forked from mindspore-Ecosystem/mindspore
eliminate external lins to dataset
This commit is contained in:
parent
453439367c
commit
41b3c30c82
|
@ -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
|
||||
|
|
|
@ -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
|
||||
|
|
Loading…
Reference in New Issue