Python torch.Generator() Examples

The following are 30 code examples of torch.Generator(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module torch , or try the search function .
Example #1
Source File: distributed.py    From mobilenetv3-segmentation with Apache License 2.0 6 votes vote down vote up 
def __iter__(self):
        if self.shuffle:
            # deterministically shuffle based on epoch
            g = torch.Generator()
            g.manual_seed(self.epoch)
            indices = torch.randperm(len(self.dataset), generator=g).tolist()
        else:
            indices = torch.arange(len(self.dataset)).tolist()

        # add extra samples to make it evenly divisible
        indices += indices[: (self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        offset = self.num_samples * self.rank
        indices = indices[offset: offset + self.num_samples]
        assert len(indices) == self.num_samples

        return iter(indices)
Example #2
Source File: sampler.py    From Cascade-RPN with Apache License 2.0 6 votes vote down vote up 
def __iter__(self):
        # deterministically shuffle based on epoch
        if self.shuffle:
            g = torch.Generator()
            g.manual_seed(self.epoch)
            indices = torch.randperm(len(self.dataset), generator=g).tolist()
        else:
            indices = torch.arange(len(self.dataset)).tolist()

        # add extra samples to make it evenly divisible
        indices += indices[:(self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        indices = indices[self.rank:self.total_size:self.num_replicas]
        assert len(indices) == self.num_samples

        return iter(indices)
Example #3
Source File: distributed.py    From R2CNN.pytorch with MIT License 6 votes vote down vote up 
def __iter__(self):
        if self.shuffle:
            # deterministically shuffle based on epoch
            g = torch.Generator()
            g.manual_seed(self.epoch)
            indices = torch.randperm(len(self.dataset), generator=g).tolist()
        else:
            indices = torch.arange(len(self.dataset)).tolist()

        # add extra samples to make it evenly divisible
        indices += indices[: (self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        offset = self.num_samples * self.rank
        indices = indices[offset : offset + self.num_samples]
        assert len(indices) == self.num_samples

        return iter(indices)
Example #4
Source File: distributed.py    From DetNAS with MIT License 6 votes vote down vote up 
def __iter__(self):
        if self.shuffle:
            # deterministically shuffle based on epoch
            g = torch.Generator()
            g.manual_seed(self.epoch)
            indices = torch.randperm(len(self.dataset), generator=g).tolist()
        else:
            indices = torch.arange(len(self.dataset)).tolist()

        # add extra samples to make it evenly divisible
        indices += indices[: (self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        offset = self.num_samples * self.rank
        indices = indices[offset : offset + self.num_samples]
        assert len(indices) == self.num_samples

        return iter(indices)
Example #5
Source File: distributed.py    From EMANet with GNU General Public License v3.0 6 votes vote down vote up 
def __iter__(self):
        # deterministically shuffle based on epoch
        g = torch.Generator()
        g.manual_seed(self.epoch)
        indices = list(torch.randperm(len(self.dataset), generator=g))

        # add extra samples to make it evenly divisible
        indices += indices[:(self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        offset = self.num_samples * self.rank
        indices = indices[offset:offset + self.num_samples]
        assert len(indices) == self.num_samples

        return iter(indices)
Example #6
Source File: sampler.py    From LEDNet with MIT License 6 votes vote down vote up 
def __iter__(self):
        if self.shuffle:
            # deterministically shuffle based on epoch
            g = torch.Generator()
            g.manual_seed(self.epoch)
            indices = torch.randperm(len(self.dataset), generator=g).tolist()
        else:
            indices = torch.arange(len(self.dataset)).tolist()

        # add extra samples to make it evenly divisible
        indices += indices[: (self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        offset = self.num_samples * self.rank
        indices = indices[offset: offset + self.num_samples]
        assert len(indices) == self.num_samples

        return iter(indices)
Example #7
Source File: sampler.py    From FoveaBox with Apache License 2.0 6 votes vote down vote up 
def __iter__(self):
        # deterministically shuffle based on epoch
        if self.shuffle:
            g = torch.Generator()
            g.manual_seed(self.epoch)
            indices = torch.randperm(len(self.dataset), generator=g).tolist()
        else:
            indices = torch.arange(len(self.dataset)).tolist()

