mirror of
https://github.com/storytold/storyteller-ml.git
synced 2026-10-22 08:16:08 +00:00
Add SadTalker @ ae0b26359d44c9379450a8e02a38b45eeec15549
MIT license Commit: https://github.com/OpenTalker/SadTalker commit ae0b26359d44c9379450a8e02a38b45eeec15549 (HEAD -> main, origin/main, origin/HEAD) Author: shadowcun <shadowcun@tencent.com> Date: Mon Jul 3 13:48:35 2023 +0800 fixed bug: hacking facexlib of FAN
This commit is contained in:
Brandon Thomas
@@ -0,0 +1,208 @@
|
||||
"""This script contains basic utilities for Deep3DFaceRecon_pytorch
|
||||
"""
|
||||
from __future__ import print_function
|
||||
import numpy as np
|
||||
import torch
|
||||
from PIL import Image
|
||||
import os
|
||||
import importlib
|
||||
import argparse
|
||||
from argparse import Namespace
|
||||
import torchvision
|
||||
|
||||
|
||||
def str2bool(v):
|
||||
if isinstance(v, bool):
|
||||
return v
|
||||
if v.lower() in ('yes', 'true', 't', 'y', '1'):
|
||||
return True
|
||||
elif v.lower() in ('no', 'false', 'f', 'n', '0'):
|
||||
return False
|
||||
else:
|
||||
raise argparse.ArgumentTypeError('Boolean value expected.')
|
||||
|
||||
|
||||
def copyconf(default_opt, **kwargs):
|
||||
conf = Namespace(**vars(default_opt))
|
||||
for key in kwargs:
|
||||
setattr(conf, key, kwargs[key])
|
||||
return conf
|
||||
|
||||
def genvalconf(train_opt, **kwargs):
|
||||
conf = Namespace(**vars(train_opt))
|
||||
attr_dict = train_opt.__dict__
|
||||
for key, value in attr_dict.items():
|
||||
if 'val' in key and key.split('_')[0] in attr_dict:
|
||||
setattr(conf, key.split('_')[0], value)
|
||||
|
||||
for key in kwargs:
|
||||
setattr(conf, key, kwargs[key])
|
||||
|
||||
return conf
|
||||
|
||||
def find_class_in_module(target_cls_name, module):
|
||||
target_cls_name = target_cls_name.replace('_', '').lower()
|
||||
clslib = importlib.import_module(module)
|
||||
cls = None
|
||||
for name, clsobj in clslib.__dict__.items():
|
||||
if name.lower() == target_cls_name:
|
||||
cls = clsobj
|
||||
|
||||
assert cls is not None, "In %s, there should be a class whose name matches %s in lowercase without underscore(_)" % (module, target_cls_name)
|
||||
|
||||
return cls
|
||||
|
||||
|
||||
def tensor2im(input_image, imtype=np.uint8):
|
||||
""""Converts a Tensor array into a numpy image array.
|
||||
|
||||
Parameters:
|
||||
input_image (tensor) -- the input image tensor array, range(0, 1)
|
||||
imtype (type) -- the desired type of the converted numpy array
|
||||
"""
|
||||
if not isinstance(input_image, np.ndarray):
|
||||
if isinstance(input_image, torch.Tensor): # get the data from a variable
|
||||
image_tensor = input_image.data
|
||||
else:
|
||||
return input_image
|
||||
image_numpy = image_tensor.clamp(0.0, 1.0).cpu().float().numpy() # convert it into a numpy array
|
||||
if image_numpy.shape[0] == 1: # grayscale to RGB
|
||||
image_numpy = np.tile(image_numpy, (3, 1, 1))
|
||||
image_numpy = np.transpose(image_numpy, (1, 2, 0)) * 255.0 # post-processing: tranpose and scaling
|
||||
else: # if it is a numpy array, do nothing
|
||||
image_numpy = input_image
|
||||
return image_numpy.astype(imtype)
|
||||
|
||||
|
||||
def diagnose_network(net, name='network'):
|
||||
"""Calculate and print the mean of average absolute(gradients)
|
||||
|
||||
Parameters:
|
||||
net (torch network) -- Torch network
|
||||
name (str) -- the name of the network
|
||||
"""
|
||||
mean = 0.0
|
||||
count = 0
|
||||
for param in net.parameters():
|
||||
if param.grad is not None:
|
||||
mean += torch.mean(torch.abs(param.grad.data))
|
||||
count += 1
|
||||
if count > 0:
|
||||
mean = mean / count
|
||||
print(name)
|
||||
print(mean)
|
||||
|
||||
|
||||
def save_image(image_numpy, image_path, aspect_ratio=1.0):
|
||||
