Python實(shí)現(xiàn)GIF動(dòng)圖以及視頻卡通化詳解
前言
我繼續(xù)魔改一下,讓該模型可以支持將gif動(dòng)圖或者視頻,也做成卡通化效果。畢竟一張圖可以那就帶邊視頻也可以,沒毛病。所以繼給次元壁來了一拳,我在加兩腳。
項(xiàng)目github地址:github地址
環(huán)境依賴
除了參考文章中的依賴,還需要加一些其他依賴,requirements.txt如下:

其他環(huán)境不太清楚的,可以看我前言鏈接地址的文章,有具體說明。
核心代碼
不廢話了,先上gif代碼。
gif動(dòng)圖卡通化
實(shí)現(xiàn)代碼如下:
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time : 2021/12/5 18:10
# @Author : 劍客阿良_ALiang
# @Site :
# @File : gif_cartoon_tool.py
# !/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time : 2021/12/5 0:26
# @Author : 劍客阿良_ALiang
# @Site :
# @File : video_cartoon_tool.py
# !/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time : 2021/12/4 22:34
# @Author : 劍客阿良_ALiang
# @Site :
# @File : image_cartoon_tool.py
from PIL import Image, ImageEnhance, ImageSequence
import torch
from torchvision.transforms.functional import to_tensor, to_pil_image
from torch import nn
import os
import torch.nn.functional as F
import uuid
import imageio
# -------------------------- hy add 01 --------------------------
class ConvNormLReLU(nn.Sequential):
def __init__(self, in_ch, out_ch, kernel_size=3, stride=1, padding=1, pad_mode="reflect", groups=1, bias=False):
pad_layer = {
"zero": nn.ZeroPad2d,
"same": nn.ReplicationPad2d,
"reflect": nn.ReflectionPad2d,
}
if pad_mode not in pad_layer:
raise NotImplementedError
super(ConvNormLReLU, self).__init__(
pad_layer[pad_mode](padding),
nn.Conv2d(in_ch, out_ch, kernel_size=kernel_size, stride=stride, padding=0, groups=groups, bias=bias),
nn.GroupNorm(num_groups=1, num_channels=out_ch, affine=True),
nn.LeakyReLU(0.2, inplace=True)
)
class InvertedResBlock(nn.Module):
def __init__(self, in_ch, out_ch, expansion_ratio=2):
super(InvertedResBlock, self).__init__()
self.use_res_connect = in_ch == out_ch
bottleneck = int(round(in_ch * expansion_ratio))
layers = []
if expansion_ratio != 1:
layers.append(ConvNormLReLU(in_ch, bottleneck, kernel_size=1, padding=0))
# dw
layers.append(ConvNormLReLU(bottleneck, bottleneck, groups=bottleneck, bias=True))
# pw
layers.append(nn.Conv2d(bottleneck, out_ch, kernel_size=1, padding=0, bias=False))
layers.append(nn.GroupNorm(num_groups=1, num_channels=out_ch, affine=True))
self.layers = nn.Sequential(*layers)
def forward(self, input):
out = self.layers(input)
if self.use_res_connect:
out = input + out
return out
class Generator(nn.Module):
def __init__(self, ):
super().__init__()
self.block_a = nn.Sequential(
ConvNormLReLU(3, 32, kernel_size=7, padding=3),
ConvNormLReLU(32, 64, stride=2, padding=(0, 1, 0, 1)),
ConvNormLReLU(64, 64)
)
self.block_b = nn.Sequential(
ConvNormLReLU(64, 128, stride=2, padding=(0, 1, 0, 1)),
ConvNormLReLU(128, 128)
)
self.block_c = nn.Sequential(