        # add extra samples to make it evenly divisible
        indices += indices[:(self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        indices = indices[self.rank:self.total_size:self.num_replicas]
        assert len(indices) == self.num_samples

        return iter(indices)
Example #8
Source File: distributed.py    From retinamask with MIT License 6 votes vote down vote up 
def __iter__(self):
        if self.shuffle:
            # deterministically shuffle based on epoch
            g = torch.Generator()
            g.manual_seed(self.epoch)
            indices = torch.randperm(len(self.dataset), generator=g).tolist()
        else:
            indices = torch.arange(len(self.dataset)).tolist()

        # add extra samples to make it evenly divisible
        indices += indices[: (self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        offset = self.num_samples * self.rank
        indices = indices[offset : offset + self.num_samples]
        assert len(indices) == self.num_samples

        return iter(indices)
Example #9
Source File: sampler.py    From mmdetection-annotated with Apache License 2.0 6 votes vote down vote up 
def __iter__(self):
        # deterministically shuffle based on epoch
        if self.shuffle:
            g = torch.Generator()
            g.manual_seed(self.epoch)
            indices = torch.randperm(len(self.dataset), generator=g).tolist()
        else:
            indices = torch.arange(len(self.dataset)).tolist()

        # add extra samples to make it evenly divisible
        indices += indices[:(self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        indices = indices[self.rank:self.total_size:self.num_replicas]
        assert len(indices) == self.num_samples

        return iter(indices)
Example #10
Source File: distributed.py    From remote_sensing_object_detection_2019 with MIT License 6 votes vote down vote up 
def __iter__(self):
        if self.shuffle:
            # deterministically shuffle based on epoch
            g = torch.Generator()
            g.manual_seed(self.epoch)
            indices = torch.randperm(len(self.dataset), generator=g).tolist()
        else:
            indices = torch.arange(len(self.dataset)).tolist()

        # add extra samples to make it evenly divisible
        indices += indices[: (self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        offset = self.num_samples * self.rank
        indices = indices[offset : offset + self.num_samples]
        assert len(indices) == self.num_samples

        return iter(indices)
Example #11
Source File: sampler.py    From mmfashion with Apache License 2.0 6 votes vote down vote up 
def __iter__(self):
        # deterministically shuffle based on epoch
        if self.shuffle:
            g = torch.Generator()
            g.manual_seed(self.epoch)
            indices = torch.randperm(len(self.dataset), generator=g).tolist()
        else:
            indices = torch.arange(len(self.dataset)).tolist()

        # add extra samples to make it evenly divisible
        indices += indices[:(self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        indices = indices[self.rank:self.total_size:self.num_replicas]
        assert len(indices) == self.num_samples

        return iter(indices)
Example #12
Source File: sampler.py    From Libra_R-CNN with Apache License 2.0 6 votes vote down vote up 
def __iter__(self):
        # deterministically shuffle based on epoch
        if self.shuffle:
            g = torch.Generator()
            g.manual_seed(self.epoch)
            indices = torch.randperm(len(self.dataset), generator=g).tolist()
        else:
            indices = torch.arange(len(self.dataset)).tolist()

        # add extra samples to make it evenly divisible
        indices += indices[:(self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        indices = indices[self.rank:self.total_size:self.num_replicas]
        assert len(indices) == self.num_samples

        return iter(indices)
Example #13
Source File: distributed.py    From FreeAnchor with MIT License 6 votes vote down vote up 
def __iter__(self):
        if self.shuffle:
            # deterministically shuffle based on epoch
            g = torch.Generator()
            g.manual_seed(self.epoch)
            indices = torch.randperm(len(self.dataset), generator=g).tolist()
        else:
            indices = torch.arange(len(self.dataset)).tolist()

