diff --git a/examples/yolov3/.gitignore b/examples/yolov3/.gitignore
index 01cdc1cbde3507576115b3a9832be30158e56fe5..19ac4b2c67adf15aaa730c8b9823a2b5c2da8780 100644
--- a/examples/yolov3/.gitignore
+++ b/examples/yolov3/.gitignore
@@ -1 +1,2 @@
 dataset/voc*
+pretrain_weights/darknet53_pretrained.pdparams
diff --git a/examples/yolov3/README.md b/examples/yolov3/README.md
index cc6d302a544f9b8d9cd06fc363b90d053919a5e9..a8784ac88a4cb1dd3d72424ff749c1b239faa87f 100644
--- a/examples/yolov3/README.md
+++ b/examples/yolov3/README.md
@@ -99,9 +99,17 @@ YOLOv3 的网络结构由基础特征提取网络、multi-scale特征融合层
   |   ...
   ```
 
+### 预训练权重下载
+
+YOLOv3模型训练需下载骨干网络DarkNet53的预训练权重，可通过如下方式下载。
+
+```bash
+sh pretrain_weights/download.sh
+```
+
 ### 模型训练
 
-数据准备完毕后，可使用`main.py`脚本启动训练和评估，如下脚本会自动每epoch交替进行训练和模型评估，并将checkpoint默认保存在`yolo_checkpoint`目录下。
+数据和预训练权重下载完成后，可使用`main.py`脚本启动训练和评估，如下脚本会自动每epoch交替进行训练和模型评估，并将checkpoint默认保存在`yolo_checkpoint`目录下。
 
 YOLOv3模型训练总batch_size为64训练，以下以使用4卡Tesla P40每卡batch_size为16训练介绍训练方式。对于静态图和动态图，多卡训练中`--batch_size`为每卡上的batch_size，即总batch_size为`--batch_size`乘以卡数。
 
@@ -117,7 +125,7 @@ python main.py --help
 使用如下方式进行多卡训练:
 
 ```bash
-CUDA_VISIBLE_DEVICES=0,1,2,3 python -m paddle.distributed.launch main.py --data=<path/to/dataset> --batch_size=16
+CUDA_VISIBLE_DEVICES=0,1,2,3 python -m paddle.distributed.launch main.py --data=<path/to/dataset> --batch_size=16 --pretrain_weights=./pretrain_weights/darknet53_pretrained
 ```
 
 #### 动态图训练
@@ -127,7 +135,7 @@ CUDA_VISIBLE_DEVICES=0,1,2,3 python -m paddle.distributed.launch main.py --data=
 使用如下方式进行多卡训练:
 
 ```bash
-CUDA_VISIBLE_DEVICES=0,1,2,3 python main.py -m paddle.distributed.launch --data=<path/to/dataset> --batch_size=16 -d
+CUDA_VISIBLE_DEVICES=0,1,2,3 python main.py -m paddle.distributed.launch --data=<path/to/dataset> --batch_size=16 -d --pretrain_weights=./pretrain_weights/darknet53_pretrained
 ```
 
 
diff --git a/examples/yolov3/main.py b/examples/yolov3/main.py
index ebe85543712d82267eaded26da4c1db8800b735f..89ba67756844551760ca70c9074eb7c316d8dbc0 100644
--- a/examples/yolov3/main.py
+++ b/examples/yolov3/main.py
@@ -28,6 +28,7 @@ from paddle.io import DataLoader
 from hapi.model import Model, Input, set_device
 from hapi.distributed import DistributedBatchSampler
 from hapi.datasets import COCODataset
+from hapi.download import get_weights_path
 from hapi.vision.transforms import *
 from hapi.vision.models import yolov3_darknet53, YoloLoss
 
@@ -124,7 +125,7 @@ def main():
                    model_mode='eval' if FLAGS.eval_only else 'train',
                    pretrained=pretrained)
 
-    if FLAGS.pretrain_weights is not None:
+    if FLAGS.pretrain_weights and not FLAGS.eval_only:
         model.load(FLAGS.pretrain_weights, skip_mismatch=True, reset_optimizer=True)
 
     optim = make_optimizer(len(batch_sampler), parameter_list=model.parameters())
@@ -196,7 +197,8 @@ if __name__ == '__main__':
     parser.add_argument(
         "-j", "--num_workers", default=4, type=int, help="reader worker number")
     parser.add_argument(
-        "-p", "--pretrain_weights", default=None, type=str,
+        "-p", "--pretrain_weights",
+        default="./pretrain_weights/darknet53_pretrained", type=str,
         help="path to pretrained weights")
     parser.add_argument(
         "-r", "--resume", default=None, type=str,
diff --git a/examples/yolov3/pretrain_weights/download.sh b/examples/yolov3/pretrain_weights/download.sh
new file mode 100644
index 0000000000000000000000000000000000000000..6982f441969069ea2b53de5242fa455161119573
--- /dev/null
+++ b/examples/yolov3/pretrain_weights/download.sh
@@ -0,0 +1,5 @@
+DIR="$( cd "$(dirname "$0")" ; pwd -P   )"
+cd "$DIR"
+
+echo "Downloading https://paddlemodels.bj.bcebos.com/hapi/darknet53_pretrained.pdparams"
+wget https://paddlemodels.bj.bcebos.com/hapi/darknet53_pretrained.pdparams
diff --git a/hapi/vision/models/darknet.py b/hapi/vision/models/darknet.py
index 85e25f4e1205ea62ec878409d640ba42e7335ee2..027cb4f2094e37ede347c090c5849cfcbf00611e 100755
--- a/hapi/vision/models/darknet.py
+++ b/hapi/vision/models/darknet.py
@@ -136,7 +136,7 @@ class LayerWarp(fluid.dygraph.Layer):
 DarkNet_cfg = {53: ([1, 2, 8, 8, 4])}
 
 
-class DarkNet(Model):
+class DarkNet(fluid.dygraph.Layer):
     """DarkNet model from
     `"YOLOv3: An Incremental Improvement" <https://arxiv.org/abs/1804.02767>`_
 
diff --git a/hapi/vision/models/yolov3.py b/hapi/vision/models/yolov3.py
index 840a402e3e1b473cc3c3deffc1b2d0fe6e7a2307..bafe148b14b7e1baf8124c61969238e049e2d6f0 100644
--- a/hapi/vision/models/yolov3.py
+++ b/hapi/vision/models/yolov3.py
@@ -118,7 +118,7 @@ class YOLOv3(Model):
         self.nms_posk = 100
         self.draw_thresh = 0.5
 
-        self.backbone = darknet53(pretrained=(model_mode=='train'))
+        self.backbone = darknet53(pretrained=False)
         self.block_outputs = []
         self.yolo_blocks = []
         self.route_blocks = []