ConvNormLReLU(128, 128),
InvertedResBlock(128, 256, 2),
InvertedResBlock(256, 256, 2),
InvertedResBlock(256, 256, 2),
InvertedResBlock(256, 256, 2),
ConvNormLReLU(256, 128),
)
self.block_d = nn.Sequential(
ConvNormLReLU(128, 128),
ConvNormLReLU(128, 128)
)
self.block_e = nn.Sequential(
ConvNormLReLU(128, 64),
ConvNormLReLU(64, 64),
ConvNormLReLU(64, 32, kernel_size=7, padding=3)
)
self.out_layer = nn.Sequential(
nn.Conv2d(32, 3, kernel_size=1, stride=1, padding=0, bias=False),
nn.Tanh()
)
def forward(self, input, align_corners=True):
out = self.block_a(input)
half_size = out.size()[-2:]
out = self.block_b(out)
out = self.block_c(out)
if align_corners:
out = F.interpolate(out, half_size, mode="bilinear", align_corners=True)
else:
out = F.interpolate(out, scale_factor=2, mode="bilinear", align_corners=False)
out = self.block_d(out)
if align_corners:
out = F.interpolate(out, input.size()[-2:], mode="bilinear", align_corners=True)
else:
out = F.interpolate(out, scale_factor=2, mode="bilinear", align_corners=False)
out = self.block_e(out)
out = self.out_layer(out)
return out
# -------------------------- hy add 02 --------------------------
def handle(gif_path: str, output_dir: str, type: int, device='cpu'):
_ext = os.path.basename(gif_path).strip().split('.')[-1]
if type == 1:
_checkpoint = './weights/paprika.pt'
elif type == 2:
_checkpoint = './weights/face_paint_512_v1.pt'
elif type == 3:
_checkpoint = './weights/face_paint_512_v2.pt'
elif type == 4:
_checkpoint = './weights/celeba_distill.pt'
else:
raise Exception('type not support')
os.makedirs(output_dir, exist_ok=True)
net = Generator()
net.load_state_dict(torch.load(_checkpoint, map_location="cpu"))
net.to(device).eval()
result = os.path.join(output_dir, '{}.{}'.format(uuid.uuid1().hex, _ext))
img = Image.open(gif_path)
out_images = []
for frame in ImageSequence.Iterator(img):
frame = frame.convert("RGB")
with torch.no_grad():
image = to_tensor(frame).unsqueeze(0) * 2 - 1
out = net(image.to(device), False).cpu()
out = out.squeeze(0).clip(-1, 1) * 0.5 + 0.5
out = to_pil_image(out)
out_images.append(out)
# out_images[0].save(result, save_all=True, loop=True, append_images=out_images[1:], duration=100)
imageio.mimsave(result, out_images, fps=15)
return result
if __name__ == '__main__':
print(handle('samples/gif/128.gif', 'samples/gif_result/', 3, 'cuda'))
代碼說明:
1、主要的handle方法入?yún)⒎謩e為:gif地址、輸出目錄、類型、設(shè)備使用(默認(rèn)cpu,可選cuda使用顯卡)。
2、類型主要是選擇模型,最好用3,人像處理更生動(dòng)一些。
執(zhí)行驗(yàn)證一下
下面是我準(zhǔn)備的gif素材

執(zhí)行結(jié)果如下

看一下效果

哈哈,有點(diǎn)意思哦。
視頻卡通化
實(shí)現(xiàn)代碼如下:
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time : 2021/12/5 0:26
