caoyue10 / cvpr17-dvsq Goto Github PK

您好，我运行代码的时候出现了一个错误：OSError: Failed to interpret file 'models/reference_pretrain.npy' as a pickle，请问这个问题该怎么解决呢？

hello,the paper on cvpr2017 gives me lots of inspiration,but i'm wondering where is the run_dvsq.sh file?

I want to run your models on my dataset. But I dont know how to get the word vector. I am sorry to bother you. Thanks for your help

model = DVSQ(config)

File "/home/password/cvpr17-dvsq/net_val.py", line 69, in init
self.load_model(self.model_weights)
File "/home/password/cvpr17-dvsq/net_val.py", line 99, in load_model
img_output = self.img_alexnet_layers(img_model_weights)
File "/home/password/cvpr17-dvsq/net_val.py", line 109, in img_alexnet_layers
net_data = np.load(model_weights).item()
File "/usr/local/lib/python3.5/dist-packages/numpy/lib/npyio.py", line 370, in load
fid = open(file, "rb")
FileNotFoundError: [Errno 2] No such file or directory: './cos_softmargin_multi_label_lr_0.02_cqlambda_0.0001_subspace_4_margin_0.7_partlabel_10_iter_5_output_300_.npy'
^C

Hi Cao Yue,

Great thanks for your great job done on the DVSQ project. I am currently working on my project at school. It has helped me a lot.

I have successfully deployed the whole project. However, when I tried to run it with my own dataset, confusions arise. May I ask where the wordvec file in the data folder comes from? I have read your paper about the transformer to convert the image representations to embedding labels. However, it does not seem relevant to this file. May I ask how I can generate the word vectors and should which dataset be converted to word vectors.

Thank you.

Best,
Zhang Zeng

I want to use this model in some image retrieval tasks, but the nuswide_81 dataset is multilabel dataset, how can i use this in single label dataset image retrieval?