Sora - 探索AI视频模型的无限可能
随着人工智能技术的飞速发展,AI视频模型已成为科技领域的新热点。而在这个浪潮中,OpenAI推出的首个AI视频模型Sora,以其卓越的性能和前瞻性的技术,引领着AI视频领域的创新发展。让我们将一起探讨Sora的技术特点、应用场景以及对未来创作方式的深远影响。
Sora模型实际上是一个扩散模型+Transformer,本文来讲述扩散模型的发展、原理及代码实践。本文基于denoising diffusion probabilistic model (DDPM),探索图像生成的过程。扩散。DDPM已经在(无)条件图像/音频/视频生成领域取得了较多显著的成果。
导入所需的环境
%%capture captured_output
!pip uninstall mindspore -y
!pip install -i https://pypi.mirrors.ustc.edu.cn/simple mindspore==2.3.0rc1
import math
from functools import partial
%matplotlib inline
import matplotlib.pyplot as plt
from tqdm.auto import tqdm
import numpy as np
from multiprocessing import cpu_count
from download import download
import mindspore as ms
import mindspore.nn as nn
import mindspore.ops as ops
from mindspore import Tensor, Parameter
from mindspore import dtype as mstype
from mindspore.dataset.vision import Resize, Inter, CenterCrop, ToTensor, RandomHorizontalFlip, ToPIL
from mindspore.common.initializer import initializer
from mindspore.amp import DynamicLossScaler
ms.set_seed(0)
构建Diffusion模型
def rearrange(head, inputs):
b, hc, x, y = inputs.shape
c = hc // head
return inputs.reshape((b, head, c, x * y))
def rsqrt(x):
res = ops.sqrt(x)
return ops.inv(res)
def randn_like(x, dtype=None):
if dtype is None:
dtype = x.dtype
res = ops.standard_normal(x.shape).astype(dtype)
return res
def randn(shape, dtype=None):
if dtype is None:
dtype = ms.float32
res = ops.standard_normal(shape).astype(dtype)
return res
def randint(low, high, size, dtype=ms.int32):
res = ops.uniform(size, Tensor(low, dtype), Tensor(high, dtype), dtype=dtype)
return res
def exists(x):
return x is not None
def default(val, d):
if exists(val):
return val
return d() if callable(d) else d
def _check_dtype(d1, d2):
if ms.float32 in (d1, d2):
return ms.float32
if d1 == d2:
return d1
raise ValueError('dtype is not supported.')
class Residual(nn.Cell):
def __init__(self, fn):
super().__init__()
self.fn = fn
def construct(self, x, *args, **kwargs):
return self.fn(x, *args, **kwargs) + x
def Upsample(dim):
return nn.Conv2dTranspose(dim, dim, 4, 2, pad_mode="pad", padding=1)
def Downsample(dim):
return nn.Conv2d(dim, dim, 4, 2, pad_mode="pad", padding=1)
位置向量
class SinusoidalPositionEmbeddings(nn.Cell):
def __init__(self, dim):
super().__init__()
self.dim = dim
half_dim = self.dim // 2
emb = math.log(10000) / (half_dim - 1)
emb = np.exp(np.arange(half_dim) * - emb)
self.emb = Tensor(emb, ms.float32)
def construct(self, x):
emb = x[:, None] * self.emb[None, :]
emb = ops.concat((ops.sin(emb), ops.cos(emb)), axis=-1)
return emb
ResNet/ConvNeXT块
class Block(nn.Cell):
def __init__(self, dim, dim_out, groups=1):
super().__init__()
self.proj = nn.Conv2d(dim, dim_out, 3, pad_mode="pad", padding=1)
self.proj = c(dim, dim_out, 3, padding=1, pad_mode='pad')
self.norm = nn.GroupNorm(groups, dim_out)
self.act = nn.SiLU()
def construct(self, x, scale_shift=None):
x = self.proj(x)
x = self.norm(x)
if exists(scale_shift):
scale, shift = scale_shift
x = x * (scale + 1) + shift
x = self.act(x)
return x
class ConvNextBlock(nn.Cell):