# @Author : 劍客阿良_ALiang
# @Site :
# @File : video_cartoon_tool.py
# !/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time : 2021/12/4 22:34
# @Author : 劍客阿良_ALiang
# @Site :
# @File : image_cartoon_tool.py
from PIL import Image, ImageEnhance
import torch
from torchvision.transforms.functional import to_tensor, to_pil_image
from torch import nn
import os
import torch.nn.functional as F
import uuid
import cv2
import numpy as np
import time
from ffmpy import FFmpeg
# -------------------------- hy add 01 --------------------------
class ConvNormLReLU(nn.Sequential):
def __init__(self, in_ch, out_ch, kernel_size=3, stride=1, padding=1, pad_mode="reflect", groups=1, bias=False):
pad_layer = {
"zero": nn.ZeroPad2d,
"same": nn.ReplicationPad2d,
"reflect": nn.ReflectionPad2d,
}
if pad_mode not in pad_layer:
raise NotImplementedError
super(ConvNormLReLU, self).__init__(
pad_layer[pad_mode](padding),
nn.Conv2d(in_ch, out_ch, kernel_size=kernel_size, stride=stride, padding=0, groups=groups, bias=bias),
nn.GroupNorm(num_groups=1, num_channels=out_ch, affine=True),
nn.LeakyReLU(0.2, inplace=True)
)
class InvertedResBlock(nn.Module):
def __init__(self, in_ch, out_ch, expansion_ratio=2):
super(InvertedResBlock, self).__init__()
self.use_res_connect = in_ch == out_ch
bottleneck = int(round(in_ch * expansion_ratio))
layers = []
if expansion_ratio != 1:
layers.append(ConvNormLReLU(in_ch, bottleneck, kernel_size=1, padding=0))
# dw
layers.append(ConvNormLReLU(bottleneck, bottleneck, groups=bottleneck, bias=True))
# pw
layers.append(nn.Conv2d(bottleneck, out_ch, kernel_size=1, padding=0, bias=False))
layers.append(nn.GroupNorm(num_groups=1, num_channels=out_ch, affine=True))
self.layers = nn.Sequential(*layers)
def forward(self, input):
out = self.layers(input)
if self.use_res_connect:
out = input + out
return out
class Generator(nn.Module):
def __init__(self, ):
super().__init__()
self.block_a = nn.Sequential(
ConvNormLReLU(3, 32, kernel_size=7, padding=3),
ConvNormLReLU(32, 64, stride=2, padding=(0, 1, 0, 1)),
ConvNormLReLU(64, 64)
)
self.block_b = nn.Sequential(
ConvNormLReLU(64, 128, stride=2, padding=(0, 1, 0, 1)),
ConvNormLReLU(128, 128)
)
self.block_c = nn.Sequential(
ConvNormLReLU(128, 128),
InvertedResBlock(128, 256, 2),
InvertedResBlock(256, 256, 2),
InvertedResBlock(256, 256, 2),
InvertedResBlock(256, 256, 2),
ConvNormLReLU(256, 128),
)
self.block_d = nn.Sequential(
ConvNormLReLU(128, 128),
ConvNormLReLU(128, 128)
)
self.block_e = nn.Sequential(
ConvNormLReLU(128, 64),
ConvNormLReLU(64, 64),
ConvNormLReLU(64, 32, kernel_size=7, padding=3)
)
self.out_layer = nn.Sequential(
nn.Conv2d(32, 3, kernel_size=1, stride=1, padding=0, bias=False),
nn.Tanh()
)
