DAN

DAN copied to clipboard

Question in demo.py and run_grad_cam.py

8

question 1: python run_grad_cam.py Traceback (most recent call last): File "run_grad_cam.py", line 94, in eigen_smooth=False) File "/home/a123/anaconda3/envs/fer/lib/python3.7/site-packages/pytorch_grad_cam/base_cam.py", line 130, in __call__ target_category, eigen_smooth) File "/home/a123/anaconda3/envs/fer/lib/python3.7/site-packages/pytorch_grad_cam/base_cam.py", line 66, in forward target_category...

CHENSY-SIYU

Added a demo for videos & camera + gradcam.

rlleshi

求问AffectNet数据集的预处理方法

2

请问作者，如何把AffectNet数据集处理成您在csv文件中给出类似datasets/AffectNet/train_set/images/245999这样的路径

jiayujerry

Is this method also applicable for fer2013 data set? Why did the author not verify it on the most common fer2013 data set

1

1chenchen22

GRADCAM++需要替换哪些变量

3

woshishauibi

您好，在执行run_grad_cam.py报错AttributeError: 'tuple' object has no attribute 'cpu'，如何解决？期待您的回复，谢谢！

study-clever

请问一下当运行rafdb.py时，在Affinity Loss中默认的num_classes为8类，可对于RAF_DB数据集而言只有7类，请问一下这8类如何解释呢

4

作者，您好！请问一下当运行rafdb.py时，在Affinity Loss中默认的num_classes为8类，可对于RAF_DB数据集而言只有7类，请问一下这8类如何解释呢，是把最后第8类当作背景类吗？ 非常感谢作者的回答

sr-feng

Hello there. I have a question how can I extract feature vector from dan model ? My aim is to to extract the feature vector from this model to concatenate...

thomaskopalidis

作者您好，论文的工作对我很有帮助，您提供的在ms-celeb上预训练模型的下载地址失效了，请问下能否更新一下呢，非常感谢🙏

yic20