深度學(xué)習(xí)將灰度圖著色

零本地設(shè)置/ DeOldify / Colab筆記本 (Zero Local Setup / DeOldify / Colab Notebook)

“Haal Kaisa Hai Janaab Ka” Bollywood Song — 1958 and “Beautiful Black & White Hollywood Movie Shots Collection”“ Haal Kaisa Hai Janaab Ka”寶萊塢歌曲-1958年和“ Beautiful Black＆White Hollywood Movie Shots Collection”

Following up on my goal of doing things easily, I wanted to try DeOldify to convert B&W video content with audio over and over again, without having to change code or lose progress due to the free resource session timing out on Google Colab.

遵循我輕松做事的目標(biāo)，我想嘗試DeOldify一次又一次地轉(zhuǎn)換B＆W視頻內(nèi)容和音頻，而不必更改代碼或由于Google Colab上的免費(fèi)資源會(huì)話超時(shí)而失去進(jìn)度。

Below are the steps — around 10 clicks, enabling you to do just that! Keep in mind I have tested only short videos (5 mins) with the free hardware resources.

以下是步驟-大約10次點(diǎn)擊，使您能夠做到這一點(diǎn)！ 請(qǐng)記住，我僅使用免費(fèi)的硬件資源測(cè)試了短片(5分鐘)。

Open the Colab Notebook link hosted in the repository. This article might also familiarize you with the power of Colab for your next exciting AI paper.

打開存儲(chǔ)庫中托管的Colab Notebook鏈接。 本文還可能使您熟悉Colab在下一篇令人興奮的AI論文中的功能。

https://colab.research.google.com/github/ojjsaw/video-processing/blob/master/Custom_DeOldify_VideoColorizer_Colab.ipynb

https://colab.research.google.com/github/ojjsaw/video-processing/blob/master/Custom_DeOldify_VideoColorizer_Colab.ipynb

First, ensure a free GPU resource is allocated by logging in. Click on Runtime menu on the top > Change runtime type > GPU > Save and then click Connect on the top right.

首先，確保通過登錄分配免費(fèi)的GPU資源。單擊頂部的“運(yùn)行 時(shí)”菜單> 更改運(yùn)行時(shí)類型 > GPU > 保存 ，然后單擊右上角的“ 連接 ”。

Step 1第1步

After logging in, hit Connect again and update the URL to your video link obtained from the share icon on your YouTube video. The default URL is the iconic “Arrival of the Train” clip from Lumière Brothers’ 1895 — History of Films 101.

登錄后，再次單擊“ 連接” ，然后將URL更新為從YouTube視頻上的共享圖標(biāo)獲得的視頻鏈接。 默認(rèn)的URL是LumièreBrothers的1895年-電影史101中的標(biāo)志性“火車到達(dá)”剪輯。

You can optionally modify the default google drive export directory path.

您可以選擇修改默認(rèn)的Google驅(qū)動(dòng)器導(dǎo)出目錄路徑。

Hit the Run icon on the left! Every time you open this page (session), you will be asked to authorize google drive to mount it to your current session.

點(diǎn)擊左側(cè)的“運(yùn)行”圖標(biāo) ！ 每次您打開此頁面( 會(huì)話 )時(shí)，系統(tǒng)都會(huì)要求您授權(quán)google驅(qū)動(dòng)器將其安裝到當(dāng)前會(huì)話中。

Step 2第2步

Copy-paste the authorization code and hit Enter. Click on the Setup text section to bring it in focus and hit the Run After option from the Runtime menu on the top of the page.

復(fù)制并粘貼授權(quán)碼，然后按Enter 。 單擊“ 設(shè)置”延伸部分以使其突出 顯示 ，然后單擊頁面頂部“ 運(yùn)行時(shí)” 菜單中的“運(yùn)行后”選項(xiàng)。

Step 3第三步

Sit tight and go grab a coffee! Just make sure your machine is running and the browser stays alive.

坐好去喝杯咖啡！ 只要確保您的機(jī)器正在運(yùn)行并且瀏覽器保持運(yùn)行狀態(tài)即可。

It will take a while to process, but after a successful conversion, the source and result videos will be uploaded to your google drive at the chosen path.

處理需要一些時(shí)間 ，但是成功轉(zhuǎn)換后， 源視頻和結(jié)果視頻將按照所選路徑上傳到您的Google驅(qū)動(dòng)器。

Again, above is the simplest path to conversion without the bells and whistles. For more customization, please take a look at the original notebook.

同樣，以上是最簡(jiǎn)單的轉(zhuǎn)換方法，沒有花哨的時(shí)間。 要進(jìn)行更多定制，請(qǐng)查看原始筆記本 。

In future posts, we will try to increase the frames-per-second of a video for a smoother clip and possibly even upscale the video to a higher resolution to satisfy the requirements of current generation display devices.

在以后的文章中，我們將嘗試增加視頻的每秒幀數(shù)以實(shí)現(xiàn)更流暢的剪輯，甚至可能將視頻放大到更高的分辨率，以滿足當(dāng)前顯示設(shè)備的要求。

If you’d like to try more start-to-finish quick AI experiments, visit my last post: Train a Neural Network to classify images & optimize CPU inferencing in 10 mins

如果您想嘗試更多的從頭到尾的快速AI實(shí)驗(yàn)，請(qǐng)?jiān)L問我的上一篇文章： 訓(xùn)練神經(jīng)網(wǎng)絡(luò)對(duì)圖像進(jìn)行分類并在10分鐘內(nèi)優(yōu)化CPU推理

翻譯自: https://towardsdatascience.com/colorize-a-video-with-deep-learning-15b30da3b57c

深度學(xué)習(xí)將灰度圖著色

總結(jié)

以上是生活随笔為你收集整理的深度学习将灰度图着色_通过深度学习为视频着色的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。