def __init__(self, dim, dim_out, *, time_emb_dim=None, mult=2, norm=True):
super().__init__()
self.mlp = (
nn.SequentialCell(nn.GELU(), nn.Dense(time_emb_dim, dim))
if exists(time_emb_dim)
else None
)
self.ds_conv = nn.Conv2d(dim, dim, 7, padding=3, group=dim, pad_mode="pad")
self.net = nn.SequentialCell(
nn.GroupNorm(1, dim) if norm else nn.Identity(),
nn.Conv2d(dim, dim_out * mult, 3, padding=1, pad_mode="pad"),
nn.GELU(),
nn.GroupNorm(1, dim_out * mult),
nn.Conv2d(dim_out * mult, dim_out, 3, padding=1, pad_mode="pad"),
)
self.res_conv = nn.Conv2d(dim, dim_out, 1) if dim != dim_out else nn.Identity()
def construct(self, x, time_emb=None):
h = self.ds_conv(x)
if exists(self.mlp) and exists(time_emb):
assert exists(time_emb), "time embedding must be passed in"
condition = self.mlp(time_emb)
condition = condition.expand_dims(-1).expand_dims(-1)
h = h + condition
h = self.net(h)
return h + self.res_conv(x)
Attention模块
class Attention(nn.Cell):
def __init__(self, dim, heads=4, dim_head=32):
super().__init__()
self.scale = dim_head ** -0.5
self.heads = heads
hidden_dim = dim_head * heads
self.to_qkv = nn.Conv2d(dim, hidden_dim * 3, 1, pad_mode='valid', has_bias=False)
self.to_out = nn.Conv2d(hidden_dim, dim, 1, pad_mode='valid', has_bias=True)
self.map = ops.Map()
self.partial = ops.Partial()
def construct(self, x):
b, _, h, w = x.shape
qkv = self.to_qkv(x).chunk(3, 1)
q, k, v = self.map(self.partial(rearrange, self.heads), qkv)
q = q * self.scale
# 'b h d i, b h d j -> b h i j'
sim = ops.bmm(q.swapaxes(2, 3), k)
attn = ops.softmax(sim, axis=-1)
# 'b h i j, b h d j -> b h i d'
out = ops.bmm(attn, v.swapaxes(2, 3))
out = out.swapaxes(-1, -2).reshape((b, -1, h, w))
return self.to_out(out)
class LayerNorm(nn.Cell):
def __init__(self, dim):
super().__init__()
self.g = Parameter(initializer('ones', (1, dim, 1, 1)), name='g')
def construct(self, x):
eps = 1e-5
var = x.var(1, keepdims=True)
mean = x.mean(1, keep_dims=True)
return (x - mean) * rsqrt((var + eps)) * self.g
class LinearAttention(nn.Cell):
def __init__(self, dim, heads=4, dim_head=32):
super().__init__()
self.scale = dim_head ** -0.5
self.heads = heads
hidden_dim = dim_head * heads
self.to_qkv = nn.Conv2d(dim, hidden_dim * 3, 1, pad_mode='valid', has_bias=False)
self.to_out = nn.SequentialCell(
nn.Conv2d(hidden_dim, dim, 1, pad_mode='valid', has_bias=True),
LayerNorm(dim)
)
self.map = ops.Map()
self.partial = ops.Partial()
def construct(self, x):
b, _, h, w = x.shape
qkv = self.to_qkv(x).chunk(3, 1)
q, k, v = self.map(self.partial(rearrange, self.heads), qkv)
q = ops.softmax(q, -2)
k = ops.softmax(k, -1)
q = q * self.scale
v = v / (h * w)
# 'b h d n, b h e n -> b h d e'
context = ops.bmm(k, v.swapaxes(2, 3))
# 'b h d e, b h d n -> b h e n'
out = ops.bmm(context.swapaxes(2, 3), q)
out = out.reshape((b, -1, h, w))
return self.to_out(out)
组归一化
class PreNorm(nn.Cell):
def __init__(self, dim, fn):
super().__init__()
self.fn = fn
self.norm = nn.GroupNorm(1, dim)
def construct(self, x):
x = self.norm(x)
return self.fn(x)
条件U-Net
class Unet(nn.Cell):
def __init__(
self,
