I'm solving scale invariant.
If you have a good paper,
you can email me by StinkyTofu95@gmail.com. Thanks!
YOLO_v3 implemented with tensorflow
- data augmentation(release)
- multi-scale training(release)
- Focal loss(increase 2 mAP, release)
- Single-Shot Object Detection with Enriched Semantics(incrase 1 mAP, not release)
- Soft-NMS(drop 0.5 mAP, release)
- Group Normalization(didn't use it in project, release)
- Deformable convolutional networks
- Scale-Aware Trident Networks for Object Detection
- Understanding the Effective Receptive Field in Deep Convolutional Neural Networks
- clone YOLO_v3 repository
git clone https://github.com/Stinky-Tofu/YOLO_v3.git
- Download datasets
Create a new folder nameddata
in the directory where theYOLO_V3
folder is located, and then create a new folder namedVOC
in thedata/
.
Download VOC 2012_trainval 、VOC 2007_trainval 、VOC 2007_test, and put datasets intodata/VOC
, name as2012_trainval
、2007_trainval
、2007_test
separately. - Train
Download pretrained weight file yolo_coco_initial.ckpt
python voc_annotation.py
python train.py
--weights_file, default=yolo_coco_initial.ckpt
--gpu, default=0
--batch_size, default=32
--frozen, default=True
--learn_rate_init, default=0.001
- Test
Download weight file yolo_416_87.78%.ckpt
python test.py
--map_calc, default=False
--weights_file, default=None
--gpu, default=0
If you want to get a higher mAP, you can set the score threshold to 0.01.
If you want to apply it, you can set the score threshold to 0.2.
paper:
YOLOv3: An Incremental Improvement
Foca Loss for Dense Object Detection
Group Normalization
Single-Shot Object Detection with Enriched Semantics
An Analysis of Scale Invariance in Object Detection - SNIP
Deformable convolutional networks
Scale-Aware Trident Networks for Object Detection
Understanding the Effective Receptive Field in Deep Convolutional Neural Networks
mAP calculate: mean Average Precision
. Tensorflow
. Opencv
. Python
. Numpy