diff --git a/app/controller/AlgorithmController.py b/app/controller/AlgorithmController.py
index 3522a89..25897d7 100644
--- a/app/controller/AlgorithmController.py
+++ b/app/controller/AlgorithmController.py
@@ -242,7 +242,7 @@ from app import file_tool
 
 
 # 启动训练
-#@start_train_algorithm()
+@start_train_algorithm()
 def train_R0DY(params_str, id):
     from app.yolov5.train_server import train_start
     params = TrainParams()
@@ -261,60 +261,60 @@ def train_R0DY(params_str, id):
 
 # 启动验证程序
 
-# @start_test_algorithm()
-# def validate_RODY(params_str, id):
-#     from app.yolov5.validate_server import validate_start
-#     params = TrainParams()
-#     params.read_from_str(params_str)
-#     weights = params.get('modPath').value  # 验证模型绝对路径
-#     (filename, extension) = os.path.splitext(weights)  # 文件名与后缀名分开
-#     img_size = int(filename.split('ROD')[1].split('_')[2])  # 获取图像参数
-#     # v_num = int(filename.split('ROD')[1].split('_')[1]) #获取版本号
-#     output = params.get('outputPath').value
-#     batch_size = params.get('batch_size').default
-#     device = params.get('device').value
-#
-#     validate_start(weights, img_size, batch_size, device, output, id)
-#
-#
-# @start_detect_algorithm()
-# def detect_RODY(params_str, id):
-#     from app.yolov5.detect_server import detect_start
-#     params = TrainParams()
-#     params.read_from_str(params_str)
-#     weights = params.get('modPath').value  # 检测模型绝对路径
-#     input = params.get('inputPath').value
-#     outpath = params.get('outputPath').value
-#     # (filename, extension) = os.path.splitext(weights)  # 文件名与后缀名分开
-#     # img_size = int(filename.split('ROD')[1].split('_')[2]) #获取图像参数
-#     # v_num = int(filename.split('ROD')[1].split('_')[1]) #获取版本号
-#     # batch_size = params.get('batch_size').default
-#     device = params.get('device').value
-#
-#     detect_start(input, weights, outpath, device, id)
-#
-#
-# @start_download_pt()
-# def Export_model_RODY(params_str):
-#     from app.yolov5.export import Start_Model_Export
-#     import zipfile
-#     params = TrainParams()
-#     params.read_from_str(params_str)
-#     exp_inputPath = params.get('exp_inputPath').value  # 模型路径
-#     exp_device = params.get('device').value
-#     modellist = Start_Model_Export(exp_inputPath, exp_device)
-#     exp_outputPath = exp_inputPath.replace('pt', 'zip')  # 压缩文件
-#     zipf = zipfile.ZipFile(exp_outputPath, 'w')
-#     for file in modellist:
-#         zipf.write(file, arcname=Path(file).name)  # 将torchscript和onnx模型压缩
-#
-#     return exp_outputPath
-    # zipf.write(modellist[1], arcname=modellist[1])
-    # zip_inputpath = os.path.join(exp_outputPath, "inference_model")
-    # zip_outputPath = os.path.join(exp_outputPath, "inference_model.zip")
+@start_test_algorithm()
+def validate_RODY(params_str, id):
+    from app.yolov5.validate_server import validate_start
+    params = TrainParams()
+    params.read_from_str(params_str)
+    weights = params.get('modPath').value  # 验证模型绝对路径
+    (filename, extension) = os.path.splitext(weights)  # 文件名与后缀名分开
+    img_size = int(filename.split('ROD')[1].split('_')[2])  # 获取图像参数
+    # v_num = int(filename.split('ROD')[1].split('_')[1]) #获取版本号
+    output = params.get('outputPath').value
+    batch_size = params.get('batch_size').default
+    device = params.get('device').value
+
+    validate_start(weights, img_size, batch_size, device, output, id)
 
