Book a Demo!
CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutPoliciesSign UpSign In
shivamshrirao
GitHub Repository: shivamshrirao/diffusers
 Path: blob/main/tests/schedulers/test_scheduler_euler_ancestral.py
1448 views
1
import torch

2


3
from diffusers import EulerAncestralDiscreteScheduler

4
from diffusers.utils import torch_device

5


6
from .test_schedulers import SchedulerCommonTest

7


8


9
class EulerAncestralDiscreteSchedulerTest(SchedulerCommonTest):

10
    scheduler_classes = (EulerAncestralDiscreteScheduler,)

11
    num_inference_steps = 10

12


13
    def get_scheduler_config(self, **kwargs):

14
        config = {

15
            "num_train_timesteps": 1100,

16
            "beta_start": 0.0001,

17
            "beta_end": 0.02,

18
            "beta_schedule": "linear",

19
        }

20


21
        config.update(**kwargs)

22
        return config

23


24
    def test_timesteps(self):

25
        for timesteps in [10, 50, 100, 1000]:

26
            self.check_over_configs(num_train_timesteps=timesteps)

27


28
    def test_betas(self):

29
        for beta_start, beta_end in zip([0.00001, 0.0001, 0.001], [0.0002, 0.002, 0.02]):

30
            self.check_over_configs(beta_start=beta_start, beta_end=beta_end)

31


32
    def test_schedules(self):

33
        for schedule in ["linear", "scaled_linear"]:

34
            self.check_over_configs(beta_schedule=schedule)

35


36
    def test_prediction_type(self):

37
        for prediction_type in ["epsilon", "v_prediction"]:

38
            self.check_over_configs(prediction_type=prediction_type)

39


40
    def test_full_loop_no_noise(self):

41
        scheduler_class = self.scheduler_classes[0]

42
        scheduler_config = self.get_scheduler_config()

43
        scheduler = scheduler_class(**scheduler_config)

44


45
        scheduler.set_timesteps(self.num_inference_steps)

46


47
        generator = torch.manual_seed(0)

48


49
        model = self.dummy_model()

50
        sample = self.dummy_sample_deter * scheduler.init_noise_sigma

51
        sample = sample.to(torch_device)

52


53
        for i, t in enumerate(scheduler.timesteps):

54
            sample = scheduler.scale_model_input(sample, t)

55


56
            model_output = model(sample, t)

57


58
            output = scheduler.step(model_output, t, sample, generator=generator)

59
            sample = output.prev_sample

60


61
        result_sum = torch.sum(torch.abs(sample))

62
        result_mean = torch.mean(torch.abs(sample))

63


64
        assert abs(result_sum.item() - 152.3192) < 1e-2

65
        assert abs(result_mean.item() - 0.1983) < 1e-3

66


67
    def test_full_loop_with_v_prediction(self):

68
        scheduler_class = self.scheduler_classes[0]

69
        scheduler_config = self.get_scheduler_config(prediction_type="v_prediction")

70
        scheduler = scheduler_class(**scheduler_config)

71


72
        scheduler.set_timesteps(self.num_inference_steps)

73


74
        generator = torch.manual_seed(0)

75


76
        model = self.dummy_model()

77
        sample = self.dummy_sample_deter * scheduler.init_noise_sigma

78
        sample = sample.to(torch_device)

79


80
        for i, t in enumerate(scheduler.timesteps):

81
            sample = scheduler.scale_model_input(sample, t)

82


83
            model_output = model(sample, t)

84


85
            output = scheduler.step(model_output, t, sample, generator=generator)

86
            sample = output.prev_sample

87


88
        result_sum = torch.sum(torch.abs(sample))

89
        result_mean = torch.mean(torch.abs(sample))

90


91
        assert abs(result_sum.item() - 108.4439) < 1e-2

92
        assert abs(result_mean.item() - 0.1412) < 1e-3

93


94
    def test_full_loop_device(self):

95
        scheduler_class = self.scheduler_classes[0]

96
        scheduler_config = self.get_scheduler_config()

97
        scheduler = scheduler_class(**scheduler_config)

98


99
        scheduler.set_timesteps(self.num_inference_steps, device=torch_device)

100
        generator = torch.manual_seed(0)

101


102
        model = self.dummy_model()

103
        sample = self.dummy_sample_deter * scheduler.init_noise_sigma

104
        sample = sample.to(torch_device)

105


106
        for t in scheduler.timesteps:

107
            sample = scheduler.scale_model_input(sample, t)

108


109
            model_output = model(sample, t)

110


111
            output = scheduler.step(model_output, t, sample, generator=generator)

112
            sample = output.prev_sample

113


114
        result_sum = torch.sum(torch.abs(sample))

115
        result_mean = torch.mean(torch.abs(sample))

116


117
        assert abs(result_sum.item() - 152.3192) < 1e-2

118
        assert abs(result_mean.item() - 0.1983) < 1e-3

119


120