File size: 12,179 Bytes
7f43c1b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
# coding=utf-8
# Copyright 2023 The HuggingFace Inc. team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""PyTorch optimization for diffusion models."""

import math
from enum import Enum
from typing import Optional, Union

from torch.optim import Optimizer
from torch.optim.lr_scheduler import LambdaLR

from .utils import logging


logger = logging.get_logger(__name__)


class SchedulerType(Enum):
    LINEAR = "linear"
    COSINE = "cosine"
    COSINE_WITH_RESTARTS = "cosine_with_restarts"
    POLYNOMIAL = "polynomial"
    CONSTANT = "constant"
    CONSTANT_WITH_WARMUP = "constant_with_warmup"


def get_constant_schedule(optimizer: Optimizer, last_epoch: int = -1):
    """
    Create a schedule with a constant learning rate, using the learning rate set in optimizer.

    Args:
        optimizer ([`~torch.optim.Optimizer`]):
            The optimizer for which to schedule the learning rate.
        last_epoch (`int`, *optional*, defaults to -1):
            The index of the last epoch when resuming training.

    Return:
        `torch.optim.lr_scheduler.LambdaLR` with the appropriate schedule.
    """
    return LambdaLR(optimizer, lambda _: 1, last_epoch=last_epoch)


def get_constant_schedule_with_warmup(optimizer: Optimizer, num_warmup_steps: int, last_epoch: int = -1):
    """
    Create a schedule with a constant learning rate preceded by a warmup period during which the learning rate
    increases linearly between 0 and the initial lr set in the optimizer.

    Args:
        optimizer ([`~torch.optim.Optimizer`]):
            The optimizer for which to schedule the learning rate.
        num_warmup_steps (`int`):
            The number of steps for the warmup phase.
        last_epoch (`int`, *optional*, defaults to -1):
            The index of the last epoch when resuming training.

    Return:
        `torch.optim.lr_scheduler.LambdaLR` with the appropriate schedule.
    """

    def lr_lambda(current_step: int):
        if current_step < num_warmup_steps:
            return float(current_step) / float(max(1.0, num_warmup_steps))
        return 1.0

    return LambdaLR(optimizer, lr_lambda, last_epoch=last_epoch)


def get_linear_schedule_with_warmup(optimizer, num_warmup_steps, num_training_steps, last_epoch=-1):
    """
    Create a schedule with a learning rate that decreases linearly from the initial lr set in the optimizer to 0, after
    a warmup period during which it increases linearly from 0 to the initial lr set in the optimizer.

    Args:
        optimizer ([`~torch.optim.Optimizer`]):
            The optimizer for which to schedule the learning rate.
        num_warmup_steps (`int`):
            The number of steps for the warmup phase.
        num_training_steps (`int`):
            The total number of training steps.
        last_epoch (`int`, *optional*, defaults to -1):
            The index of the last epoch when resuming training.

    Return:
        `torch.optim.lr_scheduler.LambdaLR` with the appropriate schedule.
    """

    def lr_lambda(current_step: int):
        if current_step < num_warmup_steps:
            return float(current_step) / float(max(1, num_warmup_steps))
        return max(
            0.0, float(num_training_steps - current_step) / float(max(1, num_training_steps - num_warmup_steps))
        )

    return LambdaLR(optimizer, lr_lambda, last_epoch)


def get_cosine_schedule_with_warmup(
    optimizer: Optimizer, num_warmup_steps: int, num_training_steps: int, num_cycles: float = 0.5, last_epoch: int = -1
):
    """
    Create a schedule with a learning rate that decreases following the values of the cosine function between the
    initial lr set in the optimizer to 0, after a warmup period during which it increases linearly between 0 and the
    initial lr set in the optimizer.

    Args:
        optimizer ([`~torch.optim.Optimizer`]):
            The optimizer for which to schedule the learning rate.
        num_warmup_steps (`int`):
            The number of steps for the warmup phase.
        num_training_steps (`int`):
            The total number of training steps.
        num_periods (`float`, *optional*, defaults to 0.5):
            The number of periods of the cosine function in a schedule (the default is to just decrease from the max
            value to 0 following a half-cosine).
        last_epoch (`int`, *optional*, defaults to -1):
            The index of the last epoch when resuming training.

    Return:
        `torch.optim.lr_scheduler.LambdaLR` with the appropriate schedule.
    """

    def lr_lambda(current_step):
        if current_step < num_warmup_steps:
            return float(current_step) / float(max(1, num_warmup_steps))
        progress = float(current_step - num_warmup_steps) / float(max(1, num_training_steps - num_warmup_steps))
        return max(0.0, 0.5 * (1.0 + math.cos(math.pi * float(num_cycles) * 2.0 * progress)))

    return LambdaLR(optimizer, lr_lambda, last_epoch)


def get_cosine_with_hard_restarts_schedule_with_warmup(
    optimizer: Optimizer, num_warmup_steps: int, num_training_steps: int, num_cycles: int = 1, last_epoch: int = -1
):
    """
    Create a schedule with a learning rate that decreases following the values of the cosine function between the
    initial lr set in the optimizer to 0, with several hard restarts, after a warmup period during which it increases
    linearly between 0 and the initial lr set in the optimizer.

    Args:
        optimizer ([`~torch.optim.Optimizer`]):
            The optimizer for which to schedule the learning rate.
        num_warmup_steps (`int`):
            The number of steps for the warmup phase.
        num_training_steps (`int`):
            The total number of training steps.
        num_cycles (`int`, *optional*, defaults to 1):
            The number of hard restarts to use.
        last_epoch (`int`, *optional*, defaults to -1):
            The index of the last epoch when resuming training.

