| | |
|---|
| | | self.shuffle = shuffle and is_training |
|---|
| | | self.drop_last = drop_last |
|---|
| | | |
|---|
| | | self.total_size = len(self.dataset) |
|---|
| | | # self.total_size = len(self.dataset) |
|---|
| | | # self.num_samples = int(math.ceil(self.total_size / self.num_replicas)) |
|---|
| | | self.epoch = 0 |
|---|
| | | self.sort_size = sort_size * num_replicas |
|---|
| | |
|---|
| | | g = torch.Generator() |
|---|
| | | g.manual_seed(self.epoch) |
|---|
| | | random.seed(self.epoch) |
|---|
| | | indices = torch.randperm(self.total_size, generator=g).tolist() |
|---|
| | | indices = torch.randperm(len(self.dataset), generator=g).tolist() |
|---|
| | | else: |
|---|
| | | indices = list(range(self.total_size)) |
|---|
| | | |
|---|
| | | indices = list(range(len(self.dataset))) |
|---|
| | | |
|---|
| | | # Sort indices by sample length |
|---|
| | | sorted_indices = sorted(indices, key=lambda idx: self.dataset.get_source_len(idx)) |
|---|
| | | |
|---|
