eliminate external lins to dataset

This commit is contained in:
chengxianbin 2020-05-08 17:15:25 +08:00
parent 453439367c
commit 41b3c30c82
2 changed files with 2 additions and 2 deletions

View File

@ -13,7 +13,7 @@ SSD network based on MobileNetV2, with support for training and evaluation.
We use coco2017 as training dataset in this example by default, and you can also use your own datasets.
1. If coco dataset is used. **Select dataset to coco when run script.**
Download coco2017: [train2017](http://images.cocodataset.org/zips/train2017.zip), [val2017](http://images.cocodataset.org/zips/val2017.zip), [test2017](http://images.cocodataset.org/zips/test2017.zip), [annotations](http://images.cocodataset.org/annotations/annotations_trainval2017.zip). Install pycocotool.
Install Cython and pycocotool.
```
pip install Cython

View File

@ -12,7 +12,7 @@ YOLOv3 network based on ResNet-18, with support for training and evaluation.
We use coco2017 as training dataset.
1. Download coco2017: [train2017](http://images.cocodataset.org/zips/train2017.zip), [val2017](http://images.cocodataset.org/zips/val2017.zip), [test2017](http://images.cocodataset.org/zips/test2017.zip), [annotations](http://images.cocodataset.org/annotations/annotations_trainval2017.zip). The directory structure is as follows:
1. The directory structure is as follows:
> ```
> .
> ├── annotations # annotation jsons