        # add extra samples to make it evenly divisible
        indices += indices[: (self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        offset = self.num_samples * self.rank
        indices = indices[offset : offset + self.num_samples]
        assert len(indices) == self.num_samples

        return iter(indices)
Example #14
Source File: sampler.py    From training_results_v0.5 with Apache License 2.0 6 votes vote down vote up 
def __iter__(self):
        # deterministically shuffle based on epoch
        g = torch.Generator()
        g.manual_seed(self.epoch)
        indices = torch.randperm(len(self.dataset), generator=g).tolist()

        # add extra samples to make it evenly divisible
        if self.pad:
            indices += indices[:(self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        indices = indices[self.rank:self.total_size:self.num_replicas]
        assert len(indices) == self.num_samples

        return iter(indices)
Example #15
Source File: sampler.py    From mmdetection_with_SENet154 with Apache License 2.0 6 votes vote down vote up 
def __iter__(self):
        # deterministically shuffle based on epoch
        if self.shuffle:
            g = torch.Generator()
            g.manual_seed(self.epoch)
            indices = torch.randperm(len(self.dataset), generator=g).tolist()
        else:
            indices = torch.arange(len(self.dataset)).tolist()

        # add extra samples to make it evenly divisible
        indices += indices[:(self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        indices = indices[self.rank:self.total_size:self.num_replicas]
        assert len(indices) == self.num_samples

        return iter(indices)
Example #16
Source File: distributed_sampler.py    From mmdetection with Apache License 2.0 6 votes vote down vote up 
def __iter__(self):
        # deterministically shuffle based on epoch
        if self.shuffle:
            g = torch.Generator()
            g.manual_seed(self.epoch)
            indices = torch.randperm(len(self.dataset), generator=g).tolist()
        else:
            indices = torch.arange(len(self.dataset)).tolist()

        # add extra samples to make it evenly divisible
        indices += indices[:(self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        indices = indices[self.rank:self.total_size:self.num_replicas]
        assert len(indices) == self.num_samples

        return iter(indices)
Example #17
Source File: sampler.py    From PolarMask with Apache License 2.0 6 votes vote down vote up 
def __iter__(self):
        # deterministically shuffle based on epoch
        if self.shuffle:
            g = torch.Generator()
            g.manual_seed(self.epoch)
            indices = torch.randperm(len(self.dataset), generator=g).tolist()
        else:
            indices = torch.arange(len(self.dataset)).tolist()

        # add extra samples to make it evenly divisible
        indices += indices[:(self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        indices = indices[self.rank:self.total_size:self.num_replicas]
        assert len(indices) == self.num_samples

        return iter(indices)
Example #18
Source File: data_utils.py    From nni with MIT License 6 votes vote down vote up 
def __iter__(self):
        # deterministically shuffle based on epoch
        g = torch.Generator()
        g.manual_seed(self.epoch)
        if self.shuffle:
            # indices = torch.randperm(len(self.dataset), generator=g).tolist()
            indices = list(self.indices[i] for i in torch.randperm(len(self.indices)))
        else:
            # indices = list(range(len(self.dataset)))
            indices = self.indices

        # add extra samples to make it evenly divisible
        indices += indices[:(self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        indices = indices[self.rank:self.total_size:self.num_replicas]
        assert len(indices) == self.num_samples

        return iter(indices)
Example #19
Source File: distributed.py    From EmbedMask with MIT License 6 votes vote down vote up 
def __iter__(self):
        if self.shuffle:
            # deterministically shuffle based on epoch
            g = torch.Generator()
            g.manual_seed(self.epoch)
            indices = torch.randperm(len(self.dataset), generator=g).tolist()
        else:
            indices = torch.arange(len(self.dataset)).tolist()

