ChipGAN

晶片GAN

用於中國水墨畫風格遷移的 ChipGAN

培訓和測試

1. 程式碼基於python2.7 + pytorch3.0。
2. 這兩個 .sh 檔案用於訓練和測試模型。
3. 您可以修改「train_horse2_edge_10_dec_150.sh」以用於其他風格化任務。
4. 預訓練模型位於檢查點文件中。
5. 您可以直接執行“bash test_horse2_10_dec_150.sh”來獲取“結果”檔案中的時尚圖像。

CHIPPHI資料集

1. 您可以使用密碼nqhi從https://pan.baidu.com/s/1oXFVv1tZCkUSoH2pSxWFSA下載我們的資料集

引文

 @inproceedings{10.1145/3240508.3240655,
author = {He, Bin and Gao, Feng and Ma, Daiqian and Shi, Boxin and Duan, Ling-Yu},
title = {ChipGAN: A Generative Adversarial Network for Chinese Ink Wash Painting Style Transfer},
year = {2018},
isbn = {9781450356657},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3240508.3240655},
doi = {10.1145/3240508.3240655},
booktitle = {Proceedings of the 26th ACM International Conference on Multimedia},
pages = {1172–1180},
numpages = {9},
keywords = {generative adversarial network, style transfer, painting},
location = {Seoul, Republic of Korea},
series = {MM ’18}
}

接觸器

如果您有任何疑問，請隨時與我聯繫：[email protected]