dim,
init_dim=None,
out_dim=None,
dim_mults=(1, 2, 4, 8),
channels=3,
with_time_emb=True,
convnext_mult=2,
):
super().__init__()
self.channels = channels
init_dim = default(init_dim, dim // 3 * 2)
self.init_conv = nn.Conv2d(channels, init_dim, 7, padding=3, pad_mode="pad", has_bias=True)
dims = [init_dim, *map(lambda m: dim * m, dim_mults)]
in_out = list(zip(dims[:-1], dims[1:]))
block_klass = partial(ConvNextBlock, mult=convnext_mult)
if with_time_emb:
time_dim = dim * 4
self.time_mlp = nn.SequentialCell(
SinusoidalPositionEmbeddings(dim),
nn.Dense(dim, time_dim),
nn.GELU(),
nn.Dense(time_dim, time_dim),
)
else:
time_dim = None
self.time_mlp = None
self.downs = nn.CellList([])
self.ups = nn.CellList([])
num_resolutions = len(in_out)
for ind, (dim_in, dim_out) in enumerate(in_out):
is_last = ind >= (num_resolutions - 1)
self.downs.append(
nn.CellList(
[
block_klass(dim_in, dim_out, time_emb_dim=time_dim),
block_klass(dim_out, dim_out, time_emb_dim=time_dim),
Residual(PreNorm(dim_out, LinearAttention(dim_out))),
Downsample(dim_out) if not is_last else nn.Identity(),
]
)
)
mid_dim = dims[-1]
self.mid_block1 = block_klass(mid_dim, mid_dim, time_emb_dim=time_dim)
self.mid_attn = Residual(PreNorm(mid_dim, Attention(mid_dim)))
self.mid_block2 = block_klass(mid_dim, mid_dim, time_emb_dim=time_dim)
for ind, (dim_in, dim_out) in enumerate(reversed(in_out[1:])):
is_last = ind >= (num_resolutions - 1)
self.ups.append(
nn.CellList(
[
block_klass(dim_out * 2, dim_in, time_emb_dim=time_dim),
block_klass(dim_in, dim_in, time_emb_dim=time_dim),
Residual(PreNorm(dim_in, LinearAttention(dim_in))),
Upsample(dim_in) if not is_last else nn.Identity(),
]
)
)
out_dim = default(out_dim, channels)
self.final_conv = nn.SequentialCell(
block_klass(dim, dim), nn.Conv2d(dim, out_dim, 1)
)
def construct(self, x, time):
x = self.init_conv(x)
t = self.time_mlp(time) if exists(self.time_mlp) else None
h = []
for block1, block2, attn, downsample in self.downs:
x = block1(x, t)
x = block2(x, t)
x = attn(x)
h.append(x)
x = downsample(x)
x = self.mid_block1(x, t)
x = self.mid_attn(x)
x = self.mid_block2(x, t)
len_h = len(h) - 1
for block1, block2, attn, upsample in self.ups:
x = ops.concat((x, h[len_h]), 1)
len_h -= 1
x = block1(x, t)
x = block2(x, t)
x = attn(x)
x = upsample(x)
return self.final_conv(x)
正向扩散
def linear_beta_schedule(timesteps):
beta_start = 0.0001
beta_end = 0.02
return np.linspace(beta_start, beta_end, timesteps).astype(np.float32)
# 扩散200步
timesteps = 200
# 定义 beta schedule
betas = linear_beta_schedule(timesteps=timesteps)
# 定义 alphas
alphas = 1. - betas
alphas_cumprod = np.cumprod(alphas, axis=0)
alphas_cumprod_prev = np.pad(alphas_cumprod[:-1], (1, 0), constant_values=1)
sqrt_recip_alphas = Tensor(np.sqrt(1. / alphas))
sqrt_alphas_cumprod = Tensor(np.sqrt(alphas_cumprod))
sqrt_one_minus_alphas_cumprod = Tensor(np.sqrt(1. - alphas_cumprod))
# 计算 q(x_{t-1} | x_t, x_0)
posterior_variance = betas * (1. - alphas_cumprod_prev) / (1. - alphas_cumprod)
p2_loss_weight = (1 + alphas_cumprod / (1 - alphas_cumprod)) ** -0.