        # add extra samples to make it evenly divisible
        indices += indices[: (self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        offset = self.num_samples * self.rank
        indices = indices[offset : offset + self.num_samples]
        assert len(indices) == self.num_samples

        return iter(indices)
Example #20
Source File: distributed.py    From maskrcnn-benchmark with MIT License 6 votes vote down vote up 
def __iter__(self):
        if self.shuffle:
            # deterministically shuffle based on epoch
            g = torch.Generator()
            g.manual_seed(self.epoch)
            indices = torch.randperm(len(self.dataset), generator=g).tolist()
        else:
            indices = torch.arange(len(self.dataset)).tolist()

        # add extra samples to make it evenly divisible
        indices += indices[: (self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        offset = self.num_samples * self.rank
        indices = indices[offset : offset + self.num_samples]
        assert len(indices) == self.num_samples

        return iter(indices)
Example #21
Source File: distributed.py    From ocr-pytorch with MIT License 6 votes vote down vote up 
def __iter__(self):
        if self.shuffle:
            # deterministically shuffle based on epoch
            g = torch.Generator()
            g.manual_seed(self.epoch)
            indices = torch.randperm(len(self.dataset), generator=g).tolist()
        else:
            indices = torch.arange(len(self.dataset)).tolist()

        # add extra samples to make it evenly divisible
        indices += indices[: (self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        offset = self.num_samples * self.rank
        indices = indices[offset : offset + self.num_samples]
        assert len(indices) == self.num_samples

        return iter(indices)
Example #22
Source File: sampler.py    From kaggle-kuzushiji-recognition with MIT License 6 votes vote down vote up 
def __iter__(self):
        # deterministically shuffle based on epoch
        if self.shuffle:
            g = torch.Generator()
            g.manual_seed(self.epoch)
            indices = torch.randperm(len(self.dataset), generator=g).tolist()
        else:
            indices = torch.arange(len(self.dataset)).tolist()

        # add extra samples to make it evenly divisible
        indices += indices[:(self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        indices = indices[self.rank:self.total_size:self.num_replicas]
        assert len(indices) == self.num_samples

        return iter(indices)
Example #23
Source File: sampler.py    From IoU-Uniform-R-CNN with Apache License 2.0 6 votes vote down vote up 
def __iter__(self):
        # deterministically shuffle based on epoch
        if self.shuffle:
            g = torch.Generator()
            g.manual_seed(self.epoch)
            indices = torch.randperm(len(self.dataset), generator=g).tolist()
        else:
            indices = torch.arange(len(self.dataset)).tolist()

        # add extra samples to make it evenly divisible
        indices += indices[:(self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        indices = indices[self.rank:self.total_size:self.num_replicas]
        assert len(indices) == self.num_samples

        return iter(indices)
Example #24
Source File: sampler.py    From Grid-R-CNN with Apache License 2.0 6 votes vote down vote up 
def __iter__(self):
        # deterministically shuffle based on epoch
        if self.shuffle:
            g = torch.Generator()
            g.manual_seed(self.epoch)
            indices = torch.randperm(len(self.dataset), generator=g).tolist()
        else:
            indices = torch.arange(len(self.dataset)).tolist()

        # add extra samples to make it evenly divisible
        indices += indices[:(self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        indices = indices[self.rank:self.total_size:self.num_replicas]
        assert len(indices) == self.num_samples

        return iter(indices)
Example #25
Source File: gaussian_mixture.py    From FrEIA with MIT License 6 votes vote down vote up 
def pick_mixture_component(w, seed=None):
        '''Randomly choose mixture component indices with probability given by
        the component weights w. Works on batches of component weights.

        w:      Weights of the mixture components, must be positive and sum to one
        seed:   Optional RNG seed for consistent decisions'''

        w_thresholds = torch.cumsum(w, dim=1)
        # Prepare local random number generator
        rng = torch.Generator(device=w.device)
        if isinstance(seed, int):
            rng = rng.manual_seed(seed)
        else:
            rng.seed()
        # Draw one uniform random number per batch row and compare against thresholds
        u = torch.rand(w.shape[0], 1, device=w.device, generator=rng)
        indices = torch.sum(u > w_thresholds, dim=1).int()
        # Return mixture component indices
        return indices
Example #26
Source File: sampler.py    From RDSNet with Apache License 2.0 6 votes vote down vote up 
def __iter__(self):
        # deterministically shuffle based on epoch
        if self.shuffle:
            g = torch.Generator()
            g.manual_seed(self.epoch)
            indices = torch.randperm(len(self.dataset), generator=g).tolist()
        else:
            indices = torch.arange(len(self.dataset)).tolist()

