Skip to content

Commit f49036b

Browse files
authored
[cherry-pick] update doc, test=document_fix (#2447)
* update doc, test=document_fix * update doc, test=document_fix
1 parent 7c17ac0 commit f49036b

File tree

3 files changed

+6
-3
lines changed

3 files changed

+6
-3
lines changed

docs/tutorials/PrepareDataSet.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -51,7 +51,7 @@ VOC数据集指的是Pascal VOC比赛使用的数据。用户自定义的VOC数
5151

5252
##### VOC数据集下载
5353

54-
- 通过代码自动化下载VOC数据集
54+
- 通过代码自动化下载VOC数据集,数据集较大,下载需要较长时间
5555

5656
```
5757
# 执行代码自动化下载VOC数据集
@@ -151,11 +151,11 @@ COCO数据集指的是COCO比赛使用的数据。用户自定义的COCO数据
151151
152152
153153
##### COCO数据下载
154-
- 通过代码自动化下载COCO数据集
154+
- 通过代码自动化下载COCO数据集,数据集较大,下载需要较长时间
155155
156156
```
157157
# 执行代码自动化下载COCO数据集
158-
python dataset/voc/download_coco.py
158+
python dataset/coco/download_coco.py
159159
```
160160
161161
代码执行完成后COCO数据集文件组织结构为:

docs/tutorials/QUICK_STARTED.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -73,6 +73,8 @@ visualdl --logdir vdl_dir/scalar/ --host <host_IP> --port <port_num>
7373
python tools/eval.py -c configs/yolov3/yolov3_mobilenet_v1_roadsign.yml -o use_gpu=true
7474
```
7575

76+
The final mAP should be around 0.85. The dataset is small so the precision may vary a little after each training.
77+
7678

7779
### 3、Inference
7880
```

docs/tutorials/QUICK_STARTED_cn.md

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -70,6 +70,7 @@ visualdl --logdir vdl_dir/scalar/ --host <host_IP> --port <port_num>
7070
7171
python tools/eval.py -c configs/yolov3/yolov3_mobilenet_v1_roadsign.yml -o use_gpu=true
7272
```
73+
最终模型精度在mAP=0.85左右,由于数据集较小因此每次训练结束后精度会有一定波动
7374

7475

7576
### 3、预测

0 commit comments

Comments
 (0)