Passing config['test_start_index'] to calc_grad_z

[expectopatronum]

Hi,
I am not sure if I am misunderstanding the parameter or if it shouldn't be passed to calc_grad_z:

pytorch_influence_functions/pytorch_influence_functions/calc_influence_function.py

Line 111 in 4df5d2e

def calc_grad_z(model, train_loader, save_pth=False, gpu=-1, start=0):

I assumed it should loop over the whole training set.

Thanks and best regards
Verena

[andrewsilva9]

I believe it does loop over the entire training set, the train_loader is a python dataloader that carries all that info with it. We can see here:

pytorch_influence_functions/pytorch_influence_functions/calc_influence_function.py

Line 133 in 4df5d2e

for i in range(start, len(train_loader.dataset)):

that it is iterating over the dataset that gets sent along with the dataloader (which would be the entire training set).

[nimarb]

Hi, @andrewsilva9 is correct in line 133 it loops over the entire training dataset so that one grad_z is calculated per training sample.

With the start argument you can start at a different point in the training dataset. This can be used if you split the calculation across multiple machines. You calculate samples [0-100] on machine 1 and on machine two you pass start=101 to calculate from training sample [101-x]. The end x is missing here in the implementation still...