python目標檢測實現黑花屏分類任務示例

OBJECT_DICT = {"Normalscreen": 0, "Colorfulscreen": 1, "Blackscreen": 2}
def parse_json_file(image_path):
    imageName = os.path.basename(image_path).split('.')[0]
    img = cv2.imread(image_path)
    size = img.shape
    label = image_path.split('/')[4].split('\\')[0]
    label = OBJECT_DICT.get(label)
    imageWidth = size[0]
    imageHeight = size[1]
    label_dict = {}
    xmin, ymin = (0, 0)
    xmax, ymax = (imageWidth, imageHeight)
    xcenter = (xmin + xmax) / 2
    xcenter = xcenter / float(imageWidth)
    ycenter = (ymin + ymax) / 2
    ycenter = ycenter / float(imageHeight)
    width = ((xmax - xmin) / float(imageWidth))
    heigt = ((ymax - ymin) / float(imageHeight))
    label_dict.update({label: [str(xcenter), str(ycenter), str(width), str(heigt)]})
    label_dict = sorted(label_dict.items(), key=lambda x: x[0])
    return imageName, label_dict

# 加載數據，獲取訓練集、測試集圖片路徑
with open(opt.data) as f:
    data_dict = yaml.load(f, Loader=yaml.FullLoader)  
    with torch_distributed_zero_first(rank):
        check_dataset(data_dict) 
train_path = data_dict['train']
test_path = data_dict['val']
Number_class, names = (1, ['item']) if opt.single_cls else (int(data_dict['nc']), data_dict['names']) 
# 創建模型
model = Model(opt.cfg, ch=3, nc=Number_class).to(device)
# 學習率的設置
lf = lambda x: ((1 + math.cos(x * math.pi / epochs)) / 2) * (1 - hyp['lrf']) + hyp['lrf']  
scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lf)
# 訓練
for epoch in range(start_epoch, epochs):  
model.train()

def compute_loss(p, targets, model):
    device = targets.device
    loss_cls, loss_box, loss_obj = torch.zeros(1, device=device), torch.zeros(1, device=device), torch.zeros(1, device=device)
    tcls, tbox, indices, anchors = build_targets(p, targets, model) 
h = model.hyp
    # 定義損失函數
    BCEcls = nn.BCEWithLogitsLoss(pos_weight=torch.Tensor([h['cls_pw']])).to(device)
    BCEobj = nn.BCEWithLogitsLoss(pos_weight=torch.Tensor([h['obj_pw']])).to(device)
    cp, cn = smooth_BCE(eps=0.0)
    # 損失
    nt = 0  
    np = len(p) 
    balance = [4.0, 1.0, 0.4] if np == 3 else [4.0, 1.0, 0.4, 0.1] 
for i, pi in enumerate(p): 
        image, anchor, gridy, gridx = indices[i]  
        tobj = torch.zeros_like(pi[..., 0], device=device) 
        n = image.shape[0]  
        if n:
            nt += n  # 計算目標
            ps = pi[anchor, image, gridy, gridx]
            pxy = ps[:, :2].sigmoid() * 2. - 0.5
            pwh = (ps[:, 2:4].sigmoid() * 2) ** 2 * anchors[i]
            predicted_box = torch.cat((pxy, pwh), 1).to(device)                    giou = bbox_iou(predicted_box.T, tbox[i], x1y1x2y2=False, CIoU=True)                 
       loss_box += (1.0 - giou).mean() 
            tobj[image, anchor, gridy, gridx] = (1.0 - model.gr) + model.gr *   giou.detach().clamp(0).type(tobj.dtype) 
            if model.nc > 1:
                t = torch.full_like(ps[:, 5:], cn, device=device)
                t[range(n), tcls[i]] = cp
                loss_cls += BCEcls(ps[:, 5:], t)  
        loss_obj += BCEobj(pi[..., 4], tobj) * balance[i]  
    s = 3 / np
    loss_box *= h['giou'] * s
    loss_obj *= h['obj'] * s * (1.4 if np == 4 else 1.)
    loss_cls *= h['cls'] * s
    bs = tobj.shape[0]
    loss = loss_box + loss_obj + loss_cls
    return loss * bs, torch.cat((loss_box, loss_obj, loss_cls, loss)).detach()

def detect(opt,img):
    out, source, weights, view_img, save_txt, imgsz = \
        opt.output, img, opt.weights, opt.view_img, opt.save_txt, opt.img_size
    device = select_device(opt.device)
    half = device.type != 'cpu'
    model = experimental.attempt_load(weights, map_location=device)
    imgsz = check_img_size(imgsz, s=model.stride.max())
    if half:
        model.half()
    img = letterbox(img)[0]
    img = img[:, :, ::-1].transpose(2, 0, 1)
    img = np.ascontiguousarray(img)
    img_warm = torch.zeros((1, 3, imgsz, imgsz), device=device)
    _ = model(img_warm.half() if half else img_warm) if device.type != 'cpu' else None 
    img = torch.from_numpy(img).to(device)
    img = img.half() if half else img.float()
    img /= 255.0
    if img.ndimension() == 3:
        img = img.unsqueeze(0)
    pred = model(img, augment=opt.augment)[0]
    # 應用非極大值抑制
    pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms)
    # 處理檢測的結果
    for i, det in enumerate(pred): 
        if det is not None and len(det):
            det[:, :4] = scale_coords(img.shape[2:], det[:, :4], img.shape).round()
            all_conf = det[:, 4]
            if len(det[:, -1]) > 1:
                ind = torch.max(all_conf, 0)[1]
                c = torch.take(det[:, -1], ind)
detect_class = int(c)
            else:
                for c in det[:, -1]:
                    detect_class = int(c)
            return detect_class