"""Save a numpy image to the disk
|
||||
|
||||
Parameters:
|
||||
image_numpy (numpy array) -- input numpy array
|
||||
image_path (str) -- the path of the image
|
||||
"""
|
||||
|
||||
image_pil = Image.fromarray(image_numpy)
|
||||
h, w, _ = image_numpy.shape
|
||||
|
||||
if aspect_ratio is None:
|
||||
pass
|
||||
elif aspect_ratio > 1.0:
|
||||
image_pil = image_pil.resize((h, int(w * aspect_ratio)), Image.BICUBIC)
|
||||
elif aspect_ratio < 1.0:
|
||||
image_pil = image_pil.resize((int(h / aspect_ratio), w), Image.BICUBIC)
|
||||
image_pil.save(image_path)
|
||||
|
||||
|
||||
def print_numpy(x, val=True, shp=False):
|
||||
"""Print the mean, min, max, median, std, and size of a numpy array
|
||||
|
||||
Parameters:
|
||||
val (bool) -- if print the values of the numpy array
|
||||
shp (bool) -- if print the shape of the numpy array
|
||||
"""
|
||||
x = x.astype(np.float64)
|
||||
if shp:
|
||||
print('shape,', x.shape)
|
||||
if val:
|
||||
x = x.flatten()
|
||||
print('mean = %3.3f, min = %3.3f, max = %3.3f, median = %3.3f, std=%3.3f' % (
|
||||
np.mean(x), np.min(x), np.max(x), np.median(x), np.std(x)))
|
||||
|
||||
|
||||
def mkdirs(paths):
|
||||
"""create empty directories if they don't exist
|
||||
|
||||
Parameters:
|
||||
paths (str list) -- a list of directory paths
|
||||
"""
|
||||
if isinstance(paths, list) and not isinstance(paths, str):
|
||||
for path in paths:
|
||||
mkdir(path)
|
||||
else:
|
||||
mkdir(paths)
|
||||
|
||||
|
||||
def mkdir(path):
|
||||
"""create a single empty directory if it didn't exist
|
||||
|
||||
Parameters:
|
||||
path (str) -- a single directory path
|
||||
"""
|
||||
if not os.path.exists(path):
|
||||
os.makedirs(path)
|
||||
|
||||
|
||||
def correct_resize_label(t, size):
|
||||
device = t.device
|
||||
t = t.detach().cpu()
|
||||
resized = []
|
||||
for i in range(t.size(0)):
|
||||
one_t = t[i, :1]
|
||||
one_np = np.transpose(one_t.numpy().astype(np.uint8), (1, 2, 0))
|
||||
one_np = one_np[:, :, 0]
|
||||
one_image = Image.fromarray(one_np).resize(size, Image.NEAREST)
|
||||
resized_t = torch.from_numpy(np.array(one_image)).long()
|
||||
resized.append(resized_t)
|
||||
return torch.stack(resized, dim=0).to(device)
|
||||
|
||||
|
||||
def correct_resize(t, size, mode=Image.BICUBIC):
|
||||
device = t.device
|
||||
t = t.detach().cpu()
|
||||
resized = []
|
||||
for i in range(t.size(0)):
|
||||
one_t = t[i:i + 1]
|
||||
one_image = Image.fromarray(tensor2im(one_t)).resize(size, Image.BICUBIC)
|
||||
resized_t = torchvision.transforms.functional.to_tensor(one_image) * 2 - 1.0
|
||||
resized.append(resized_t)
|
||||
return torch.stack(resized, dim=0).to(device)
|
||||
|
||||
def draw_landmarks(img, landmark, color='r', step=2):
|
||||
"""
|
||||
Return:
|
||||
img -- numpy.array, (B, H, W, 3) img with landmark, RGB order, range (0, 255)
|
||||
|
||||
|
||||
Parameters:
|
||||
img -- numpy.array, (B, H, W, 3), RGB order, range (0, 255)
|
||||
landmark -- numpy.array, (B, 68, 2), y direction is opposite to v direction
|
||||
color -- str, 'r' or 'b' (red or blue)
|
||||
"""
|
||||
if color =='r':
|
||||
c = np.array([255., 0, 0])
|
||||
else:
|
||||
c = np.array([0, 0, 255.])
|
||||
|
||||
_, H, W, _ = img.shape
|
||||
img, landmark = img.copy(), landmark.copy()
|
||||
landmark[..., 1] = H - 1 - landmark[..., 1]
|
||||
landmark = np.round(landmark).astype(np.int32)
|
||||
for i in range(landmark.shape[1]):
|
||||
x, y = landmark[:, i, 0], landmark[:, i, 1]
|
||||
for j in range(-step, step):
|
||||
for k in range(-step, step):
|
||||
u = np.clip(x + j, 0, W - 1)
|
||||
v = np.clip(y + k, 0, H - 1)
|
||||
for m in range(landmark.shape[0]):
|
||||
img[m, v[m], u[m]] = c
|
||||
return img
|
||||
Reference in New Issue
Block a user