mirror of
https://github.com/Stability-AI/stablediffusion.git
synced 2024-12-22 23:55:00 +00:00
Fix typos
Found via `codespell -L therefrom,siz` and `typos --format brief`.
This commit is contained in:
parent
c12d960d1e
commit
5576aee1b0
11 changed files with 25 additions and 25 deletions
|
@ -233,7 +233,7 @@ class PLMSSampler(object):
|
||||||
# 2nd order Pseudo Linear Multistep (Adams-Bashforth)
|
# 2nd order Pseudo Linear Multistep (Adams-Bashforth)
|
||||||
e_t_prime = (3 * e_t - old_eps[-1]) / 2
|
e_t_prime = (3 * e_t - old_eps[-1]) / 2
|
||||||
elif len(old_eps) == 2:
|
elif len(old_eps) == 2:
|
||||||
# 3nd order Pseudo Linear Multistep (Adams-Bashforth)
|
# 3rd order Pseudo Linear Multistep (Adams-Bashforth)
|
||||||
e_t_prime = (23 * e_t - 16 * old_eps[-1] + 5 * old_eps[-2]) / 12
|
e_t_prime = (23 * e_t - 16 * old_eps[-1] + 5 * old_eps[-2]) / 12
|
||||||
elif len(old_eps) >= 3:
|
elif len(old_eps) >= 3:
|
||||||
# 4nd order Pseudo Linear Multistep (Adams-Bashforth)
|
# 4nd order Pseudo Linear Multistep (Adams-Bashforth)
|
||||||
|
|
|
@ -12,9 +12,9 @@ from ldm.modules.diffusionmodules.util import checkpoint
|
||||||
try:
|
try:
|
||||||
import xformers
|
import xformers
|
||||||
import xformers.ops
|
import xformers.ops
|
||||||
XFORMERS_IS_AVAILBLE = True
|
XFORMERS_IS_AVAILABLE = True
|
||||||
except:
|
except:
|
||||||
XFORMERS_IS_AVAILBLE = False
|
XFORMERS_IS_AVAILABLE = False
|
||||||
|
|
||||||
# CrossAttn precision handling
|
# CrossAttn precision handling
|
||||||
import os
|
import os
|
||||||
|
@ -251,7 +251,7 @@ class BasicTransformerBlock(nn.Module):
|
||||||
def __init__(self, dim, n_heads, d_head, dropout=0., context_dim=None, gated_ff=True, checkpoint=True,
|
def __init__(self, dim, n_heads, d_head, dropout=0., context_dim=None, gated_ff=True, checkpoint=True,
|
||||||
disable_self_attn=False):
|
disable_self_attn=False):
|
||||||
super().__init__()
|
super().__init__()
|
||||||
attn_mode = "softmax-xformers" if XFORMERS_IS_AVAILBLE else "softmax"
|
attn_mode = "softmax-xformers" if XFORMERS_IS_AVAILABLE else "softmax"
|
||||||
assert attn_mode in self.ATTENTION_MODES
|
assert attn_mode in self.ATTENTION_MODES
|
||||||
attn_cls = self.ATTENTION_MODES[attn_mode]
|
attn_cls = self.ATTENTION_MODES[attn_mode]
|
||||||
self.disable_self_attn = disable_self_attn
|
self.disable_self_attn = disable_self_attn
|
||||||
|
|
|
@ -11,9 +11,9 @@ from ldm.modules.attention import MemoryEfficientCrossAttention
|
||||||
try:
|
try:
|
||||||
import xformers
|
import xformers
|
||||||
import xformers.ops
|
import xformers.ops
|
||||||
XFORMERS_IS_AVAILBLE = True
|
XFORMERS_IS_AVAILABLE = True
|
||||||
except:
|
except:
|
||||||
XFORMERS_IS_AVAILBLE = False
|
XFORMERS_IS_AVAILABLE = False
|
||||||
print("No module 'xformers'. Proceeding without it.")
|
print("No module 'xformers'. Proceeding without it.")
