Why is num_nodes not updated in FixedPoints transform?

[ptoews]

It changes the count of points in the data instance and even uses the num_nodes attribute for selection, but doesn't change its value after updating all items of the data instance.

pytorch_geometric/torch_geometric/transforms/fixed_points.py

Lines 34 to 55 in 36a80d7

	def __call__(self, data):
	num_nodes = data.num_nodes
	if self.replace:
	choice = np.random.choice(num_nodes, self.num, replace=True)
	choice = torch.from_numpy(choice).to(torch.long)
	elif not self.allow_duplicates:
	choice = torch.randperm(num_nodes)[:self.num]
	else:
	choice = torch.cat([
	torch.randperm(num_nodes)
	for _ in range(math.ceil(self.num / num_nodes))
	], dim=0)[:self.num]
	for key, item in data:
	if bool(re.search('edge', key)):
	continue
	if (torch.is_tensor(item) and item.size(0) == num_nodes
	and item.size(0) != 1):
	data[key] = item[choice]
	return data

[rusty1s]

Thanks for reporting. I fixed it in #4394.