        # add extra samples to make it evenly divisible
        indices += indices[:(self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        indices = indices[self.rank:self.total_size:self.num_replicas]
        assert len(indices) == self.num_samples

        return iter(indices)
Example #27
Source File: scheduler.py    From pytorch-image-models with Apache License 2.0 6 votes vote down vote up 
def _add_noise(self, lrs, t):
        if self.noise_range_t is not None:
            if isinstance(self.noise_range_t, (list, tuple)):
                apply_noise = self.noise_range_t[0] <= t < self.noise_range_t[1]
            else:
                apply_noise = t >= self.noise_range_t
            if apply_noise:
                g = torch.Generator()
                g.manual_seed(self.noise_seed + t)
                if self.noise_type == 'normal':
                    while True:
                        # resample if noise out of percent limit, brute force but shouldn't spin much
                        noise = torch.randn(1, generator=g).item()
                        if abs(noise) < self.noise_pct:
                            break
                else:
                    noise = 2 * (torch.rand(1, generator=g).item() - 0.5) * self.noise_pct
                lrs = [v + v * noise for v in lrs]
        return lrs
Example #28
Source File: plateau_lr.py    From pytorch-image-models with Apache License 2.0 6 votes vote down vote up 
def _apply_noise(self, epoch):
        g = torch.Generator()
        g.manual_seed(self.noise_seed + epoch)
        if self.noise_type == 'normal':
            while True:
                # resample if noise out of percent limit, brute force but shouldn't spin much
                noise = torch.randn(1, generator=g).item()
                if abs(noise) < self.noise_pct:
                    break
        else:
            noise = 2 * (torch.rand(1, generator=g).item() - 0.5) * self.noise_pct

        # apply the noise on top of previous LR, cache the old value so we can restore for normal
        # stepping of base scheduler
        restore_lr = []
        for i, param_group in enumerate(self.optimizer.param_groups):
            old_lr = float(param_group['lr'])
            restore_lr.append(old_lr)
            new_lr = old_lr + old_lr * noise
            param_group['lr'] = new_lr
        self.restore_lr = restore_lr
Example #29
Source File: distributed.py    From HRNet-MaskRCNN-Benchmark with MIT License 6 votes vote down vote up 
def __iter__(self):
        if self.shuffle:
            # deterministically shuffle based on epoch
            g = torch.Generator()
            g.manual_seed(self.epoch)
            indices = torch.randperm(len(self.dataset), generator=g).tolist()
        else:
            indices = torch.arange(len(self.dataset)).tolist()

        # add extra samples to make it evenly divisible
        indices += indices[: (self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        offset = self.num_samples * self.rank
        indices = indices[offset : offset + self.num_samples]
        assert len(indices) == self.num_samples

        return iter(indices)
Example #30
Source File: distributed.py    From sampling-free with MIT License 6 votes vote down vote up 
def __iter__(self):
        if self.shuffle:
            # deterministically shuffle based on epoch
            g = torch.Generator()
            g.manual_seed(self.epoch)
            indices = torch.randperm(len(self.dataset), generator=g).tolist()
        else:
            indices = torch.arange(len(self.dataset)).tolist()

        # add extra samples to make it evenly divisible
        indices += indices[: (self.total_size - len(indices))]
        assert len(indices) == self.total_size

        # subsample
        offset = self.num_samples * self.rank
        indices = indices[offset : offset + self.num_samples]
        assert len(indices) == self.num_samples

        return iter(indices)