区分stable diffusion中的通道数与张量维度 - ToB企服应用市场:ToB评测及商务社交产业平台

# This code copyed from diffusers.pipline_controlnet_img2img.py
# 6. Prepare latent variables
latents = self.prepare_latents(
image,
latent_timestep,
batch_size,
num_images_per_prompt,
prompt_embeds.dtype,
device,
generator,
)

复制代码

# Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_latents
def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
if isinstance(generator, list) and len(generator) != batch_size:
raise ValueError(
f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
f" size of {batch_size}. Make sure the batch size matches the length of the generators."
)
if latents is None:
latents = randn_tensor(shape, generator=generator, device=device, dtype=dtype)
else:
latents = latents.to(device)
# scale the initial noise by the standard deviation required by the scheduler
latents = latents * self.scheduler.init_noise_sigma
return latents

复制代码

# Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_img2img.StableDiffusionImg2ImgPipeline.prepare_latents
def prepare_latents(self, image, timestep, batch_size, num_images_per_prompt, dtype, device, generator=None):
if not isinstance(image, (torch.Tensor, PIL.Image.Image, list)):
raise ValueError(
f"`image` has to be of type `torch.Tensor`, `PIL.Image.Image` or list but is {type(image)}"
)
image = image.to(device=device, dtype=dtype)
batch_size = batch_size * num_images_per_prompt
if image.shape[1] == 4:
init_latents = image
else:
if isinstance(generator, list) and len(generator) != batch_size:
raise ValueError(
f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
f" size of {batch_size}. Make sure the batch size matches the length of the generators."
)
elif isinstance(generator, list):
init_latents = [
self.vae.encode(image[i : i + 1]).latent_dist.sample(generator[i]) for i in range(batch_size)
]
init_latents = torch.cat(init_latents, dim=0)
else:
init_latents = self.vae.encode(image).latent_dist.sample(generator)
init_latents = self.vae.config.scaling_factor * init_latents
if batch_size > init_latents.shape[0] and batch_size % init_latents.shape[0] == 0:
# expand init_latents for batch_size
deprecation_message = (
f"You have passed {batch_size} text prompts (`prompt`), but only {init_latents.shape[0]} initial"
" images (`image`). Initial images are now duplicating to match the number of text prompts. Note"
" that this behavior is deprecated and will be removed in a version 1.0.0. Please make sure to update"
" your script to pass as many initial images as text prompts to suppress this warning."
)
deprecate("len(prompt) != len(image)", "1.0.0", deprecation_message, standard_warn=False)
additional_image_per_prompt = batch_size // init_latents.shape[0]
init_latents = torch.cat([init_latents] * additional_image_per_prompt, dim=0)
elif batch_size > init_latents.shape[0] and batch_size % init_latents.shape[0] != 0:
raise ValueError(
f"Cannot duplicate `image` of batch size {init_latents.shape[0]} to {batch_size} text prompts."
)
else:
init_latents = torch.cat([init_latents], dim=0)
shape = init_latents.shape
noise = randn_tensor(shape, generator=generator, device=device, dtype=dtype)
# get latents
init_latents = self.scheduler.add_noise(init_latents, noise, timestep)
latents = init_latents
return latents

复制代码

new_map = texture.permute(1, 2, 0)
RuntimeError: permute(sparse_coo): number of dimensions in the tensor input does not match the length of the desired ordering of dimensions i.e. input.dim() = 4 is not equal to len(dims) = 3

复制代码

print("sample:", sample.shape)
print("sample:", sample[0].shape)
print("sample:", sample[0][0].shape)

复制代码

>>
sample: torch.Size([10, 4, 96, 96])
sample: torch.Size([4, 96, 96])
sample: torch.Size([96, 96])

复制代码

# sample: torch.Size([10, 4, 96, 96])
views = [view for view in sample]
print("views:", views.shape)

复制代码

>>AttributeError: 'list' object has no attribute 'shape'

复制代码

print("views:", views[0].shape)

复制代码

>>views: torch.Size([4, 96, 96])

复制代码

# 方法二
for i, view in enumerate(prev_views):
pred_prev_sample[i] = view

复制代码

# 定义一个Python列表
my_list = [1, 2, 3, 4, 5]
# 将Python列表转换为PyTorch张量
my_tensor = torch.tensor(my_list)
print(my_tensor)

复制代码

>>tensor([1, 2, 3, 4, 5])

复制代码

# 假设你有一个包含多个张量的列表
tensor_list = [torch.tensor([1, 2, 3]), torch.tensor([4, 5, 6]), torch.tensor([7, 8, 9])]
# 使用torch.stack将它们堆叠成一个新的张量
stacked_tensor = torch.stack(tensor_list)
print(stacked_tensor)

复制代码

>>tensor([[1, 2, 3],
[4, 5, 6],
[7, 8, 9]])

复制代码

# 默认情况下，它在新的维度（即0维）上堆叠这些张量。
# views is a list,and views[0].shape is ([4, 96, 96]).
views = torch.stack(views, axis=0) # ([10, 4, 96, 96])

复制代码

import torch
# 假设你有一个包含多个张量的列表
tensor_list = [torch.tensor([1, 2, 3]), torch.tensor([4, 5, 6]), torch.tensor([7, 8, 9])]
# 使用 torch.cat 将张量沿着现有维度拼接
concatenated_tensor = torch.cat(tensor_list, dim=0)
# 使用 torch.unsqueeze 在新的维度上增加维度
stacked_tensor = torch.unsqueeze(concatenated_tensor, dim=0)

复制代码