diff --git a/tools/infer/utility.py b/tools/infer/utility.py
old mode 100755
new mode 100644
index db2ec9c80ddfdd8d42f0429abb40196820baa805..af6c54bb1cc8aeadd1687df5fbd70c16c2cc8b4b
--- a/tools/infer/utility.py
+++ b/tools/infer/utility.py
@@ -159,93 +159,7 @@ def create_predictor(args, mode, logger):
         sess = ort.InferenceSession(model_file_path)
         return sess, sess.get_inputs()[0], None, None
 
-    if args.use_gpu:
-        gpu_id = get_infer_gpuid()
-        if gpu_id is None:
-            raise ValueError(
-                "Not found GPU in current device. Please check your device or set args.use_gpu as False"
-            )
-        config.enable_use_gpu(args.gpu_mem, 0)
-        if args.use_tensorrt:
-            config.enable_tensorrt_engine(
-                workspace_size=1 << 30,
-                precision_mode=precision,
-                max_batch_size=args.max_batch_size,
-                min_subgraph_size=args.min_subgraph_size)
-            # skip the minmum trt subgraph
-        if mode == "det":
-            min_input_shape = {
-                "x": [1, 3, 50, 50],
-                "conv2d_92.tmp_0": [1, 120, 20, 20],
-                "conv2d_91.tmp_0": [1, 24, 10, 10],
-                "conv2d_59.tmp_0": [1, 96, 20, 20],
-                "nearest_interp_v2_1.tmp_0": [1, 256, 10, 10],
-                "nearest_interp_v2_2.tmp_0": [1, 256, 20, 20],
-                "conv2d_124.tmp_0": [1, 256, 20, 20],
-                "nearest_interp_v2_3.tmp_0": [1, 64, 20, 20],
-                "nearest_interp_v2_4.tmp_0": [1, 64, 20, 20],
-                "nearest_interp_v2_5.tmp_0": [1, 64, 20, 20],
-                "elementwise_add_7": [1, 56, 2, 2],
-                "nearest_interp_v2_0.tmp_0": [1, 256, 2, 2]
-            }
-            max_input_shape = {
-                "x": [1, 3, 2000, 2000],
-                "conv2d_92.tmp_0": [1, 120, 400, 400],
-                "conv2d_91.tmp_0": [1, 24, 200, 200],
-                "conv2d_59.tmp_0": [1, 96, 400, 400],
-                "nearest_interp_v2_1.tmp_0": [1, 256, 200, 200],
-                "conv2d_124.tmp_0": [1, 256, 400, 400],
-                "nearest_interp_v2_2.tmp_0": [1, 256, 400, 400],
-                "nearest_interp_v2_3.tmp_0": [1, 64, 400, 400],
-                "nearest_interp_v2_4.tmp_0": [1, 64, 400, 400],
-                "nearest_interp_v2_5.tmp_0": [1, 64, 400, 400],
-                "elementwise_add_7": [1, 56, 400, 400],
-                "nearest_interp_v2_0.tmp_0": [1, 256, 400, 400]
-            }
-            opt_input_shape = {
-                "x": [1, 3, 640, 640],
-                "conv2d_92.tmp_0": [1, 120, 160, 160],
-                "conv2d_91.tmp_0": [1, 24, 80, 80],
-                "conv2d_59.tmp_0": [1, 96, 160, 160],
-                "nearest_interp_v2_1.tmp_0": [1, 256, 80, 80],
-                "nearest_interp_v2_2.tmp_0": [1, 256, 160, 160],
-                "conv2d_124.tmp_0": [1, 256, 160, 160],
-                "nearest_interp_v2_3.tmp_0": [1, 64, 160, 160],
-                "nearest_interp_v2_4.tmp_0": [1, 64, 160, 160],
-                "nearest_interp_v2_5.tmp_0": [1, 64, 160, 160],
-                "elementwise_add_7": [1, 56, 40, 40],
-                "nearest_interp_v2_0.tmp_0": [1, 256, 40, 40]
-            }
-            min_pact_shape = {
-                "nearest_interp_v2_26.tmp_0": [1, 256, 20, 20],
-                "nearest_interp_v2_27.tmp_0": [1, 64, 20, 20],
-                "nearest_interp_v2_28.tmp_0": [1, 64, 20, 20],
-                "nearest_interp_v2_29.tmp_0": [1, 64, 20, 20]
-            }
-            max_pact_shape = {
-                "nearest_interp_v2_26.tmp_0": [1, 256, 400, 400],
-                "nearest_interp_v2_27.tmp_0": [1, 64, 400, 400],
-                "nearest_interp_v2_28.tmp_0": [1, 64, 400, 400],
-                "nearest_interp_v2_29.tmp_0": [1, 64, 400, 400]
-            }
-            opt_pact_shape = {
-                "nearest_interp_v2_26.tmp_0": [1, 256, 160, 160],
-                "nearest_interp_v2_27.tmp_0": [1, 64, 160, 160],
-                "nearest_interp_v2_28.tmp_0": [1, 64, 160, 160],
-                "nearest_interp_v2_29.tmp_0": [1, 64, 160, 160]
-            }
-            min_input_shape.update(min_pact_shape)
-            max_input_shape.update(max_pact_shape)
-            opt_input_shape.update(opt_pact_shape)
-        elif mode == "rec":
-            min_input_shape = {"x": [1, 3, 32, 10]}
-            max_input_shape = {"x": [args.rec_batch_num, 3, 32, 2000]}
-            opt_input_shape = {"x": [args.rec_batch_num, 3, 32, 320]}
-        elif mode == "cls":
-            min_input_shape = {"x": [1, 3, 48, 10]}
-            max_input_shape = {"x": [args.rec_batch_num, 3, 48, 2000]}
-            opt_input_shape = {"x": [args.rec_batch_num, 3, 48, 320]}
-
+    else:
         model_file_path = model_dir + "/inference.pdmodel"
         params_file_path = model_dir + "/inference.pdiparams"
         if not os.path.exists(model_file_path):
@@ -276,6 +190,7 @@ def create_predictor(args, mode, logger):
             config.enable_use_gpu(args.gpu_mem, 0)
             if args.use_tensorrt:
                 config.enable_tensorrt_engine(
+                    workspace_size=1 << 30,
                     precision_mode=precision,
                     max_batch_size=args.max_batch_size,
                     min_subgraph_size=args.min_subgraph_size)
@@ -396,13 +311,10 @@ def create_predictor(args, mode, logger):
 
 
 def get_infer_gpuid():
-    cmd = "nvidia-smi"
-    try:
-        res = os.popen(cmd).readlines()
-    except:
-        res = None
-    if len(res) == 0:
-        return None
+    #cmd = "nvidia-smi"
+    #res = os.popen(cmd).readlines()
+    #if len(res) == 0:
+    #    return None
     cmd = "env | grep CUDA_VISIBLE_DEVICES"
     env_cuda = os.popen(cmd).readlines()
     if len(env_cuda) == 0: