diff --git a/docs/images/PULC/docs/safety_helmet_data_demo.jpg b/docs/images/PULC/docs/safety_helmet_data_demo.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..70bd2d952fd20e6f8fe39182914e400177d913c4
Binary files /dev/null and b/docs/images/PULC/docs/safety_helmet_data_demo.jpg differ
diff --git a/docs/images/PULC/docs/safety_helmet_data_demo.png b/docs/images/PULC/docs/safety_helmet_data_demo.png
deleted file mode 100644
index 8e2f1c4afe460bf2e0867c3bd35dc22fd3211293..0000000000000000000000000000000000000000
Binary files a/docs/images/PULC/docs/safety_helmet_data_demo.png and /dev/null differ
diff --git a/docs/zh_CN/PULC/PULC_safety_helmet.md b/docs/zh_CN/PULC/PULC_safety_helmet.md
index a7f348beb1e38aeada6d1235b270dbc1843d3753..dd8ae93896986924ae234da30ef90ce33fd9c95f 100644
--- a/docs/zh_CN/PULC/PULC_safety_helmet.md
+++ b/docs/zh_CN/PULC/PULC_safety_helmet.md
@@ -165,7 +165,7 @@ print(next(result))
 
 处理后的数据集部分数据可视化如下：
 
-![](../../images/PULC/docs/safety_helmet_data_demo.png)
+![](../../images/PULC/docs/safety_helmet_data_demo.jpg)
 
 此处提供了经过上述方法处理好的数据，可以直接下载得到。
 
@@ -217,7 +217,7 @@ python3 -m paddle.distributed.launch \
     -c ./ppcls/configs/PULC/safety_helmet/PPLCNet_x1_0.yaml
 ```
 
-验证集的最佳指标在 `0.975-0.985` 之间（数据集较小，容易造成波动）。
+验证集的最佳指标在 `0.985-0.993` 之间（数据集较小，容易造成波动）。
 
 **备注：**
 
diff --git a/ppcls/configs/PULC/safety_helmet/MobileNetV3_small_x0_35.yaml b/ppcls/configs/PULC/safety_helmet/MobileNetV3_small_x0_35.yaml
index 2b536e1b99cf9656c8ed141c50e62bfee6bfc762..9ef4beb79db475869414ec3c6e7b9ade3e24b50a 100644
--- a/ppcls/configs/PULC/safety_helmet/MobileNetV3_small_x0_35.yaml
+++ b/ppcls/configs/PULC/safety_helmet/MobileNetV3_small_x0_35.yaml
@@ -36,7 +36,7 @@ Optimizer:
   momentum: 0.9
   lr:
     name: Cosine
-    learning_rate: 0.4
+    learning_rate: 0.08
     warmup_epoch: 5
   regularizer:
     name: 'L2'
@@ -66,11 +66,11 @@ DataLoader:
 
     sampler:
       name: DistributedBatchSampler
-      batch_size: 64
+      batch_size: 512
       drop_last: False
       shuffle: True
     loader:
-      num_workers: 4
+      num_workers: 8
       use_shared_memory: True
 
   Eval: