diffusion-model-framework 0.1.2rc3__tar.gz → 1.0.0rc1__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {diffusion_model_framework-0.1.2rc3 → diffusion_model_framework-1.0.0rc1}/PKG-INFO +11 -8
- diffusion_model_framework-1.0.0rc1/diffusion_models/__init__.py +1 -0
- {diffusion_model_framework-0.1.2rc3 → diffusion_model_framework-1.0.0rc1}/diffusion_models/gaussian_diffusion/base_diffuser.py +4 -3
- {diffusion_model_framework-0.1.2rc3 → diffusion_model_framework-1.0.0rc1}/diffusion_models/gaussian_diffusion/beta_schedulers.py +4 -3
- diffusion_model_framework-1.0.0rc1/diffusion_models/gaussian_diffusion/ddimm_diffuser.py +187 -0
- {diffusion_model_framework-0.1.2rc3 → diffusion_model_framework-1.0.0rc1}/diffusion_models/gaussian_diffusion/gaussian_diffuser.py +21 -11
- {diffusion_model_framework-0.1.2rc3 → diffusion_model_framework-1.0.0rc1}/diffusion_models/models/SimpleUnet.py +2 -1
- {diffusion_model_framework-0.1.2rc3 → diffusion_model_framework-1.0.0rc1}/diffusion_models/models/base_diffusion_model.py +10 -6
- {diffusion_model_framework-0.1.2rc3 → diffusion_model_framework-1.0.0rc1}/diffusion_models/utils/schemas.py +11 -2
- {diffusion_model_framework-0.1.2rc3 → diffusion_model_framework-1.0.0rc1}/pyproject.toml +18 -7
- diffusion_model_framework-0.1.2rc3/diffusion_models/__init__.py +0 -1
- {diffusion_model_framework-0.1.2rc3 → diffusion_model_framework-1.0.0rc1}/README.md +0 -0
- {diffusion_model_framework-0.1.2rc3 → diffusion_model_framework-1.0.0rc1}/diffusion_models/diffusion_inference.py +0 -0
- {diffusion_model_framework-0.1.2rc3 → diffusion_model_framework-1.0.0rc1}/diffusion_models/diffusion_trainer.py +0 -0
- {diffusion_model_framework-0.1.2rc3 → diffusion_model_framework-1.0.0rc1}/diffusion_models/gaussian_diffusion/__init__.py +0 -0
- {diffusion_model_framework-0.1.2rc3 → diffusion_model_framework-1.0.0rc1}/diffusion_models/models/__init__.py +0 -0
- {diffusion_model_framework-0.1.2rc3 → diffusion_model_framework-1.0.0rc1}/diffusion_models/utils/__init__.py +0 -0
- {diffusion_model_framework-0.1.2rc3 → diffusion_model_framework-1.0.0rc1}/diffusion_models/utils/tensorboard.py +0 -0
|
@@ -1,21 +1,24 @@
|
|
|
1
1
|
Metadata-Version: 2.1
|
|
2
2
|
Name: diffusion-model-framework
|
|
3
|
-
Version: 0.
|
|
3
|
+
Version: 1.0.0rc1
|
|
4
4
|
Summary:
|
|
5
5
|
Home-page: https://github.com/sachahu1/Diffusion-Model-Framework
|
|
6
6
|
Author: Sacha Hu
|
|
7
7
|
Author-email: sachahu@mindsparkai.com
|
|
8
|
-
Requires-Python: >=3.
|
|
8
|
+
Requires-Python: >=3.10,<3.13
|
|
9
9
|
Classifier: Programming Language :: Python :: 3
|
|
10
|
-
Classifier: Programming Language :: Python :: 3.9
|
|
11
10
|
Classifier: Programming Language :: Python :: 3.10
|
|
12
11
|
Classifier: Programming Language :: Python :: 3.11
|
|
13
|
-
|
|
14
|
-
Requires-Dist:
|
|
15
|
-
Requires-Dist:
|
|
16
|
-
Requires-Dist:
|
|
17
|
-
Requires-Dist:
|
|
12
|
+
Classifier: Programming Language :: Python :: 3.12
|
|
13
|
+
Requires-Dist: jupyter (>=1.0.0,<2.0.0)
|
|
14
|
+
Requires-Dist: matplotlib (>=3.9.2,<4.0.0)
|
|
15
|
+
Requires-Dist: numpy (>=2.1.3,<3.0.0)
|
|
16
|
+
Requires-Dist: pillow (>=11.0.0,<12.0.0)
|
|
17
|
+
Requires-Dist: tensorboard (>=2.18.0,<3.0.0)
|
|
18
|
+
Requires-Dist: torch (>=2.5.1,<3.0.0)
|
|
19
|
+
Requires-Dist: torchvision (>=0.20.1,<0.21.0)
|
|
18
20
|
Requires-Dist: tqdm (>=4.66.2,<5.0.0)
|
|
21
|
+
Requires-Dist: transformers (>=4.46.1,<5.0.0)
|
|
19
22
|
Project-URL: Documentation, https://www.sachahu.com/docs/diffusion-model-framework/latest/index.html
|
|
20
23
|
Project-URL: Repository, https://github.com/sachahu1/Diffusion-Model-Framework
|
|
21
24
|
Description-Content-Type: text/markdown
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
__version__ = "1.0.0-rc.1"
|
|
@@ -7,12 +7,12 @@ import torch
|
|
|
7
7
|
from diffusion_models.gaussian_diffusion.beta_schedulers import (
|
|
8
8
|
BaseBetaScheduler,
|
|
9
9
|
)
|
|
10
|
+
|
|
10
11
|
if TYPE_CHECKING:
|
|
11
12
|
from diffusion_models.models.base_diffusion_model import BaseDiffusionModel
|
|
12
13
|
|
|
13
14
|
|
|
14
15
|
class BaseDiffuser(abc.ABC):
|
|
15
|
-
|
|
16
16
|
def __init__(self, beta_scheduler: BaseBetaScheduler):
|
|
17
17
|
"""Initializes the object with the specified beta scheduler.
|
|
18
18
|
|
|
@@ -51,7 +51,9 @@ class BaseDiffuser(abc.ABC):
|
|
|
51
51
|
raise NotImplementedError()
|
|
52
52
|
|
|
53
53
|
@abc.abstractmethod
|
|
54
|
-
def denoise_batch(
|
|
54
|
+
def denoise_batch(
|
|
55
|
+
self, images: torch.Tensor, model: "BaseDiffusionModel"
|
|
56
|
+
) -> List[torch.Tensor]:
|
|
55
57
|
"""Denoise a batch of images.
|
|
56
58
|
|
|
57
59
|
Args:
|
|
@@ -75,4 +77,3 @@ class BaseDiffuser(abc.ABC):
|
|
|
75
77
|
Default is "cpu".
|
|
76
78
|
"""
|
|
77
79
|
raise NotImplementedError()
|
|
78
|
-
|
|
@@ -6,7 +6,8 @@ import torch
|
|
|
6
6
|
|
|
7
7
|
|
|
8
8
|
class BaseBetaScheduler:
|
|
9
|
-
def __init__(
|
|
9
|
+
def __init__(
|
|
10
|
+
self,
|
|
10
11
|
steps: int,
|
|
11
12
|
enforce_zero_terminal_snr: bool = False,
|
|
12
13
|
initialize: bool = True,
|
|
@@ -46,8 +47,8 @@ class BaseBetaScheduler:
|
|
|
46
47
|
self.enforce_zero_terminal_snr()
|
|
47
48
|
|
|
48
49
|
def _initialize(self):
|
|
49
|
-
|
|
50
|
-
|
|
50
|
+
self.betas = self.sample_betas()
|
|
51
|
+
self.alpha_bars = self.compute_alpha_bar()
|
|
51
52
|
|
|
52
53
|
def enforce_zero_terminal_snr(self):
|
|
53
54
|
"""Enforce terminal SNR by adjusting :math:`\\beta` and :math:`\\bar{\\alpha}`.
|
|
@@ -0,0 +1,187 @@
|
|
|
1
|
+
from enum import Enum
|
|
2
|
+
from typing import List, Tuple
|
|
3
|
+
|
|
4
|
+
import numpy as np
|
|
5
|
+
import torch
|
|
6
|
+
from tqdm import tqdm
|
|
7
|
+
|
|
8
|
+
from diffusion_models.gaussian_diffusion.base_diffuser import BaseDiffuser
|
|
9
|
+
from diffusion_models.gaussian_diffusion.beta_schedulers import \
|
|
10
|
+
BaseBetaScheduler
|
|
11
|
+
from diffusion_models.models.base_diffusion_model import BaseDiffusionModel
|
|
12
|
+
from diffusion_models.utils.schemas import Checkpoint
|
|
13
|
+
|
|
14
|
+
class DenoisingMode(str, Enum):
|
|
15
|
+
Linear = "linear"
|
|
16
|
+
Quadratic = "quadratic"
|
|
17
|
+
|
|
18
|
+
class DdimDiffuser(BaseDiffuser):
|
|
19
|
+
def __init__(self, beta_scheduler: BaseBetaScheduler):
|
|
20
|
+
"""Initializes the class instance.
|
|
21
|
+
|
|
22
|
+
Args:
|
|
23
|
+
beta_scheduler (BaseBetaScheduler): The beta scheduler instance to be used.
|
|
24
|
+
|
|
25
|
+
"""
|
|
26
|
+
super().__init__(beta_scheduler)
|
|
27
|
+
self.device: str = "cpu"
|
|
28
|
+
"""The device to use. Defaults to cpu."""
|
|
29
|
+
|
|
30
|
+
@classmethod
|
|
31
|
+
def from_checkpoint(cls, checkpoint: Checkpoint) -> "DdimDiffuser":
|
|
32
|
+
"""Instantiate a DDIM Diffuser from a training checkpoint.
|
|
33
|
+
|
|
34
|
+
Args:
|
|
35
|
+
checkpoint: The training checkpoint object containing
|
|
36
|
+
the trained model's parameters and configuration.
|
|
37
|
+
|
|
38
|
+
Returns:
|
|
39
|
+
An instance of the DdimDiffuser class initialized with the parameters
|
|
40
|
+
loaded from the given checkpoint.
|
|
41
|
+
"""
|
|
42
|
+
return cls(
|
|
43
|
+
beta_scheduler=BaseBetaScheduler.from_tensors(
|
|
44
|
+
steps=checkpoint.beta_scheduler_config.steps,
|
|
45
|
+
betas=checkpoint.beta_scheduler_config.betas,
|
|
46
|
+
alpha_bars=checkpoint.beta_scheduler_config.alpha_bars,
|
|
47
|
+
)
|
|
48
|
+
)
|
|
49
|
+
|
|
50
|
+
def to(self, device: str = "cpu"):
|
|
51
|
+
"""Moves the data to the specified device.
|
|
52
|
+
|
|
53
|
+
This performs a similar behaviour to the `to` method of PyTorch. moving the
|
|
54
|
+
GaussianDiffuser and the BetaScheduler to the specified device.
|
|
55
|
+
|
|
56
|
+
Args:
|
|
57
|
+
device: The device to which the method should move the object.
|
|
58
|
+
Default is "cpu".
|
|
59
|
+
|
|
60
|
+
Example:
|
|
61
|
+
>>> ddim_diffuser = DdimDiffuser()
|
|
62
|
+
>>> ddim_diffuser = ddim_diffuser.to(device="cuda")
|
|
63
|
+
"""
|
|
64
|
+
self.device = device
|
|
65
|
+
self.beta_scheduler = self.beta_scheduler.to(self.device)
|
|
66
|
+
return self
|
|
67
|
+
|
|
68
|
+
def _diffuse_batch(
|
|
69
|
+
self, images: torch.Tensor, timesteps: torch.Tensor
|
|
70
|
+
) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
|
|
71
|
+
noise = torch.randn_like(images, device=self.device)
|
|
72
|
+
|
|
73
|
+
alpha_bar_t = self.beta_scheduler.alpha_bars.gather(dim=0, index=timesteps)
|
|
74
|
+
|
|
75
|
+
alpha_bar_t = alpha_bar_t.reshape((-1, *((1,) * (len(images.shape) - 1))))
|
|
76
|
+
|
|
77
|
+
mu = torch.sqrt(alpha_bar_t)
|
|
78
|
+
sigma = torch.sqrt(1 - alpha_bar_t)
|
|
79
|
+
images = mu * images + sigma * noise
|
|
80
|
+
return images, noise, timesteps
|
|
81
|
+
|
|
82
|
+
def diffuse_batch(
|
|
83
|
+
self, images: torch.Tensor
|
|
84
|
+
) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
|
|
85
|
+
"""Diffuse a batch of images.
|
|
86
|
+
|
|
87
|
+
Diffuse the given batch of images by adding noise based on the beta scheduler.
|
|
88
|
+
|
|
89
|
+
Args:
|
|
90
|
+
images: Batch of images to diffuse.\n
|
|
91
|
+
Shape should be ``(B, C, H, W)``.
|
|
92
|
+
|
|
93
|
+
Returns:
|
|
94
|
+
A tuple containing three tensors
|
|
95
|
+
|
|
96
|
+
- images: Diffused batch of images.
|
|
97
|
+
- noise: Noise added to the images.
|
|
98
|
+
- timesteps: Timesteps used for diffusion.
|
|
99
|
+
"""
|
|
100
|
+
timesteps = torch.randint(
|
|
101
|
+
0, self.beta_scheduler.steps, (images.shape[0],), device=self.device
|
|
102
|
+
)
|
|
103
|
+
return self._diffuse_batch(images, timesteps)
|
|
104
|
+
|
|
105
|
+
@torch.no_grad()
|
|
106
|
+
def _denoise_step(
|
|
107
|
+
self,
|
|
108
|
+
images: torch.Tensor,
|
|
109
|
+
model: torch.nn.Module,
|
|
110
|
+
timestep: torch.Tensor,
|
|
111
|
+
timestep_prev: torch.Tensor,
|
|
112
|
+
eta: float = 0.0,
|
|
113
|
+
) -> torch.Tensor:
|
|
114
|
+
epsilon_theta = model(images, timestep)
|
|
115
|
+
|
|
116
|
+
alpha_bar_t = self.beta_scheduler.alpha_bars.gather(
|
|
117
|
+
dim=0, index=timestep
|
|
118
|
+
).reshape(-1, 1, 1, 1)
|
|
119
|
+
|
|
120
|
+
alpha_bar_t_prev = self.beta_scheduler.alpha_bars.gather(
|
|
121
|
+
dim=0, index=timestep_prev
|
|
122
|
+
).reshape(-1, 1, 1, 1)
|
|
123
|
+
|
|
124
|
+
sigma = eta * torch.sqrt(
|
|
125
|
+
(1 - alpha_bar_t_prev)
|
|
126
|
+
/ (1 - alpha_bar_t)
|
|
127
|
+
* (1 - alpha_bar_t / alpha_bar_t_prev)
|
|
128
|
+
)
|
|
129
|
+
|
|
130
|
+
epsilon_t = torch.randn_like(images)
|
|
131
|
+
|
|
132
|
+
mu = (
|
|
133
|
+
torch.sqrt(alpha_bar_t_prev / alpha_bar_t) * images
|
|
134
|
+
+ (
|
|
135
|
+
torch.sqrt(1 - alpha_bar_t_prev - sigma**2)
|
|
136
|
+
- torch.sqrt((alpha_bar_t_prev * (1 - alpha_bar_t)) / alpha_bar_t)
|
|
137
|
+
) * epsilon_theta
|
|
138
|
+
)
|
|
139
|
+
return mu + sigma * epsilon_t
|
|
140
|
+
|
|
141
|
+
def denoise_batch(
|
|
142
|
+
self,
|
|
143
|
+
images: torch.Tensor,
|
|
144
|
+
model: "BaseDiffusionModel",
|
|
145
|
+
number_of_steps: int = 50,
|
|
146
|
+
mode: DenoisingMode = DenoisingMode.Linear
|
|
147
|
+
) -> List[torch.Tensor]:
|
|
148
|
+
"""Denoise a batch of images.
|
|
149
|
+
|
|
150
|
+
This denoises a batch images. This is the image generation process.
|
|
151
|
+
|
|
152
|
+
Args:
|
|
153
|
+
images: A batch of noisy images.
|
|
154
|
+
model: The model to be used for denoising.
|
|
155
|
+
number_of_steps: Number of steps used in the denoising process.
|
|
156
|
+
mode: Linear or Quadratic sampling.
|
|
157
|
+
|
|
158
|
+
Returns:
|
|
159
|
+
A list of tensors containing a batch of denoised images.
|
|
160
|
+
"""
|
|
161
|
+
if mode == DenoisingMode.Linear:
|
|
162
|
+
a = self.beta_scheduler.steps // number_of_steps
|
|
163
|
+
time_steps = np.asarray(list(range(0, self.beta_scheduler.steps, a)))
|
|
164
|
+
else:
|
|
165
|
+
time_steps = (
|
|
166
|
+
np.linspace(0, np.sqrt(self.beta_scheduler.steps * 0.8), number_of_steps)
|
|
167
|
+
** 2
|
|
168
|
+
).astype(int)
|
|
169
|
+
|
|
170
|
+
time_steps = time_steps + 1
|
|
171
|
+
time_steps_prev = np.concatenate([[0], time_steps[:-1]])
|
|
172
|
+
|
|
173
|
+
denoised_images = []
|
|
174
|
+
for i in tqdm(range(number_of_steps)[::-1], desc="Denoising"):
|
|
175
|
+
timestep = torch.full(
|
|
176
|
+
(images.shape[0],), time_steps[i], device=self.device
|
|
177
|
+
)
|
|
178
|
+
timestep_prev = torch.full(
|
|
179
|
+
(images.shape[0],), time_steps_prev[i], device=self.device
|
|
180
|
+
)
|
|
181
|
+
|
|
182
|
+
images = self._denoise_step(
|
|
183
|
+
images, model=model, timestep=timestep, timestep_prev=timestep_prev,
|
|
184
|
+
)
|
|
185
|
+
images = torch.clamp(images, -1.0, 1.0)
|
|
186
|
+
denoised_images.append(images)
|
|
187
|
+
return denoised_images
|
|
@@ -1,5 +1,8 @@
|
|
|
1
|
-
from typing import
|
|
1
|
+
from typing import TYPE_CHECKING
|
|
2
|
+
from typing import List
|
|
3
|
+
from typing import Tuple
|
|
2
4
|
|
|
5
|
+
import numpy as np
|
|
3
6
|
import torch
|
|
4
7
|
from tqdm import tqdm
|
|
5
8
|
|
|
@@ -9,9 +12,11 @@ from diffusion_models.gaussian_diffusion.beta_schedulers import (
|
|
|
9
12
|
)
|
|
10
13
|
from diffusion_models.utils.schemas import Checkpoint
|
|
11
14
|
|
|
15
|
+
|
|
12
16
|
if TYPE_CHECKING:
|
|
13
17
|
from diffusion_models.models.base_diffusion_model import BaseDiffusionModel
|
|
14
18
|
|
|
19
|
+
|
|
15
20
|
class GaussianDiffuser(BaseDiffuser):
|
|
16
21
|
def __init__(self, beta_scheduler: BaseBetaScheduler):
|
|
17
22
|
"""Initializes the class instance.
|
|
@@ -62,6 +67,20 @@ class GaussianDiffuser(BaseDiffuser):
|
|
|
62
67
|
self.beta_scheduler = self.beta_scheduler.to(self.device)
|
|
63
68
|
return self
|
|
64
69
|
|
|
70
|
+
def _diffuse_batch(
|
|
71
|
+
self, images: torch.Tensor, timesteps: torch.Tensor
|
|
72
|
+
) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
|
|
73
|
+
noise = torch.randn_like(images, device=self.device)
|
|
74
|
+
|
|
75
|
+
alpha_bar_t = self.beta_scheduler.alpha_bars.gather(dim=0, index=timesteps)
|
|
76
|
+
|
|
77
|
+
alpha_bar_t = alpha_bar_t.reshape((-1, *((1,) * (len(images.shape) - 1))))
|
|
78
|
+
|
|
79
|
+
mu = torch.sqrt(alpha_bar_t)
|
|
80
|
+
sigma = torch.sqrt(1 - alpha_bar_t)
|
|
81
|
+
images = mu * images + sigma * noise
|
|
82
|
+
return images, noise, timesteps
|
|
83
|
+
|
|
65
84
|
def diffuse_batch(
|
|
66
85
|
self, images: torch.Tensor
|
|
67
86
|
) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
|
|
@@ -83,16 +102,7 @@ class GaussianDiffuser(BaseDiffuser):
|
|
|
83
102
|
timesteps = torch.randint(
|
|
84
103
|
0, self.beta_scheduler.steps, (images.shape[0],), device=self.device
|
|
85
104
|
)
|
|
86
|
-
|
|
87
|
-
|
|
88
|
-
alpha_bar_t = self.beta_scheduler.alpha_bars.gather(dim=0, index=timesteps)
|
|
89
|
-
|
|
90
|
-
alpha_bar_t = alpha_bar_t.reshape((-1, *((1,) * (len(images.shape) - 1))))
|
|
91
|
-
|
|
92
|
-
mu = torch.sqrt(alpha_bar_t)
|
|
93
|
-
sigma = torch.sqrt(1 - alpha_bar_t)
|
|
94
|
-
images = mu * images + sigma * noise
|
|
95
|
-
return images, noise, timesteps
|
|
105
|
+
return self._diffuse_batch(images, timesteps)
|
|
96
106
|
|
|
97
107
|
@torch.no_grad()
|
|
98
108
|
def _denoise_step(
|
|
@@ -4,6 +4,7 @@ import math
|
|
|
4
4
|
import torch
|
|
5
5
|
from torch import nn
|
|
6
6
|
|
|
7
|
+
from diffusion_models.gaussian_diffusion.base_diffuser import BaseDiffuser
|
|
7
8
|
from diffusion_models.gaussian_diffusion.gaussian_diffuser import (
|
|
8
9
|
GaussianDiffuser,
|
|
9
10
|
)
|
|
@@ -63,7 +64,7 @@ class SinusoidalPositionEmbeddings(nn.Module):
|
|
|
63
64
|
class SimpleUnet(BaseDiffusionModel):
|
|
64
65
|
def __init__(
|
|
65
66
|
self,
|
|
66
|
-
diffuser:
|
|
67
|
+
diffuser: BaseDiffuser,
|
|
67
68
|
image_channels: int,
|
|
68
69
|
):
|
|
69
70
|
"""A Simplified variant of the Unet architecture used in DDPM.
|
|
@@ -48,16 +48,20 @@ class BaseDiffusionModel(nn.Module, abc.ABC):
|
|
|
48
48
|
def denoise(self, images: torch.Tensor) -> List[torch.Tensor]:
|
|
49
49
|
"""Denoise a batch of images.
|
|
50
50
|
|
|
51
|
-
|
|
52
|
-
|
|
51
|
+
Args:
|
|
52
|
+
images: A tensor containing a batch of images to denoise.
|
|
53
53
|
|
|
54
|
-
|
|
55
|
-
|
|
56
|
-
|
|
54
|
+
Returns:
|
|
55
|
+
A list of tensors containing a batch of denoised images.
|
|
56
|
+
"""
|
|
57
57
|
return self.diffuser.denoise_batch(images=images, model=self)
|
|
58
58
|
|
|
59
59
|
@abc.abstractmethod
|
|
60
|
-
def forward(
|
|
60
|
+
def forward(
|
|
61
|
+
self,
|
|
62
|
+
x: torch.Tensor,
|
|
63
|
+
timestep: torch.Tensor,
|
|
64
|
+
) -> torch.Tensor:
|
|
61
65
|
"""Forward pass of the diffusion model.
|
|
62
66
|
|
|
63
67
|
The forward pass of the diffusion model, predicting the noise at a single
|
|
@@ -17,6 +17,7 @@ from diffusion_models.gaussian_diffusion.beta_schedulers import (
|
|
|
17
17
|
@dataclass
|
|
18
18
|
class TrainingConfiguration:
|
|
19
19
|
"""A training configuration for simple experiment management."""
|
|
20
|
+
|
|
20
21
|
training_name: str
|
|
21
22
|
"""The name of the training."""
|
|
22
23
|
batch_size: int
|
|
@@ -36,6 +37,7 @@ class TrainingConfiguration:
|
|
|
36
37
|
@dataclass
|
|
37
38
|
class LogConfiguration:
|
|
38
39
|
"""An object to manage logging configuration."""
|
|
40
|
+
|
|
39
41
|
log_rate: int = 10
|
|
40
42
|
"""The rate at which training metrics are logged."""
|
|
41
43
|
image_rate: int = 50
|
|
@@ -48,6 +50,7 @@ class LogConfiguration:
|
|
|
48
50
|
@dataclass
|
|
49
51
|
class BetaSchedulerConfiguration:
|
|
50
52
|
"""A simplified beta scheduler configuration."""
|
|
53
|
+
|
|
51
54
|
steps: int
|
|
52
55
|
"""The number of steps in the beta scheduler."""
|
|
53
56
|
betas: torch.Tensor
|
|
@@ -55,9 +58,11 @@ class BetaSchedulerConfiguration:
|
|
|
55
58
|
alpha_bars: torch.Tensor
|
|
56
59
|
"""The alpha bar values."""
|
|
57
60
|
|
|
61
|
+
|
|
58
62
|
@dataclass
|
|
59
63
|
class Checkpoint:
|
|
60
64
|
"""A simplified checkpoint framework for easy saving and loading."""
|
|
65
|
+
|
|
61
66
|
epoch: int
|
|
62
67
|
"""The current epoch."""
