资源分类
》 资源 》算法》RetinaNet_SE-ResNeXt

RetinaNet_SE-ResNeXt

2020-02-24 | |  31 |   0 |   0

An Implentation of RetinaNet in Pytorch

图片.png

optional backbone:

usage:

setup.sh: compile cython code
config.json: config file
train.py: main train script
dataGen/data_loader.py: Subclass torch.utils.data.Dataset or modify class RsnaDataset for your owen dataset.
prepare_data.ipynb: data processing script for RSNA Pneumonia Detection Challenge
demo.ipynb: sample code showing how to predict with model.predict method

Application

train this model with dataset of RSNA Pneumonia Detection Challenge

图片.png

credits:

  1. Cadene pretrained-models.pytorch

  2. fizyr/keras-retinanet

  3. Squeeze-and-Excitation Networks

  4. Focal Loss for Dense Object Detection


上一篇：ResNeXt-for-HRRSI-scene-classification

下一篇：SENet_ResNeXt_Remote_Sensing_Scene_Classification

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 ...

  • shih-styletransfer

    shih-styletransfer Code from Style Transfer ...