where you load the train_img.txt about cifar10 dataset??

LiuChaoXD commented 4 years ago

For the ADSH_pytorch, in the ADSH_CIFAR_10.py, I find you random sample the training set from database, the codes is as follows,

for iter in range(max_iter):
        iter_time = time.time()
        '''
        sampling and construct similarity matrix
        '''
        select_index = list(np.random.permutation(range(num_database)))[0: num_samples]
        _sampler = subsetsampler.SubsetSampler(select_index)
        trainloader = DataLoader(dset_database, batch_size=batch_size,
                                 sampler=_sampler,
                                 shuffle=False,
                                 num_workers=4)

However, follow your paper, the training set is randomly sample 500 images for each class. Such that there are 5000 training samples. so in your program there is a list "train_img.txt" with 5000 lines for training.

The problem is I cannot find any codes about loading the train_img.txt ?? can you introduce it clearly?

jiangqy commented 4 years ago

5000 samples are sampled from database_img.txt

https://github.com/jiangqy/ADSH-AAAI2018/blob/2e95574aaafa6ab139a142e5fb5020317384b338/ADSH_pytorch/ADSH_CIFAR_10.py#L196

zhangcheng-007 commented 3 years ago

I would like to ask whether each class of random sampling in the test set has an impact on MAP?And if it is completely random sampling, how will the results change?

jiangqy / ADSH-AAAI2018

where you load the train_img.txt about cifar10 dataset?? #10