|
||||||
|
|
||||||
|
|
||||||
|
@ -279,7 +279,7 @@ class MemoryEfficientCrossAttentionWrapper(MemoryEfficientCrossAttention):
|
||||||
|
|
||||||
def make_attn(in_channels, attn_type="vanilla", attn_kwargs=None):
|
def make_attn(in_channels, attn_type="vanilla", attn_kwargs=None):
|
||||||
assert attn_type in ["vanilla", "vanilla-xformers", "memory-efficient-cross-attn", "linear", "none"], f'attn_type {attn_type} unknown'
|
assert attn_type in ["vanilla", "vanilla-xformers", "memory-efficient-cross-attn", "linear", "none"], f'attn_type {attn_type} unknown'
|
||||||
if XFORMERS_IS_AVAILBLE and attn_type == "vanilla":
|
if XFORMERS_IS_AVAILABLE and attn_type == "vanilla":
|
||||||
attn_type = "vanilla-xformers"
|
attn_type = "vanilla-xformers"
|
||||||
print(f"making attention of type '{attn_type}' with {in_channels} in_channels")
|
print(f"making attention of type '{attn_type}' with {in_channels} in_channels")
|
||||||
if attn_type == "vanilla":
|
if attn_type == "vanilla":
|
||||||
|
|
|
@ -345,7 +345,7 @@ def count_flops_attn(model, _x, y):
|
||||||
|
|
||||||
class QKVAttentionLegacy(nn.Module):
|
class QKVAttentionLegacy(nn.Module):
|
||||||
"""
|
"""
|
||||||
A module which performs QKV attention. Matches legacy QKVAttention + input/ouput heads shaping
|
A module which performs QKV attention. Matches legacy QKVAttention + input/output heads shaping
|
||||||
"""
|
"""
|
||||||
|
|
||||||
def __init__(self, n_heads):
|
def __init__(self, n_heads):
|
||||||
|
|
|
@ -3,14 +3,14 @@ from torch import nn
|
||||||
|
|
||||||
|
|
||||||
class LitEma(nn.Module):
|
class LitEma(nn.Module):
|
||||||
def __init__(self, model, decay=0.9999, use_num_upates=True):
|
def __init__(self, model, decay=0.9999, use_num_updates=True):
|
||||||
super().__init__()
|
super().__init__()
|
||||||
if decay < 0.0 or decay > 1.0:
|
if decay < 0.0 or decay > 1.0:
|
||||||
raise ValueError('Decay must be between 0 and 1')
|
raise ValueError('Decay must be between 0 and 1')
|
||||||
|
|
||||||
self.m_name2s_name = {}
|
self.m_name2s_name = {}
|
||||||
self.register_buffer('decay', torch.tensor(decay, dtype=torch.float32))
|
self.register_buffer('decay', torch.tensor(decay, dtype=torch.float32))
|
||||||
self.register_buffer('num_updates', torch.tensor(0, dtype=torch.int) if use_num_upates
|
self.register_buffer('num_updates', torch.tensor(0, dtype=torch.int) if use_num_updates
|
||||||
else torch.tensor(-1, dtype=torch.int))
|
else torch.tensor(-1, dtype=torch.int))
|
||||||
|
|
||||||
for name, p in model.named_parameters():
|
for name, p in model.named_parameters():
|
||||||
|
|
|
@ -170,7 +170,7 @@ def gen_kernel(k_size=np.array([15, 15]), scale_factor=np.array([4, 4]), min_var
|
||||||
[X, Y] = np.meshgrid(range(k_size[0]), range(k_size[1]))
|
[X, Y] = np.meshgrid(range(k_size[0]), range(k_size[1]))
|
||||||
Z = np.stack([X, Y], 2)[:, :, :, None]
|
Z = np.stack([X, Y], 2)[:, :, :, None]
|
||||||
|
|
||||||
# Calcualte Gaussian for every pixel of the kernel
|
# Calculate Gaussian for every pixel of the kernel
|
||||||
ZZ = Z - MU
|
ZZ = Z - MU
|
||||||
ZZ_t = ZZ.transpose(0, 1, 3, 2)
|
ZZ_t = ZZ.transpose(0, 1, 3, 2)
|
||||||
raw_kernel = np.exp(-0.5 * np.squeeze(ZZ_t @ INV_SIGMA @ ZZ)) * (1 + noise)
|
raw_kernel = np.exp(-0.5 * np.squeeze(ZZ_t @ INV_SIGMA @ ZZ)) * (1 + noise)
|
||||||
|
|
|
@ -169,7 +169,7 @@ def gen_kernel(k_size=np.array([15, 15]), scale_factor=np.array([4, 4]), min_var
|
||||||
[X, Y] = np.meshgrid(range(k_size[0]), range(k_size[1]))
|
[X, Y] = np.meshgrid(range(k_size[0]), range(k_size[1]))
|
||||||
Z = np.stack([X, Y], 2)[:, :, :, None]
|
Z = np.stack([X, Y], 2)[:, :, :, None]
|
||||||
|
|
||||||
# Calcualte Gaussian for every pixel of the kernel
|
# Calculate Gaussian for every pixel of the kernel
|
||||||
ZZ = Z - MU
|
ZZ = Z - MU
|
||||||
ZZ_t = ZZ.transpose(0, 1, 3, 2)
|
ZZ_t = ZZ.transpose(0, 1, 3, 2)
|
||||||
raw_kernel = np.exp(-0.5 * np.squeeze(ZZ_t @ INV_SIGMA @ ZZ)) * (1 + noise)
|
raw_kernel = np.exp(-0.5 * np.squeeze(ZZ_t @ INV_SIGMA @ ZZ)) * (1 + noise)
|
||||||
|
|
|
@ -59,7 +59,7 @@ def surf(Z, cmap='rainbow', figsize=None):
|
||||||
|
|
||||||
'''
|
'''
|
||||||
# --------------------------------------------
|
# --------------------------------------------
|
||||||
# get image pathes
|
# get image paths
|
||||||
# --------------------------------------------
|
# --------------------------------------------
|
||||||
'''
|
'''
|
||||||
|
|
||||||
|
@ -122,14 +122,14 @@ def imssave(imgs, img_path):
|
||||||
cv2.imwrite(new_path, img)
|
cv2.imwrite(new_path, img)
|
||||||
|
|
||||||
|
|
||||||
def split_imageset(original_dataroot, taget_dataroot, n_channels=3, p_size=800, p_overlap=96, p_max=1000):
|
def split_imageset(original_dataroot, target_dataroot, n_channels=3, p_size=800, p_overlap=96, p_max=1000):
|
||||||
"""
|
"""
|
||||||
split the large images from original_dataroot into small overlapped images with size (p_size)x(p_size),
|
split the large images from original_dataroot into small overlapped images with size (p_size)x(p_size),
|
||||||
and save them into taget_dataroot; only the images with larger size than (p_max)x(p_max)
|
and save them into target_dataroot; only the images with larger size than (p_max)x(p_max)
|
||||||
will be splitted.
