| import torch |
|
|
| from diffusers import KDPM2AncestralDiscreteScheduler |
| from diffusers.utils import torch_device |
|
|
| from .test_schedulers import SchedulerCommonTest |
|
|
|
|
| class KDPM2AncestralDiscreteSchedulerTest(SchedulerCommonTest): |
| scheduler_classes = (KDPM2AncestralDiscreteScheduler,) |
| num_inference_steps = 10 |
|
|
| def get_scheduler_config(self, **kwargs): |
| config = { |
| "num_train_timesteps": 1100, |
| "beta_start": 0.0001, |
| "beta_end": 0.02, |
| "beta_schedule": "linear", |
| } |
|
|
| config.update(**kwargs) |
| return config |
|
|
| def test_timesteps(self): |
| for timesteps in [10, 50, 100, 1000]: |
| self.check_over_configs(num_train_timesteps=timesteps) |
|
|
| def test_betas(self): |
| for beta_start, beta_end in zip([0.00001, 0.0001, 0.001], [0.0002, 0.002, 0.02]): |
| self.check_over_configs(beta_start=beta_start, beta_end=beta_end) |
|
|
| def test_schedules(self): |
| for schedule in ["linear", "scaled_linear"]: |
| self.check_over_configs(beta_schedule=schedule) |
|
|
| def test_full_loop_no_noise(self): |
| if torch_device == "mps": |
| return |
| scheduler_class = self.scheduler_classes[0] |
| scheduler_config = self.get_scheduler_config() |
| scheduler = scheduler_class(**scheduler_config) |
|
|
| scheduler.set_timesteps(self.num_inference_steps) |
|
|
| generator = torch.manual_seed(0) |
|
|
| model = self.dummy_model() |
| sample = self.dummy_sample_deter * scheduler.init_noise_sigma |
| sample = sample.to(torch_device) |
|
|
| for i, t in enumerate(scheduler.timesteps): |
| sample = scheduler.scale_model_input(sample, t) |
|
|
| model_output = model(sample, t) |
|
|
| output = scheduler.step(model_output, t, sample, generator=generator) |
| sample = output.prev_sample |
|
|
| result_sum = torch.sum(torch.abs(sample)) |
| result_mean = torch.mean(torch.abs(sample)) |
|
|
| assert abs(result_sum.item() - 13849.3877) < 1e-2 |
| assert abs(result_mean.item() - 18.0331) < 5e-3 |
|
|
| def test_prediction_type(self): |
| for prediction_type in ["epsilon", "v_prediction"]: |
| self.check_over_configs(prediction_type=prediction_type) |
|
|
| def test_full_loop_with_v_prediction(self): |
| if torch_device == "mps": |
| return |
| scheduler_class = self.scheduler_classes[0] |
| scheduler_config = self.get_scheduler_config(prediction_type="v_prediction") |
| scheduler = scheduler_class(**scheduler_config) |
|
|
| scheduler.set_timesteps(self.num_inference_steps) |
|
|
| model = self.dummy_model() |
| sample = self.dummy_sample_deter * scheduler.init_noise_sigma |
| sample = sample.to(torch_device) |
|
|
| generator = torch.manual_seed(0) |
|
|
| for i, t in enumerate(scheduler.timesteps): |
| sample = scheduler.scale_model_input(sample, t) |
|
|
| model_output = model(sample, t) |
|
|
| output = scheduler.step(model_output, t, sample, generator=generator) |
| sample = output.prev_sample |
|
|
| result_sum = torch.sum(torch.abs(sample)) |
| result_mean = torch.mean(torch.abs(sample)) |
|
|
| assert abs(result_sum.item() - 328.9970) < 1e-2 |
| assert abs(result_mean.item() - 0.4284) < 1e-3 |
|
|
| def test_full_loop_device(self): |
| if torch_device == "mps": |
| return |
| scheduler_class = self.scheduler_classes[0] |
| scheduler_config = self.get_scheduler_config() |
| scheduler = scheduler_class(**scheduler_config) |
|
|
| scheduler.set_timesteps(self.num_inference_steps, device=torch_device) |
| generator = torch.manual_seed(0) |
|
|
| model = self.dummy_model() |
| sample = self.dummy_sample_deter.to(torch_device) * scheduler.init_noise_sigma |
|
|
| for t in scheduler.timesteps: |
| sample = scheduler.scale_model_input(sample, t) |
|
|
| model_output = model(sample, t) |
|
|
| output = scheduler.step(model_output, t, sample, generator=generator) |
| sample = output.prev_sample |
|
|
| result_sum = torch.sum(torch.abs(sample)) |
| result_mean = torch.mean(torch.abs(sample)) |
|
|
| assert abs(result_sum.item() - 13849.3818) < 1e-1 |
| assert abs(result_mean.item() - 18.0331) < 1e-3 |
|
|
