I've been using this function to load data from stackoverflow data_set. However, one problem occurs that every time I use this function and set cache_dir to the location of the keras/dataset or the location of the cache, it still tries to download the tar from the internet(Even when I have already the 8.5G tar file download in local). Is there a simple way to avoid downloading from the internet and access by local?
I've also tried to write the save and load function, but it seems they cannot be applied to HDF5ClientData type.