|
|
63
68
|
model_state_dict: Dict[str, Any]
|
|
@@ -83,7 +88,9 @@ class Checkpoint:
|
|
|
83
88
|
"""
|
|
84
89
|
|
|
85
90
|
@classmethod
|
|
86
|
-
def from_file(
|
|
91
|
+
def from_file(
|
|
92
|
+
cls, file_path: str, map_location: Optional[str] = None
|
|
93
|
+
) -> "Checkpoint":
|
|
87
94
|
"""Load and instantiate a checkpoint from a file.
|
|
88
95
|
|
|
89
96
|
Args:
|
|
@@ -93,7 +100,9 @@ class Checkpoint:
|
|
|
93
100
|
Returns:
|
|
94
101
|
A checkpoint instance.
|
|
95
102
|
"""
|
|
96
|
-
checkpoint = torch.load(
|
|
103
|
+
checkpoint = torch.load(
|
|
104
|
+
f=file_path, weights_only=True, map_location=map_location
|
|
105
|
+
)
|
|
97
106
|
checkpoint = cls(**checkpoint)
|
|
98
107
|
beta_scheduler_config = BetaSchedulerConfiguration(
|
|
99
108
|
**checkpoint.beta_scheduler_config
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
[tool.poetry]
|
|
2
2
|
name = "diffusion-model-framework"
|
|
3
|
-
version = "0.
|
|
3
|
+
version = "1.0.0-rc.1"
|
|
4
4
|
description = ""
|
|
5
5
|
authors = ["Sacha Hu <sachahu@mindsparkai.com>"]
|
|
6
6
|
readme = "README.md"
|
|
@@ -11,13 +11,17 @@ packages = [
|
|
|
11
11
|
]
|
|
12
12
|
|
|
13
13
|
[tool.poetry.dependencies]
|
|
14
|
-
python = ">=3.
|
|
15
|
-
pillow-simd = "^9.0.0
|
|
14
|
+
python = ">=3.10,<3.13"
|
|
15
|
+
#pillow-simd = "^9.0.0"
|
|
16
16
|
tqdm = "^4.66.2"
|
|
17
|
-
numpy = "^1.
|
|
18
|
-
torchvision = "^0.
|
|
19
|
-
torch = "^2.
|
|
20
|
-
tensorboard = "^2.
|
|
17
|
+
numpy = "^2.1.3"
|
|
18
|
+
torchvision = "^0.20.1"
|
|
19
|
+
torch = "^2.5.1"
|
|
20
|
+
tensorboard = "^2.18.0"
|
|
21
|
+
matplotlib = "^3.9.2"
|
|
22
|
+
jupyter = "^1.0.0"
|
|
23
|
+
pillow = "^11.0.0"
|
|
24
|
+
transformers = "^4.46.1"
|
|
21
25
|
|
|
22
26
|
[tool.poetry.group.gdown]
|
|
23
27
|
optional = true
|
|
@@ -51,6 +55,12 @@ sphinx-copybutton = "^0.5.2"
|
|
|
51
55
|
sphinx-autoapi = "^3.2.1"
|
|
52
56
|
gitpython = "^3.1.43"
|
|
53
57
|
|
|
58
|
+
[tool.poetry.group.coco]
|
|
59
|
+
optional = true
|
|
60
|
+
|
|
61
|
+
[tool.poetry.group.coco.dependencies]
|
|
62
|
+
pycocotools = "^2.0.8"
|
|
63
|
+
|
|
54
64
|
[build-system]
|
|
55
65
|
requires = ["poetry-core>=1.0.0", "poetry-dynamic-versioning>=1.0.0,<2.0.0"]
|
|
56
66
|
build-backend = "poetry_dynamic_versioning.backend"
|
|
@@ -64,6 +74,7 @@ exclude = [".venv", ".env", ".git", "tests"]
|
|
|
64
74
|
# Add the `line-too-long` rule to the enforced rule set. By default, Ruff omits rules that
|
|
65
75
|
# overlap with the use of a formatter, like Black, but we can override this behavior by
|
|
66
76
|
# explicitly adding the rule.
|
|
77
|
+
select = ["NPY201"]
|
|
67
78
|
extend-select = [
|
|
68
79
|
"B", # flake8-bugbear
|
|
69
80
|
"C4", # flake8-comprehensions
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
__version__ = "0.1.2-rc.3"
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|