diff --git a/deploy/slim/quantization/export_model.py b/deploy/slim/quantization/export_model.py
index 0cb86108d2275dc6ee1a74e118c27b94131975d3..79d95d04ebf04c927d15f64a0a934082d298460f 100755
--- a/deploy/slim/quantization/export_model.py
+++ b/deploy/slim/quantization/export_model.py
@@ -127,6 +127,7 @@ def main():
     arch_config = config["Architecture"]
     if arch_config["algorithm"] in ["Distillation", ]:  # distillation model
         for idx, name in enumerate(model.model_name_list):
+            model.model_list[idx].eval()
             sub_model_save_path = os.path.join(save_path, name, "inference")
             export_single_model(quanter, model.model_list[idx], infer_shape,
                                 sub_model_save_path, logger)
diff --git a/ppocr/postprocess/rec_postprocess.py b/ppocr/postprocess/rec_postprocess.py
index caaa2948522cb6ea7ed74b8ab79a3d0b465059a3..cddc263a659f30925e257dc1f1a28256f3b31eee 100644
--- a/ppocr/postprocess/rec_postprocess.py
+++ b/ppocr/postprocess/rec_postprocess.py
@@ -87,7 +87,7 @@ class CTCLabelDecode(BaseRecLabelDecode):
                                              use_space_char)
 
     def __call__(self, preds, label=None, *args, **kwargs):
-        if isinstance(preds, tuple):
+        if isinstance(preds, (tuple, list)):
             preds = preds[-1]
         if isinstance(preds, paddle.Tensor):
             preds = preds.numpy()
diff --git a/tools/infer/utility.py b/tools/infer/utility.py
index 7b7b81e3cd22c12561b30e6705eded1c92ec7761..37122f0aa0858281676b43d8c525a113677b2375 100644
--- a/tools/infer/utility.py
+++ b/tools/infer/utility.py
@@ -305,12 +305,22 @@ def create_predictor(args, mode, logger):
         input_names = predictor.get_input_names()
         for name in input_names:
             input_tensor = predictor.get_input_handle(name)
-        output_names = predictor.get_output_names()
-        output_tensors = []
+        output_tensors = get_output_tensors(args, mode, predictor)
+        return predictor, input_tensor, output_tensors, config
+
+
+def get_output_tensors(args, mode, predictor):
+    output_names = predictor.get_output_names()
+    output_tensors = []
+    if mode == "rec" and args.rec_algorithm == "CRNN":
+        output_name = 'softmax_0.tmp_0'
+        if output_name in output_names:
+            return [predictor.get_output_handle(output_name)]
+    else:
         for output_name in output_names:
             output_tensor = predictor.get_output_handle(output_name)
             output_tensors.append(output_tensor)
-        return predictor, input_tensor, output_tensors, config
+    return output_tensors
 
 
 def get_infer_gpuid():