    Return:
        `torch.optim.lr_scheduler.LambdaLR` with the appropriate schedule.
    """

    def lr_lambda(current_step):
        if current_step < num_warmup_steps:
            return float(current_step) / float(max(1, num_warmup_steps))
        progress = float(current_step - num_warmup_steps) / float(max(1, num_training_steps - num_warmup_steps))
        if progress >= 1.0:
            return 0.0
        return max(0.0, 0.5 * (1.0 + math.cos(math.pi * ((float(num_cycles) * progress) % 1.0))))

    return LambdaLR(optimizer, lr_lambda, last_epoch)


def get_polynomial_decay_schedule_with_warmup(
    optimizer, num_warmup_steps, num_training_steps, lr_end=1e-7, power=1.0, last_epoch=-1
):
    """
    Create a schedule with a learning rate that decreases as a polynomial decay from the initial lr set in the
    optimizer to end lr defined by *lr_end*, after a warmup period during which it increases linearly from 0 to the
    initial lr set in the optimizer.

    Args:
        optimizer ([`~torch.optim.Optimizer`]):
            The optimizer for which to schedule the learning rate.
        num_warmup_steps (`int`):
            The number of steps for the warmup phase.
        num_training_steps (`int`):
            The total number of training steps.
        lr_end (`float`, *optional*, defaults to 1e-7):
            The end LR.
        power (`float`, *optional*, defaults to 1.0):
            Power factor.
        last_epoch (`int`, *optional*, defaults to -1):
            The index of the last epoch when resuming training.

    Note: *power* defaults to 1.0 as in the fairseq implementation, which in turn is based on the original BERT
    implementation at
    https://github.com/google-research/bert/blob/f39e881b169b9d53bea03d2d341b31707a6c052b/optimization.py#L37

    Return:
        `torch.optim.lr_scheduler.LambdaLR` with the appropriate schedule.

    """

    lr_init = optimizer.defaults["lr"]
    if not (lr_init > lr_end):
        raise ValueError(f"lr_end ({lr_end}) must be be smaller than initial lr ({lr_init})")

    def lr_lambda(current_step: int):
        if current_step < num_warmup_steps:
            return float(current_step) / float(max(1, num_warmup_steps))
        elif current_step > num_training_steps:
            return lr_end / lr_init  # as LambdaLR multiplies by lr_init
        else:
            lr_range = lr_init - lr_end
            decay_steps = num_training_steps - num_warmup_steps
            pct_remaining = 1 - (current_step - num_warmup_steps) / decay_steps
            decay = lr_range * pct_remaining**power + lr_end
            return decay / lr_init  # as LambdaLR multiplies by lr_init

    return LambdaLR(optimizer, lr_lambda, last_epoch)


TYPE_TO_SCHEDULER_FUNCTION = {
    SchedulerType.LINEAR: get_linear_schedule_with_warmup,
    SchedulerType.COSINE: get_cosine_schedule_with_warmup,
    SchedulerType.COSINE_WITH_RESTARTS: get_cosine_with_hard_restarts_schedule_with_warmup,
    SchedulerType.POLYNOMIAL: get_polynomial_decay_schedule_with_warmup,
    SchedulerType.CONSTANT: get_constant_schedule,
    SchedulerType.CONSTANT_WITH_WARMUP: get_constant_schedule_with_warmup,
}


def get_scheduler(
    name: Union[str, SchedulerType],
    optimizer: Optimizer,
    num_warmup_steps: Optional[int] = None,
    num_training_steps: Optional[int] = None,
    num_cycles: int = 1,
    power: float = 1.0,
):
    """
    Unified API to get any scheduler from its name.

    Args:
        name (`str` or `SchedulerType`):
            The name of the scheduler to use.
        optimizer (`torch.optim.Optimizer`):
            The optimizer that will be used during training.
        num_warmup_steps (`int`, *optional*):
            The number of warmup steps to do. This is not required by all schedulers (hence the argument being
            optional), the function will raise an error if it's unset and the scheduler type requires it.
        num_training_steps (`int``, *optional*):
            The number of training steps to do. This is not required by all schedulers (hence the argument being
            optional), the function will raise an error if it's unset and the scheduler type requires it.
        num_cycles (`int`, *optional*):
            The number of hard restarts used in `COSINE_WITH_RESTARTS` scheduler.
        power (`float`, *optional*, defaults to 1.0):
            Power factor. See `POLYNOMIAL` scheduler
        last_epoch (`int`, *optional*, defaults to -1):
            The index of the last epoch when resuming training.
    """
    name = SchedulerType(name)
    schedule_func = TYPE_TO_SCHEDULER_FUNCTION[name]
    if name == SchedulerType.CONSTANT:
        return schedule_func(optimizer)

    # All other schedulers require `num_warmup_steps`
    if num_warmup_steps is None:
        raise ValueError(f"{name} requires `num_warmup_steps`, please provide that argument.")

    if name == SchedulerType.CONSTANT_WITH_WARMUP:
        return schedule_func(optimizer, num_warmup_steps=num_warmup_steps)

    # All other schedulers require `num_training_steps`
    if num_training_steps is None:
        raise ValueError(f"{name} requires `num_training_steps`, please provide that argument.")

    if name == SchedulerType.COSINE_WITH_RESTARTS:
        return schedule_func(
            optimizer, num_warmup_steps=num_warmup_steps, num_training_steps=num_training_steps, num_cycles=num_cycles
        )

    if name == SchedulerType.POLYNOMIAL:
        return schedule_func(
            optimizer, num_warmup_steps=num_warmup_steps, num_training_steps=num_training_steps, power=power
        )

    return schedule_func(optimizer, num_warmup_steps=num_warmup_steps, num_training_steps=num_training_steps)