 
-#@obtain_train_param()
+@start_detect_algorithm()
+def detect_RODY(params_str, id):
+    from app.yolov5.detect_server import detect_start
+    params = TrainParams()
+    params.read_from_str(params_str)
+    weights = params.get('modPath').value  # 检测模型绝对路径
+    input = params.get('inputPath').value
+    outpath = params.get('outputPath').value
+    # (filename, extension) = os.path.splitext(weights)  # 文件名与后缀名分开
+    # img_size = int(filename.split('ROD')[1].split('_')[2]) #获取图像参数
+    # v_num = int(filename.split('ROD')[1].split('_')[1]) #获取版本号
+    # batch_size = params.get('batch_size').default
+    device = params.get('device').value
+
+    detect_start(input, weights, outpath, device, id)
+
+
+@start_download_pt()
+def Export_model_RODY(params_str):
+    from app.yolov5.export import Start_Model_Export
+    import zipfile
+    params = TrainParams()
+    params.read_from_str(params_str)
+    exp_inputPath = params.get('exp_inputPath').value  # 模型路径
+    exp_device = params.get('device').value
+    modellist = Start_Model_Export(exp_inputPath, exp_device)
+    exp_outputPath = exp_inputPath.replace('pt', 'zip')  # 压缩文件
+    zipf = zipfile.ZipFile(exp_outputPath, 'w')
+    for file in modellist:
+        zipf.write(file, arcname=Path(file).name)  # 将torchscript和onnx模型压缩
+
+    return exp_outputPath
+    zipf.write(modellist[1], arcname=modellist[1])
+    zip_inputpath = os.path.join(exp_outputPath, "inference_model")
+    zip_outputPath = os.path.join(exp_outputPath, "inference_model.zip")
+
+
+@obtain_train_param()
 def returnTrainParams():
     # nvmlInit()
     # gpuDeviceCount = nvmlDeviceGetCount()  # 获取Nvidia GPU块数
@@ -347,63 +347,63 @@ def returnTrainParams():
     return params_str
 
