salience_object_detection-master

所属分类:图形图象
开发工具:Python
文件大小:1454KB
下载次数:14
上传日期:2018-09-11 16:09:51
上 传 者Ryo
说明:  用深度学习框架Pytorch的图像语义分割
(Image semantic segmentation using deep learning framework Pytorch)

文件列表:
cal_grb_mean.py (476, 2018-04-13)
csv_generator.py (674, 2018-04-13)
dataset (0, 2018-04-13)
dataset\.DS_Store (6148, 2018-04-13)
dataset\pig (0, 2018-04-13)
dataset\pig\.DS_Store (6148, 2018-04-13)
dataset\pig\IMG_20180202_093718.jpg (59408, 2018-04-13)
dataset\piglabel (0, 2018-04-13)
dataset\piglabel\.DS_Store (6148, 2018-04-13)
dataset\piglabel\IMG_20180202_093718.png (12542, 2018-04-13)
dataset\pigtest (0, 2018-04-13)
dataset\pigtest\.DS_Store (6148, 2018-04-13)
dataset\pigtest\IMG_20180202_114844.jpg (54958, 2018-04-13)
dataset\pigtestlabel (0, 2018-04-13)
dataset\pigtestlabel\.DS_Store (6148, 2018-04-13)
dataset\pigtestlabel\IMG_20180202_114844.png (10926, 2018-04-13)
model.py (10609, 2018-04-13)
pig.csv (39618, 2018-04-13)
pigtest.csv (1728, 2018-04-13)
tensorboard (0, 2018-04-13)
tensorboard\未命名 11.png (705381, 2018-04-13)
tensorboard\未命名 3.png (399568, 2018-04-13)
tensorboard\未命名.png (295984, 2018-04-13)
test.py (2001, 2018-04-13)
train.py (11922, 2018-04-13)
vgg16.py (3568, 2018-04-13)

# Salience Object Detection Salience Object Detection Using python + tensorflow This is tensorflow implementation for cvpr2017 paper "Deeply Supervised Salient Object Detection with Short Connections".
My wechat is:630546915, If u have some problem pls contact me.
If it is useful for u, pls give me a star! THX
Cuz i trained this model on my company's data,so to be honest i dont know this model still reach the performance mentioned in paper or not. ## Project info This code can be used to train, but the data is owned by my company.I'll try my best to provide code and model that can do inference.

My Chinese blog about the implementation of this paper http://blog.csdn.net/gbyy42299/article/details/79427457
## Usage I trained this model on gpu Tesla P100(1200 images, 10h)
u need download vgg16.npy as pre-trained model.
1.Just put ur data under the folder named 'dataset'.
2.run csv_generater.py to get the csv files for ur training.
3.run train.py for training ur own model.
4.run test.py for testing new photo.

## Tensorboard info

# Update ## 2018.02.04 I added model scripy fot u guys for training on ur own dataset. ## 2018.03.28 I fixed some bug, like loss problem etc, now u can use it. ## 2018.04.13 U can find another salience obeject detection in this url: https://github.com/gbyy422990/salience_object-detection-non-local

近期下载者

相关文件


收藏者