def forward(self, input, align_corners=True):
out = self.block_a(input)
half_size = out.size()[-2:]
out = self.block_b(out)
out = self.block_c(out)
if align_corners:
out = F.interpolate(out, half_size, mode="bilinear", align_corners=True)
else:
out = F.interpolate(out, scale_factor=2, mode="bilinear", align_corners=False)
out = self.block_d(out)
if align_corners:
out = F.interpolate(out, input.size()[-2:], mode="bilinear", align_corners=True)
else:
out = F.interpolate(out, scale_factor=2, mode="bilinear", align_corners=False)
out = self.block_e(out)
out = self.out_layer(out)
return out
# -------------------------- hy add 02 --------------------------
def handle(video_path: str, output_dir: str, type: int, fps: int, device='cpu'):
_ext = os.path.basename(video_path).strip().split('.')[-1]
if type == 1:
_checkpoint = './weights/paprika.pt'
elif type == 2:
_checkpoint = './weights/face_paint_512_v1.pt'
elif type == 3:
_checkpoint = './weights/face_paint_512_v2.pt'
elif type == 4:
_checkpoint = './weights/celeba_distill.pt'
else:
raise Exception('type not support')
os.makedirs(output_dir, exist_ok=True)
# 獲取視頻音頻
_audio = extract(video_path, output_dir, 'wav')
net = Generator()
net.load_state_dict(torch.load(_checkpoint, map_location="cpu"))
net.to(device).eval()
result = os.path.join(output_dir, '{}.{}'.format(uuid.uuid1().hex, _ext))
capture = cv2.VideoCapture(video_path)
size = (int(capture.get(cv2.CAP_PROP_FRAME_WIDTH)), int(capture.get(cv2.CAP_PROP_FRAME_HEIGHT)))
print(size)
videoWriter = cv2.VideoWriter(result, cv2.VideoWriter_fourcc(*'mp4v'), fps, size)
cul = 0
with torch.no_grad():
while True:
ret, frame = capture.read()
if ret:
print(ret)
image = to_tensor(frame).unsqueeze(0) * 2 - 1
out = net(image.to(device), False).cpu()
out = out.squeeze(0).clip(-1, 1) * 0.5 + 0.5
out = to_pil_image(out)
contrast_enhancer = ImageEnhance.Contrast(out)
img_enhanced_image = contrast_enhancer.enhance(2)
enhanced_image = np.asarray(img_enhanced_image)
videoWriter.write(enhanced_image)
cul += 1
print('第{}張圖'.format(cul))
else:
break
videoWriter.release()
# 視頻添加原音頻
_final_video = video_add_audio(result, _audio, output_dir)
return _final_video
# -------------------------- hy add 03 --------------------------
def extract(video_path: str, tmp_dir: str, ext: str):
file_name = '.'.join(os.path.basename(video_path).split('.')[0:-1])
print('文件名:{},提取音頻'.format(file_name))
if ext == 'mp3':
return _run_ffmpeg(video_path, os.path.join(tmp_dir, '{}.{}'.format(uuid.uuid1().hex, ext)), 'mp3')
if ext == 'wav':
return _run_ffmpeg(video_path, os.path.join(tmp_dir, '{}.{}'.format(uuid.uuid1().hex, ext)), 'wav')
def _run_ffmpeg(video_path: str, audio_path: str, format: str):
