nus_wide MAP ?

[xy4869]

May I know your specific parameters in NUS_ Wide？I use your library's parameters to run out the result is only 0.8188 using resnet model and 64 bit hash code in NUS_ Wide dataset

[swuxyj]

I get mAP 0.844 when use
optimizer = torch.optim.RMSprop(params_list, lr = 1e-5, weight_decay=10 ** -5)

[yuanli2333]

I get mAP 0.844 when use
optimizer = torch.optim.RMSprop(params_list, lr = 1e-5, weight_decay=10 ** -5)

Nice try!

[Kenny-Li2023]

May I know your specific parameters in NUS_ Wide？I use your library's parameters to run out the result is only 0.8188 using resnet model and 64 bit hash code in NUS_ Wide dataset

Can you share the NUS_WIDE dataset with me

[swuxyj]

May I know your specific parameters in NUS_ Wide？I use your library's parameters to run out the result is only 0.8188 using resnet model and 64 bit hash code in NUS_ Wide dataset

Can you share the NUS_WIDE dataset with me

NUS_WIDE dataset can be downloaded in HashNet or DSDH_PyTorch

[Kenny-Li2023]

May I know your specific parameters in NUS_ Wide？I use your library's parameters to run out the result is only 0.8188 using resnet model and 64 bit hash code in NUS_ Wide dataset

Can you share the NUS_WIDE dataset with me

NUS_WIDE dataset can be downloaded in HashNet or DSDH_PyTorch

Thanks！！The format of the NUS_WIDS dataset is different from the script format in the code. How do I generate my own script
please?

[swuxyj]

May I know your specific parameters in NUS_ Wide？I use your library's parameters to run out the result is only 0.8188 using resnet model and 64 bit hash code in NUS_ Wide dataset

Can you share the NUS_WIDE dataset with me

NUS_WIDE dataset can be downloaded in HashNet or DSDH_PyTorch

Thanks！！The format of the NUS_WIDS dataset is different from the script format in the code. How do I generate my own script
please?

You can refer to this code to divide your own dataset

[Kenny-Li2023]

Why is the accuracy I trained is only 0.7146 on the NUS_WIDE dataset?

[Kenny-Li2023]

I get mAP 0.844 when use
optimizer = torch.optim.RMSprop(params_list, lr = 1e-5, weight_decay=10 ** -5)

你好，请问你具体改了哪些参数？我直接用作者的代码但是精确度只有0.7146，论文用的NUS_WIDE不是原始NUS_WIDE数据集吧？