Xialei Liu
Xialei Liu
Thanks for your quick reply. Another question about using import scipy.misc as scm, in mini-imagenet-tools, import imageio is used, I am wondering what's the reason to change it? For me...
Thanks, good to know your new project. And last thing is that the following line works for me using: class_idxs = list(range(0, self.way_num)) https://github.com/yaoyao-liu/tiered-imagenet-tools/blob/master/tiered_imagenet_dataloader.py#L147 with these fixes, it works fine...
It's fine, only several minor points, you could fix it directly if that is correct to you. Thanks.
Yes, of course, I would be very grateful if you can submit a pull request with your paper and more ICML papers.
是的
TID2013: https://pan.baidu.com/s/1VzyC_MN8PCG2ojlz1K7NuQ code: hrmr
LIVE: https://pan.baidu.com/s/1_YWDmhyEFuuBU5vkVqMRsA code: i9i7
Sorry for the late reply. Yes, the forgetting should be also the weighted average.
改变输入大小需要改变train_vgg.prototxt 里data层的图像大小，相应的src.data_layer里也要改，由于网络最后是全连接层，所以全连接层的输入维度也不一样。
其中一张图我记得是人造图，所以没用