Skip to content

SeetaResearch / SeetaDet

Go to a project
Commit 169218d4 by Ting PAN
Options

Update README.md

1 parent 8558d3df
Inline Side-by-side
Showing with 14 additions and 12 deletions
README.md
......@@ -7,7 +7,7 @@ including R-CNN series, SSD, and RetinaNet.
We have achieved the same or higher performance than the baseline reported by the original paper.
This repository is based on our [Dragon](https://github.com/seetaresearch/Dragon),
This repository is based on [Dragon](https://github.com/seetaresearch/dragon),
while the style of codes is PyTorch.
The torch-style codes help us to simplify the hierarchical pipeline of modern detection.
......@@ -40,7 +40,7 @@ cd SeetaDet && python setup.py install
You can also install it from remote repository:
```bash
pip install git+https://gitlab.seetatech.com/seetaresearch/SeetaDet.git@master
pip install git+https://gitlab.seetatech.com/seetaresearch/seetadet.git@master
```
## Quick Start
......@@ -52,7 +52,7 @@ cd tools
python train.py --cfg <MODEL_YAML>
```
We have provided the default YAML examples into ``SeetaDet/configs``.
We have provided the default YAML examples into ``seetadet/configs``.
#### Test a detection model
......@@ -80,13 +80,13 @@ python export.py --cfg <MODEL_YAML> --exp_dir <EXP_DIR> --iter <ITERATION>
| Model | Usage |
| :------: | :------: |
| [VGG16.SSD](http://dragon.seetatech.com/download/models/SeetaDet/imagenet/VGG16.SSD.pth)| SSD |
| [VGG16.RCNN](http://dragon.seetatech.com/download/models/SeetaDet/imagenet/VGG16.RCNN.pth)| R-CNN |
| [R-18.Affine](http://dragon.seetatech.com/download/models/SeetaDet/imagenet/R-18.Affine.pth)| R-CNN, RetinaNet, SSD |
| [R-34.Affine](http://dragon.seetatech.com/download/models/SeetaDet/imagenet/R-34.Affine.pth)| R-CNN, RetinaNet, SSD |
| [R-50.Affine](http://dragon.seetatech.com/download/models/SeetaDet/imagenet/R-50.Affine.pth)| R-CNN, RetinaNet, SSD |
| [R-101.Affine](http://dragon.seetatech.com/download/models/SeetaDet/imagenet/R-101.Affine.pth)| R-CNN, RetinaNet, SSD |
| [AirNet.Affine](http://dragon.seetatech.com/download/models/SeetaDet/imagenet/AirNet.Affine.pth)| R-CNN, RetinaNet, SSD |
| [VGG16.SSD](https://dragon.seetatech.com/download/models/seetadet/imagenet/VGG16.SSD.pth)| SSD |
| [VGG16.RCNN](https://dragon.seetatech.com/download/models/seetadet/imagenet/VGG16.RCNN.pth)| R-CNN |
| [R-18.Affine](https://dragon.seetatech.com/download/models/seetadet/imagenet/R-18.Affine.pth)| R-CNN, RetinaNet, SSD |
| [R-34.Affine](https://dragon.seetatech.com/download/models/seetadet/imagenet/R-34.Affine.pth)| R-CNN, RetinaNet, SSD |
| [R-50.Affine](https://dragon.seetatech.com/download/models/seetadet/imagenet/R-50.Affine.pth)| R-CNN, RetinaNet, SSD |
| [R-101.Affine](https://dragon.seetatech.com/download/models/seetadet/imagenet/R-101.Affine.pth)| R-CNN, RetinaNet, SSD |
| [AirNet.Affine](https://dragon.seetatech.com/download/models/seetadet/imagenet/AirNet.Affine.pth)| R-CNN, RetinaNet, SSD |
## References
......
seetadet/utils/boxes_v2.py
......@@ -61,11 +61,13 @@ def ioa2(boxes1, boxes2):
area = np.expand_dims(boxes_area(boxes2), axis=0)
return inter / area
def iou(boxes1, boxes2):
"""Computes pairwise intersection-over-union between box collections."""
inter = intersection(boxes1, boxes2)
area1 = boxes_area(boxes1)
area2 = boxes_area(boxes2)
union = np.expand_dims(area1, axis=1) + \
np.expand_dims(area2, axis=0) - inter
union = \
np.expand_dims(area1, axis=1) + \
np.expand_dims(area2, axis=0) - inter
return inter / union
Markdown is supported
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!