 
-# @obtain_test_param()
-# def returnValidateParams():
-#     # nvmlInit()
-#     # gpuDeviceCount = nvmlDeviceGetCount()  # 获取Nvidia GPU块数
-#     # _kernel = [f"cuda:{a}" for a in range(gpuDeviceCount)]
-#     params_list = [
-#         {"index": 0, "name": "modPath", "value": "E:/alg_demo-master/alg_demo/app/yolov5/圆孔_123_RODY_1_640.pt",
-#          "description": '验证模型路径', "default": "./app/maskrcnn/saved_model/test.pt", "type": "S", 'show': False},
-#         {"index": 1, "name": "batch_size", "value": 1, "description": '批次图像数量', "default": 1, "type": "I",
-#          'show': False},
-#         {"index": 2, "name": "img_size", "value": 640, "description": '训练图像大小', "default": 640, "type": "I",
-#          'show': False},
-#         {"index": 3, "name": "outputPath", "value": 'E:/aicheck/data_set/11442136178662604800/val_results/',
-#          "description": '输出结果路径',
-#          "default": './app/maskrcnn/datasets/M006B_waibi/res', "type": "S", 'show': False},
-#         {"index": 4, "name": "device", "value": "0", "description": '训练核心', "default": "cuda", "type": "S",
-#          "items": '', 'show': False}  # _kernel
-#     ]
-#     # {"index": 9, "name": "saveEpoch", "value": 2, "description": '保存模型轮次', "default": 2, "type": "I", 'show': True}]
-#     params_str = json.dumps(params_list)
-#     return params_str
-#
-#
-# @obtain_detect_param()
-# def returnDetectParams():
-#     # nvmlInit()
-#     # gpuDeviceCount = nvmlDeviceGetCount()  # 获取Nvidia GPU块数
-#     # _kernel = [f"cuda:{a}" for a in range(gpuDeviceCount)]
-#     params_list = [
-#         {"index": 0, "name": "inputPath", "value": 'E:/aicheck/data_set/11442136178662604800/input/',
-#          "description": '输入图像路径', "default": './app/maskrcnn/datasets/M006B_waibi/JPEGImages', "type": "S",
-#          'show': False},
-#         {"index": 1, "name": "outputPath", "value": 'E:/aicheck/data_set/11442136178662604800/val_results/',
-#          "description": '输出结果路径',
-#          "default": './app/maskrcnn/datasets/M006B_waibi/res', "type": "S", 'show': False},
-#         {"index": 0, "name": "modPath", "value": "E:/alg_demo-master/alg_demo/app/yolov5/圆孔_123_RODY_1_640.pt",
-#          "description": '模型路径', "default": "./app/maskrcnn/saved_model/test.pt", "type": "S", 'show': False},
-#         {"index": 3, "name": "device", "value": "0", "description": '推理核', "default": "cpu", "type": "S",
-#          'show': False},
-#     ]
-#     # {"index": 9, "name": "saveEpoch", "value": 2, "description": '保存模型轮次', "default": 2, "type": "I", 'show': True}]
-#     params_str = json.dumps(params_list)
-#     return params_str
-#
-#
-# @obtain_download_pt_param()
-# def returnDownloadParams():
-#     params_list = [
-#         {"index": 0, "name": "exp_inputPath", "value": 'E:/alg_demo-master/alg_demo/app/yolov5/圆孔_123_RODY_1_640.pt',
-#          "description": '转化模型输入路径',
-#          "default": '/mnt/sdc/IntelligentizeAI/IntelligentizeAI/data_set/weights/new磁环检测test_183504733393264640_R-DDM_11.pt/',
-#          "type": "S", 'show': False},
-#         {"index": 1, "name": "device", "value": 'gpu', "description": 'CPU或GPU', "default": 'gpu', "type": "S",
-#          'show': False}
-#     ]
-#     params_str = json.dumps(params_list)
-#     return params_str
+@obtain_test_param()
+def returnValidateParams():
+    # nvmlInit()
+    # gpuDeviceCount = nvmlDeviceGetCount()  # 获取Nvidia GPU块数
+    # _kernel = [f"cuda:{a}" for a in range(gpuDeviceCount)]
+    params_list = [
+        {"index": 0, "name": "modPath", "value": "E:/alg_demo-master/alg_demo/app/yolov5/圆孔_123_RODY_1_640.pt",
+         "description": '验证模型路径', "default": "./app/maskrcnn/saved_model/test.pt", "type": "S", 'show': False},
+        {"index": 1, "name": "batch_size", "value": 1, "description": '批次图像数量', "default": 1, "type": "I",
+         'show': False},
+        {"index": 2, "name": "img_size", "value": 640, "description": '训练图像大小', "default": 640, "type": "I",
+         'show': False},
+        {"index": 3, "name": "outputPath", "value": 'E:/aicheck/data_set/11442136178662604800/val_results/',
+         "description": '输出结果路径',
+         "default": './app/maskrcnn/datasets/M006B_waibi/res', "type": "S", 'show': False},
+        {"index": 4, "name": "device", "value": "0", "description": '训练核心', "default": "cuda", "type": "S",
+         "items": '', 'show': False}  # _kernel
+    ]
+    # {"index": 9, "name": "saveEpoch", "value": 2, "description": '保存模型轮次', "default": 2, "type": "I", 'show': True}]
+    params_str = json.dumps(params_list)
+    return params_str
+
+
+@obtain_detect_param()
+def returnDetectParams():
+    # nvmlInit()
+    # gpuDeviceCount = nvmlDeviceGetCount()  # 获取Nvidia GPU块数
+    # _kernel = [f"cuda:{a}" for a in range(gpuDeviceCount)]
+    params_list = [
+        {"index": 0, "name": "inputPath", "value": 'E:/aicheck/data_set/11442136178662604800/input/',
+         "description": '输入图像路径', "default": './app/maskrcnn/datasets/M006B_waibi/JPEGImages', "type": "S",
+         'show': False},
+        {"index": 1, "name": "outputPath", "value": 'E:/aicheck/data_set/11442136178662604800/val_results/',
+         "description": '输出结果路径',
+         "default": './app/maskrcnn/datasets/M006B_waibi/res', "type": "S", 'show': False},
+        {"index": 0, "name": "modPath", "value": "E:/alg_demo-master/alg_demo/app/yolov5/圆孔_123_RODY_1_640.pt",
+         "description": '模型路径', "default": "./app/maskrcnn/saved_model/test.pt", "type": "S", 'show': False},
+        {"index": 3, "name": "device", "value": "0", "description": '推理核', "default": "cpu", "type": "S",
+         'show': False},
+    ]
+    # {"index": 9, "name": "saveEpoch", "value": 2, "description": '保存模型轮次', "default": 2, "type": "I", 'show': True}]
+    params_str = json.dumps(params_list)
+    return params_str
+
+
+@obtain_download_pt_param()
+def returnDownloadParams():
+    params_list = [
+        {"index": 0, "name": "exp_inputPath", "value": 'E:/alg_demo-master/alg_demo/app/yolov5/圆孔_123_RODY_1_640.pt',
+         "description": '转化模型输入路径',
+         "default": '/mnt/sdc/IntelligentizeAI/IntelligentizeAI/data_set/weights/new磁环检测test_183504733393264640_R-DDM_11.pt/',
+         "type": "S", 'show': False},
+        {"index": 1, "name": "device", "value": 'gpu', "description": 'CPU或GPU', "default": 'gpu', "type": "S",
+         'show': False}
+    ]
+    params_str = json.dumps(params_list)
+    return params_str
 
 
 if __name__ == '__main__':