文件名称:vagan-code:Tensorflow实现``使用Wasserstein GAN的视觉特征归因''
文件大小:91.78MB
文件格式:ZIP
更新时间:2024-05-24 12:45:10
Python
VA-GAN代码 使用Wasserstein GANs方法的视觉特征归因的公共张量流实现,已在接受了演示。 如果您发现此代码对您的研究有所帮助,请引用以下文章: @InProceedings{baumgartner2018visual, author = {Baumgartner, Christian F. and Koch, Lisa M. and Tezcan, Kerem Can and Ang, Jia Xi and Konukoglu, Ender}, title = {Visual Feature Attribution Using Wasserstein {GAN}s}, booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June},
【文件预览】:
vagan-code-master
----.gitignore(53B)
----classifier()
--------model_classifier.py(20KB)
--------__init__.py(0B)
--------experiments()
--------network_zoo()
----pretrained_weights()
--------adni_vagan_share.tgz(59.58MB)
--------synth_vagan_share.tgz(29.11MB)
----requirements.txt(486B)
----data()
--------adni_data_loader.py(14KB)
--------adni_data.py(4KB)
--------batch_provider.py(2KB)
--------subject_rids.txt(8KB)
--------synthetic_data_loader.py(7KB)
--------synthetic_data.py(4KB)
----vagan_train.py(965B)
----classifier_test_saliencies.py(3KB)
----LICENSE(34KB)
----preprocess_adni_all.py(23KB)
----vagan_test_loop.py(4KB)
----tfwrapper()
--------__init__.py(0B)
--------layers.py(28KB)
--------utils.py(6KB)
--------losses.py(4KB)
----utils.py(3KB)
----README.md(5KB)
----config()
--------system.py(1KB)
--------__init__.py(0B)
----figures()
--------synth_results.png(573KB)
--------method.png(164KB)
--------adni_results.png(1.74MB)
--------three_views.png(615KB)
----vagan()
--------__init__.py(0B)
--------experiments()
--------network_zoo()
--------model_vagan.py(21KB)
----grad_accum_optimizers.py(3KB)
----classifier_train.py(909B)
----SGE_scripts()
--------run_on_host_short.sh(2KB)
--------run_on_host.sh(2KB)
----classifier_test_accuracy.py(2KB)