Shu Kong

Hi, Ely, Thanks for the careful check. According to what you said, I wrote matlab script as below to check the consistency. I concatenate the rows for DoF attribute from...

Hi, Ely, Do you mean that some of the images do not appear in the "datasetImages" folder but they are listed in the TestNew txt file? At my end, I...

Hi, Thanks for your interest! As you may also found in other papers, the score distribution is mostly like Gaussian (long tail) -- most images are around the middle point...

Hi, Yes. When an image is scored 0.00, it means this image is not used for either training or testing; because it might be painting, drawing or a photo containing...

I believe these images were not used for any training. This can be easily done by finding those through the names and excluding them. On Mon, Dec 11, 2017 at...

In our AADB dataset, there are many 0's for attribute annotation, meaning these attributes are not conveyed in the image. So when training a classifier to recognize each attribute, we...

Hi, Eric, Thanks for your interest! This is not a bug, but a reported error when using the mean array. This is caused by different input size of the mean...

Hi Alex, can you try the link below? https://drive.google.com/drive/folders/0BxeylfSgpk1MOVduWGxyVlJFUHM?resourcekey=0-qecf-sZVexPbF6XLU4Gq_g&usp=sharing On Sun, Nov 14, 2021 at 7:38 AM Alex Mavrichev ***@***.***> wrote: > Hey! I want to test my model on...

Hi, Thanks for your interest. I believe that is because of the nature of Alexnet ( https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf ) In Alexnet, after conv1 (including pooling and normalization layers), all the feature...

Hi, If you are using Caffe, you don't need to to anything other than providing the prototxt file to define the architecture and the pre-trained model (over ImageNet). In the...