ff = FFmpeg(inputs={video_path: None},
outputs={audio_path: '-f {} -vn'.format(format)})
print(ff.cmd)
ff.run()
return audio_path
# 視頻添加音頻
def video_add_audio(video_path: str, audio_path: str, output_dir: str):
_ext_video = os.path.basename(video_path).strip().split('.')[-1]
_ext_audio = os.path.basename(audio_path).strip().split('.')[-1]
if _ext_audio not in ['mp3', 'wav']:
raise Exception('audio format not support')
_codec = 'copy'
if _ext_audio == 'wav':
_codec = 'aac'
result = os.path.join(
output_dir, '{}.{}'.format(
uuid.uuid4(), _ext_video))
ff = FFmpeg(
inputs={video_path: None, audio_path: None},
outputs={result: '-map 0:v -map 1:a -c:v copy -c:a {} -shortest'.format(_codec)})
print(ff.cmd)
ff.run()
return result
if __name__ == '__main__':
print(handle('samples/video/981.mp4', 'samples/video_result/', 3, 25, 'cuda'))
代碼說明
1、主要的實(shí)現(xiàn)方法入?yún)⒎謩e為:視頻地址、輸出目錄、類型、fps(幀率)、設(shè)備類型(默認(rèn)cpu,可選擇cuda顯卡模式)。
2、類型主要是選擇模型,最好用3,人像處理更生動(dòng)一些。
3、代碼設(shè)計(jì)思路:先將視頻音頻提取出來、將視頻逐幀處理后寫入新視頻、新視頻和原視頻音頻融合。
關(guān)于如何視頻提取音頻可以參考我的另一篇文章:python 提取視頻中的音頻
關(guān)于如何視頻融合音頻可以參考我的另一篇文章:Python 視頻添加音頻
4、視頻中間會(huì)產(chǎn)生臨時(shí)文件,沒有清理,如需要可以修改代碼自行清理。
驗(yàn)證一下
下面是我準(zhǔn)備的視頻素材截圖,我會(huì)上傳到github上。

執(zhí)行結(jié)果

看看效果截圖

還是很不錯(cuò)的哦。
總結(jié)
這次可不是沒什么好總結(jié)的,總結(jié)的東西蠻多的。首先我說一下這個(gè)開源項(xiàng)目目前模型的一些問題。
1、我測(cè)試了不少圖片,總的來說對(duì)亞洲人的臉型不能很好的卡通化,但是歐美的臉型都比較好。所以還是訓(xùn)練的數(shù)據(jù)不是很夠,但是能理解,畢竟要專門做卡通化的標(biāo)注數(shù)據(jù)想想就是蠻頭疼的事。所以我建議大家在使用的時(shí)候,多關(guān)注一下項(xiàng)目是否更新了最新的模型。
2、視頻一但有字幕,會(huì)對(duì)字幕也做處理。所以可以考慮找一些視頻和字幕分開的素材,效果會(huì)更好一些。
以上就是Python實(shí)現(xiàn)GIF動(dòng)圖以及視頻卡通化詳解的詳細(xì)內(nèi)容,更多關(guān)于Python 動(dòng)圖 視頻卡通化的資料請(qǐng)關(guān)注腳本之家其它相關(guān)文章!
相關(guān)文章
使用Python對(duì)Dicom文件進(jìn)行讀取與寫入的實(shí)現(xiàn)
這篇文章主要介紹了使用Python對(duì)Dicom文件進(jìn)行讀取與寫入的實(shí)現(xiàn),文中通過示例代碼介紹的非常詳細(xì),對(duì)大家的學(xué)習(xí)或者工作具有一定的參考學(xué)習(xí)價(jià)值,需要的朋友們下面隨著小編來一起學(xué)習(xí)學(xué)習(xí)吧2020-04-04
Python將list中的string批量轉(zhuǎn)化成int/float的方法
今天小編就為大家分享一篇Python將list中的string批量轉(zhuǎn)化成int/float的方法,具有很好的參考價(jià)值,希望對(duì)大家有所幫助。一起跟隨小編過來看看吧2018-06-06
python讀取excel表格生成erlang數(shù)據(jù)
這篇文章主要為大家詳細(xì)介紹了python讀取excel表格生成erlang數(shù)據(jù),具有一定的參考價(jià)值,感興趣的小伙伴們可以參考一下2017-08-08
anaconda虛擬環(huán)境默認(rèn)路徑的更改圖文教程
在Anaconda中如果沒有指定路徑,虛擬環(huán)境會(huì)默認(rèn)安裝在anaconda所安裝的目錄下,這篇文章主要給大家介紹了關(guān)于anaconda虛擬環(huán)境默認(rèn)路徑更改的相關(guān)資料,需要的朋友可以參考下2023-10-10
python將多個(gè)py文件和其他文件打包為exe可執(zhí)行文件
這篇文章主要介紹了python將多個(gè)py文件和其他文件打包為exe可執(zhí)行文件,通過準(zhǔn)備要打包的工程文件展開詳情,需要的小伙伴可以參考一下2022-05-05
Pyinstaller打包報(bào)錯(cuò)小結(jié)
本文主要介紹了Pyinstaller打包報(bào)錯(cuò)小結(jié),詳細(xì)的介紹了5種錯(cuò)誤的解決方法,文中通過示例代碼介紹的非常詳細(xì),需要的朋友們下面隨著小編來一起學(xué)習(xí)學(xué)習(xí)吧2024-02-02

