iamhankai / attribute-aware-attention

[ACM MM 2018] Attribute-Aware Attention Model for Fine-grained Representation Learning

https://arxiv.org/abs/1901.00392

156 stars 30 forks source link

How you are deciding this value 11788? and what does it mean? #3

Closed chandanmishra-03 closed 5 years ago

chandanmishra-03 commented 5 years ago

transform binary attribute to clustered attribute

nb_attr = len(start_idxs)-1 A_all = np.zeros((11788,nb_attr)) image_attribute_file = '../CUB_200_2011/attributes/image_attribute_labels.txt'

iamhankai commented 5 years ago

transform binary attribute to clustered attribute

nb_attr = len(start_idxs)-1 A_all = np.zeros((11788,nb_attr)) image_attribute_file = '../CUB_200_2011/attributes/image_attribute_labels.txt'

11788 is the number of training samples.