p2_loss_weight = Tensor(p2_loss_weight)
def extract(a, t, x_shape):
b = t.shape[0]
out = Tensor(a).gather(t, -1)
return out.reshape(b, *((1,) * (len(x_shape) - 1)))
数据准备预处理
# 下载MNIST数据集
url = 'https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/notebook/datasets/dataset.zip'
path = download(url, './', kind="zip", replace=True)
from mindspore.dataset import FashionMnistDataset
image_size = 28
channels = 1
batch_size = 2
fashion_mnist_dataset_dir = "./dataset"
dataset = FashionMnistDataset(dataset_dir=fashion_mnist_dataset_dir, usage="train",
num_parallel_workers=cpu_count(), shuffle=True,
num_shards=1, shard_id=0, num_samples=4000)
transforms = [
RandomHorizontalFlip(),
ToTensor(),
lambda t: (t * 2) - 1
]
dataset = dataset.project('image')
dataset = dataset.shuffle(64)
dataset = dataset.map(transforms, 'image')
dataset = dataset.batch(2, drop_remainder=True)
采样
def p_sample(model, x, t, t_index):
betas_t = extract(betas, t, x.shape)
sqrt_one_minus_alphas_cumprod_t = extract(
sqrt_one_minus_alphas_cumprod, t, x.shape
)
sqrt_recip_alphas_t = extract(sqrt_recip_alphas, t, x.shape)
model_mean = sqrt_recip_alphas_t * (x - betas_t * model(x, t) / sqrt_one_minus_alphas_cumprod_t)
if t_index == 0:
return model_mean
posterior_variance_t = extract(posterior_variance, t, x.shape)
noise = randn_like(x)
return model_mean + ops.sqrt(posterior_variance_t) * noise
def p_sample_loop(model, shape):
b = shape[0]
# 从纯噪声开始
img = randn(shape, dtype=None)
imgs = []
for i in tqdm(reversed(range(0, timesteps)), desc='sampling loop time step', total=timesteps):
img = p_sample(model, img, ms.numpy.full((b,), i, dtype=mstype.int32), i)
imgs.append(img.asnumpy())
return imgs
def sample(model, image_size, batch_size=16, channels=3):
return p_sample_loop(model, shape=(batch_size, channels, image_size, image_size))
训练过程
# 定义动态学习率
lr = nn.cosine_decay_lr(min_lr=1e-7, max_lr=1e-4, total_step=1*2000, step_per_epoch=2000, decay_epoch=1)
# 定义 Unet模型
unet_model = Unet(
dim=image_size,
channels=channels,
dim_mults=(1, 2, 4,)
)
name_list = []
for (name, par) in list(unet_model.parameters_and_names()):
name_list.append(name)
i = 0
for item in list(unet_model.trainable_params()):
item.name = name_list[i]
i += 1
# 定义优化器
optimizer = nn.Adam(unet_model.trainable_params(), learning_rate=lr)
loss_scaler = DynamicLossScaler(65536, 2, 1000)
# 定义前向过程
def forward_fn(data, t, noise=None):
loss = p_losses(unet_model, data, t, noise)
return loss
# 计算梯度
grad_fn = ms.value_and_grad(forward_fn, None, optimizer.parameters, has_aux=False)
# 梯度更新
def train_step(data, t, noise):
loss, grads = grad_fn(data, t, noise)
optimizer(grads)
return loss
import time
# 由于时间问题和内存问题,在 CPU 环境下 epoch 设置为 1,可以根据需求进行调整。建议在 Ascend/GPU 环境体验该教程。
epochs = 1
for epoch in range(epochs):
begin_time = time.time()
for step, batch in enumerate(dataset.create_tuple_iterator()):
unet_model.set_train()
batch_size = batch[0].shape[0]
t = randint(0, timesteps, (batch_size,), dtype=ms.int32)
noise = randn_like(batch[0])
loss = train_step(batch[0], t, noise)
if step % 100 == 0:
print(" epoch: ", epoch, " step: ", step, " Loss: ", loss)
end_time = time.time()
times = end_time - begin_time
print("training time:", times, "s")
# 展示随机采样效果
unet_model.set_train(False)
samples = sample(unet_model, image_size=image_size, batch_size=64, channels=channels)
plt.imshow(samples[-1][5].reshape(image_size, image_size, channels), cmap="gray")
print("Training Success!")
推理过程(从模型中采样)
# 采样64个图片
unet_model.set_train(False)
samples = sample(unet_model, image_size=image_size, batch_size=64, channels=channels)
# 展示一个随机效果
random_index = 5
plt.imshow(samples[-1][random_index].reshape(image_size, image_size, channels), cmap="gray")
结果
学习心得:
扩散模型的训练过程是通过多个步骤逐渐向图片增加噪点,直到图片变成完全无结构的噪点图片,然后在生成图片的时候,基于一张完全噪点的图片,逐步减少噪点,直到还原出一张清晰的图片而文本模型,比如 GPT-4 则是 Transformer 模型。Sora 则是一个融合了两者的 Diffusion Transformer 模型。
GPT-4 像是通过学习文本的语法规则,从而预测序列中的下一个词。在文本预测生成中,基本单位是 Token,Token 很好理解,就是一个单词或者单词的一部分而像 Sora 这样的 Diffusion Transformer 模型则像是在学习物理学——宇宙的语法,从而预测视频的下一段内容。OpenAI 把 Sora 看做“世界模拟器”的第一步,能够用文本提示词来模拟任何现实中的场景。