def dataset(self, texts, targets):
for text, target in zip(texts, targets):
t, t_len = self.encode_text(text)
t, t_len = t.unsqueeze(0), t_len.unsqueeze(0)
target_idx = self.vocab.stoi[target]
yield Batch(inputs=(t, ),
labels=(target_idx, ),
additional_args=t_len)
def formatted_data_iter():
dataset = torchvision.datasets.CIFAR10(
root="data/test", train=False, download=True, transform=transforms.ToTensor()
)
dataloader = iter(
torch.utils.data.DataLoader(dataset, batch_size=4, shuffle=False, num_workers=2)
)
while True:
images, labels = next(dataloader)
yield Batch(inputs=images, labels=labels)
input_imgs = torch.cat(list(map(lambda i: full_img_transform(i), imgs)), 0)
visualizer = AttributionVisualizer(
models=[model],
score_func=lambda o: torch.nn.functional.softmax(o, 1),
classes=list(map(lambda k: idx_to_labels[k][1], idx_to_labels.keys())),
features=[
ImageFeature(
"Photo",
baseline_transforms=[baseline_func],
input_transforms=[],
)
],
dataset=[Batch(input_imgs, labels=[282, 849, 69])])
#########################################################################
# Note that running the cell above didn’t take much time at all, unlike
# our attributions above. That’s because Captum Insights lets you
# configure different attribution algorithms in a visual widget, after
# which it will compute and display the attributions. *That* process will
# take a few minutes.
#
# Running the cell below will render the Captum Insights widget. You can
# then choose attributions methods and their arguments, filter model
# responses based on predicted class or prediction correctness, see the
# model’s predictions with associated probabilities, and view heatmaps of
# the attribution compared with the original image.
#
def _formatted_data_iter(self,dl,normalize_func):
dl_iter=iter(dl)
while True:
images,labels=next(dl_iter)
images=normalize_func.decode(images).to(dl.device)
yield Batch(inputs=images, labels=labels)
def formatted_data_iter(dataloader):
dataloader = iter(dataloader)
while True:
images, labels = next(dataloader)
yield Batch(inputs=images, labels=labels)