Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
liuxinchen3 8746a7269f | 1 year ago | |
---|---|---|
README.md | 1 year ago | |
data | 1 year ago | |
dataset.py | 1 year ago | |
log | 1 year ago | |
models.py | 1 year ago | |
preprocess.py | 1 year ago | |
preprocess_test.py | 1 year ago | |
requirements.txt | 1 year ago | |
rexnetv1.py | 1 year ago | |
run.sh | 1 year ago | |
run_test.sh | 1 year ago | |
test.py | 1 year ago | |
train.py | 1 year ago | |
util.py | 1 year ago | |
weights | 1 year ago |
This work was supported by the National Key R&D Program of China under Grant No. 2020AAA0103804(Sponsor: Hefu Liu). This work belongs to the University of science and technology of China.
pip install -r requirements.txt
git clone https://github.com/NVIDIA/apex.git & cd apex
python3 setup.py install
pip install -v --no-cache-dir ./
Download the Google Landmarks Dataset v2 to ./data
using the scripts at https://github.com/cvdfoundation/google-landmark This is our training data.
Download the train label csv file from here and put it in ./train.csv
Download ReXNet_V1-2.0x pretrained model weights from here and put it in ./rexnetv1_2.0x.pth
python preprocess.py
to get ./train_0.csv
and ./idx2landmark_id.pkl
After training, models will be saved in ./weights/
Tranning logs will be saved in ./logs/
by default.
bash run.sh
Download test data set, put it in ./data/test
, download test.tar.part1, test.tar.part2, then cat test.tar.* | tar -xv
python preprocess_test.py
to generate ./test.csv
label for test, or download from here
Download final checkpoint ./weights/final_model.pth
from here
bash run_test.sh
本算法提出了图像地标识别模型,Findwhere。与普通的分类任务不同,我们使用了度量学习的思想,将分类问题转为输入图片和类别之间的距离度量问题。
Python Shell Text
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》