape).round()
-
-        # Print results
-        s = ''
-        for c in det[:, -1].unique():
-            n = (det[:, -1] == c).sum()  # detections per class
-            s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string
-
-        # Write results
         for *xyxy, conf, cls in reversed(det):
             label = f'{names[int(cls)]} {conf:.2f}'
             plot_one_box(xyxy, img0, label=label, color=colors[int(cls)], line_thickness=1)
 
-    f"""
-    ### Prediction result:
-    """
-    img0 = cv2.cvtColor(np.asarray(img0), cv2.COLOR_BGR2RGB)
+    img0 = cv2.cvtColor(img0, cv2.COLOR_BGR2RGB)
     st.image(img0, caption="Prediction Result", use_column_width=True)
-
-#set paramters
-
-# 取得目前檔案 (streamlit_app.py) 所在的目錄
+# 取得目前檔案所在目錄
 current_dir = os.path.dirname(os.path.abspath(__file__))
 
-# 回到根目錄後組合出 .pkl 檔案的路徑
+# 模型權重路徑
 weight_path = os.path.join(current_dir, 'best.pt')
 
+# 參數設定
 imgsz = 640
 conf = 0.4
 conf_thres = 0.25
-iou_thres=0.45
+iou_thres = 0.45
 device = torch.device("cpu")
-path = "./"
 
-# Load model
-#model = attempt_load(weight_path, map_location=torch.device('cpu'))  # load FP32 model
-ckpt = torch.load(weight_path, map_location=torch.device('cpu'), weights_only=False)
+# 載入模型
+ckpt = torch.load(weight_path, map_location=device, weights_only=False)
 model = ckpt['ema' if ckpt.get('ema') else 'model'].float().fuse().eval()
 
-"""
-# YOLOv7
-Detect whether a person is wearing a face mask or not.
-"""
-option = st.radio("", ["Upload Image", "Image URL"])
+# Streamlit 介面
+st.title("YOLOv7 Mask Detection")
+st.write("Detect whether a person is wearing a face mask or not.")
 
-if option == "Upload Image":
-    uploaded_file = st.file_uploader("Please upload an image.")
+option = st.radio("Select Input Method", ["Upload Image", "Image URL"])
 
+if option == "Upload Image":
+    uploaded_file = st.file_uploader("Please upload an image.", type=["jpg", "jpeg", "png"])
     if uploaded_file is not None:
         img = PILImage.create(uploaded_file)
-        detect_modify(img, model, conf=conf, imgsz=imgsz, conf_thres=conf_thres, iou_thres=iou_thres)
-else:
-    url = st.text_input("Please input a url.")
-    if url != "":
+        detect_modify(img, model, device, conf=conf, imgsz=imgsz, conf_thres=conf_thres, iou_thres=iou_thres)
+
+elif option == "Image URL":
+    url = st.text_input("Please input an image URL.")
+    if url:
         try:
             response = requests.get(url)
+            response.raise_for_status()  # 檢查 http status
             pil_img = PILImage.create(BytesIO(response.content))
-            detect_modify(pil_img, model, conf=conf, imgsz=imgsz, conf_thres=conf_thres, iou_thres=iou_thres)
-        except:
-            st.text("Problem reading image from", url)
+            detect_modify(pil_img, model, device, conf=conf, imgsz=imgsz, conf_thres=conf_thres, iou_thres=iou_thres)
+        except Exception as e:
+            st.error(f"Problem reading image from URL: {url}")
+            st.error(str(e))
+