资源分类
》 资源 》算法》YOLOv3_tf

YOLOv3_tf

2020-03-04 | |  44 |   0 |   0

YOLOv3_tf

Try to implement YOLOv3 with TensorFlow

  1. transform darknet weight into npz: save_npz.py

  2. darknet 52 conv layer: darknet53_trainable.py

  3. yolo layer(loss & predict): yolo_layer.py

图片.png

train (train_net.py)

1. for now, only train detector layer(50 epoch, batch size: 8)
2. froze feature extractor('darknet53.conv.74')
3. TODO: finetune end2end

traindata: VOC2007 trainval & VOC2012 trainval

sample prediction (predict_net.py)



图片.png

trained weights

Acknowledgements & Reference

上一篇：xview-yolov3

下一篇：BMW-YOLOv3-Inference-API-GPU

用户评价
全部评价

热门资源

  • seetafaceJNI

    项目介绍 基于中科院seetaface2进行封装的JAVA...

  • spark-corenlp

    This package wraps Stanford CoreNLP annotators ...

  • Keras-ResNeXt

    Keras ResNeXt Implementation of ResNeXt models...

  • capsnet-with-caps...

    CapsNet with capsule-wise convolution Project ...

  • inferno-boilerplate

    This is a very basic boilerplate example for pe...