|
will be split.
|
||||||
Args:
|
Args:
|
||||||
original_dataroot:
|
original_dataroot:
|
||||||
taget_dataroot:
|
target_dataroot:
|
||||||
p_size: size of small images
|
p_size: size of small images
|
||||||
p_overlap: patch size in training is a good choice
|
p_overlap: patch size in training is a good choice
|
||||||
p_max: images with smaller size than (p_max)x(p_max) keep unchanged.
|
p_max: images with smaller size than (p_max)x(p_max) keep unchanged.
|
||||||
|
@ -139,8 +139,8 @@ def split_imageset(original_dataroot, taget_dataroot, n_channels=3, p_size=800,
|
||||||
# img_name, ext = os.path.splitext(os.path.basename(img_path))
|
# img_name, ext = os.path.splitext(os.path.basename(img_path))
|
||||||
img = imread_uint(img_path, n_channels=n_channels)
|
img = imread_uint(img_path, n_channels=n_channels)
|
||||||
patches = patches_from_image(img, p_size, p_overlap, p_max)
|
patches = patches_from_image(img, p_size, p_overlap, p_max)
|
||||||
imssave(patches, os.path.join(taget_dataroot,os.path.basename(img_path)))
|
imssave(patches, os.path.join(target_dataroot,os.path.basename(img_path)))
|
||||||
#if original_dataroot == taget_dataroot:
|
#if original_dataroot == target_dataroot:
|
||||||
#del img_path
|
#del img_path
|
||||||
|
|
||||||
'''
|
'''
|
||||||
|
@ -180,7 +180,7 @@ def mkdir_and_rename(path):
|
||||||
|
|
||||||
|
|
||||||
# --------------------------------------------
|
# --------------------------------------------
|
||||||
# get uint8 image of size HxWxn_channles (RGB)
|
# get uint8 image of size HxWxn_channels (RGB)
|
||||||
# --------------------------------------------
|
# --------------------------------------------
|
||||||
def imread_uint(path, n_channels=3):
|
def imread_uint(path, n_channels=3):
|
||||||
# input: path
|
# input: path
|
||||||
|
@ -215,7 +215,7 @@ def imwrite(img, img_path):
|
||||||
|
|
||||||
|
|
||||||
# --------------------------------------------
|
# --------------------------------------------
|
||||||
# get single image of size HxWxn_channles (BGR)
|
# get single image of size HxWxn_channels (BGR)
|
||||||
# --------------------------------------------
|
# --------------------------------------------
|
||||||
def read_img(path):
|
def read_img(path):
|
||||||
# read image by cv2
|
# read image by cv2
|
||||||
|
|
|
@ -125,7 +125,7 @@ class Resize(object):
|
||||||
# fit height
|
# fit height
|
||||||
scale_width = scale_height
|
scale_width = scale_height
|
||||||
elif self.__resize_method == "minimal":
|
elif self.__resize_method == "minimal":
|
||||||
# scale as least as possbile
|
# scale as least as possible
|
||||||
if abs(1 - scale_width) < abs(1 - scale_height):
|
if abs(1 - scale_width) < abs(1 - scale_height):
|
||||||
# fit width
|
# fit width
|
||||||
scale_height = scale_width
|
scale_height = scale_width
|
||||||
|
|
|
@ -23,7 +23,7 @@ def log_txt_as_img(wh, xc, size=10):
|
||||||
try:
|
try:
|
||||||
draw.text((0, 0), lines, fill="black", font=font)
|
draw.text((0, 0), lines, fill="black", font=font)
|
||||||
except UnicodeEncodeError:
|
except UnicodeEncodeError:
|
||||||
print("Cant encode string for logging. Skipping.")
|
print("Can't encode string for logging. Skipping.")
|
||||||
|
|
||||||
txt = np.array(txt).transpose(2, 0, 1) / 127.5 - 1.0
|
txt = np.array(txt).transpose(2, 0, 1) / 127.5 - 1.0
|
||||||
txts.append(txt)
|
txts.append(txt)
|
||||||
|
|
Loading…
Reference in a new issue