When I tried to reproduce the Diabetes results using pate-gan with the command below, I got an torch size mismatch error. After searching online, I found that it's caused by the loss function. Here's the StackOverflow issue
So I added some fixes before passing the label (target) to criterion in pate-gan train function. Then the training worked.
Traceback (most recent call last): File "evaluate.py", line 144, in <module> lap_scale=opt.lap_scale, class_ratios=class_ratios, lr=1e-4)) File "/content/private-data-generation/models/pate_gan.py", line 93, in train err_d_real = criterion(output, label.double()) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(*input, **kwargs) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/loss.py", line 613, in forward return F.binary_cross_entropy(input, target, weight=self.weight, reduction=self.reduction) File "/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py", line 2755, in binary_cross_entropy "Please ensure they have the same size.".format(target.size(), input.size()) ValueError: Using a target size (torch.Size([64])) that is different to the input size (torch.Size([64, 1])) is deprecated. Please ensure they have the same size.
When I tried to reproduce the Diabetes results using pate-gan with the command below, I got an torch size mismatch error. After searching online, I found that it's caused by the loss function. Here's the StackOverflow issue
So I added some fixes before passing the label (target) to criterion in pate-gan train function. Then the training worked.
!python evaluate.py --target-variable='status' \ --train-data-path=./data/processed_train.csv \ --test-data-path=./data/processed_test.csv --normalize-data pate-gan \ --enable-privacy --target-epsilon=8 --target-delta=1e-5 --save-synthetic --lap-scale=1e-4Traceback (most recent call last): File "evaluate.py", line 144, in <module> lap_scale=opt.lap_scale, class_ratios=class_ratios, lr=1e-4)) File "/content/private-data-generation/models/pate_gan.py", line 93, in train err_d_real = criterion(output, label.double()) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(*input, **kwargs) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/loss.py", line 613, in forward return F.binary_cross_entropy(input, target, weight=self.weight, reduction=self.reduction) File "/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py", line 2755, in binary_cross_entropy "Please ensure they have the same size.".format(target.size(), input.size()) ValueError: Using a target size (torch.Size([64])) that is different to the input size (torch.Size([64, 1])) is deprecated. Please ensure they have the same size.