You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
qizhi_hgd_zyh 058d4f9d2b fefwr 6 months ago
images 3.16 6 months ago
nts_net 3.17.5 6 months ago
.gitignore 3.16 6 months ago
LICENSE 3.16 6 months ago
README.md 3.16 6 months ago
bird_classes.py 3.16 6 months ago
example.py 3.16 6 months ago
hubconf.py 3.16 6 months ago
ntsnet_train.py 3.19.2 6 months ago
requirements.txt 3.16 6 months ago
test.py fef 6 months ago
test_model.py fefwr 6 months ago
test_ntsnet.py fef 6 months ago

README.md

Open on Torch Hub
License: MIT

Open In Colab

NtsNet pre trained on cub200 2011

A pretrained ntsnet

How to use

net = netsnet(pretrained=True, **{'topN': 6, 'device':'cpu', 'num_classes': 200})

Citation

You can read the full paper at this link.

@INPROCEEDINGS{Gallo:2019:IVCNZ, 
  author={Nawaz, Shah and Calefati, Alessandro and Caraffini, Moreno and Landro, Nicola and Gallo, Ignazio},
  booktitle={2019 International Conference on Image and Vision Computing New Zealand (IVCNZ 2019)}, 
  title={Are These Birds Similar: Learning Branched Networks for Fine-grained Representations},
  year={2019}, 
  month={Dec},
}

简介

No Description

Python other

贡献者 (1)