diff --git a/README.md b/README.md index 1d4d9b6..f142aa9 100644 --- a/README.md +++ b/README.md @@ -78,7 +78,7 @@ sudo apt-get install cuda ``` sudo apt-get install libsnappy-dev -sudo apt-get install libgraphicsmagick-dev +sudo apt-get install libgraphicsmagick1-dev ``` #### Install Torch7 @@ -182,7 +182,7 @@ th waifu2x.lua -m noise -noise_level 1 -resume 1 -l data/frame.txt -o new_frames Generating a video from waifu2xed images and audio. ``` -avconv -f image2 -r 24 -i new_frames/%d.png -i audio.mp3 -r 24 -vcodec libx264 -crf 16 video.mp4 +avconv -f image2 -framerate 24 -i new_frames/%d.png -i audio.mp3 -r 24 -vcodec libx264 -crf 16 video.mp4 ``` ## Train Your Own Model diff --git a/appendix/benchmark.md b/appendix/benchmark.md index 09822d0..33b377d 100644 --- a/appendix/benchmark.md +++ b/appendix/benchmark.md @@ -1,10 +1,15 @@ # Benchmark results +## Usage -## dataset +``` +th tools/benchmark.lua -dir path/to/dataset_dir -method scale -color y -model1_dir path/to/model_dir +``` - photo_set: 300 various photos. - art_set : 90 artworks (PNG only). +## Dataset + + photo_test: 300 various photos. + art_test : 90 artworks (PNG only). ## 2x upscaling model diff --git a/appendix/waifu2x.nginx.conf b/appendix/waifu2x.nginx.conf index dd582c6..9fd1cce 100644 --- a/appendix/waifu2x.nginx.conf +++ b/appendix/waifu2x.nginx.conf @@ -15,6 +15,7 @@ map $http_accept_language $lang { ~tr tr; ~zh-CN zh-CN; ~zh zh-CN; + ~ko ko; ~en en; } diff --git a/assets/index.de.html b/assets/index.de.html index 6cfed7b..770a227 100644 --- a/assets/index.de.html +++ b/assets/index.de.html @@ -53,6 +53,10 @@ 简体中文 + / + + 한국어 +
Einzelbild Super-Auflösungs Konvertierung für Bilder im Anime Stil mithilfe eines faltenden neuralen Netzwerks. Zusätzlich dazu unterstützt es auch Fotos.
@@ -84,7 +88,7 @@
Mejora la resolución de ilustraciones de tipo anime utilizando redes neuronales convolucionales. También es compatible con fotografías.
diff --git a/assets/index.fr.html b/assets/index.fr.html index 0ad0920..9910473 100644 --- a/assets/index.fr.html +++ b/assets/index.fr.html @@ -53,6 +53,10 @@ 简体中文 + / + + 한국어 +
Outil permettant d'agrandir n'importe quelle image de style "anime", par le biais de réseaux de neurones convolutionnels. Fonctionne également sur les photos.
diff --git a/assets/index.html b/assets/index.html index 123e435..68a9853 100644 --- a/assets/index.html +++ b/assets/index.html @@ -53,6 +53,10 @@ 简体中文 + / + + 한국어 +
Single-Image Super-Resolution for Anime-Style Art using Deep Convolutional Neural Networks. And it supports photo.
diff --git a/assets/index.ja.html b/assets/index.ja.html index 010939a..64b6eaf 100644 --- a/assets/index.ja.html +++ b/assets/index.ja.html @@ -53,6 +53,10 @@ 简体中文 + / + + 한국어 +
深層畳み込みニューラルネットワークによる二次元画像のための超解像システム。 写真にも対応。
diff --git a/assets/index.ko.html b/assets/index.ko.html new file mode 100644 index 0000000..3f022cc --- /dev/null +++ b/assets/index.ko.html @@ -0,0 +1,182 @@ + + + +
+ + + + + + + + + + +컨볼루젼 신경망(CNN) 시스템을 통한 딥 러닝으로 2차원 이미지의 해상도를 개선합니다. 그림 뿐만 아니라 사진에도 대응합니다.
++ + 실제 데모 보기 + + | + + GitHub에서 보기 + +
+ +Single-Image Super-Resolution for Anime-Style Art using Deep Convolutional Neural Networks. And it supports photo.
diff --git a/assets/index.ru.html b/assets/index.ru.html index 5bda367..81413f4 100644 --- a/assets/index.ru.html +++ b/assets/index.ru.html @@ -53,6 +53,10 @@ 简体中文 + / + + 한국어 +
Waifu2x позволяет увеличивать в 4 раза рисованные изображения, например аниме или арт, а также устранять шум на изображении (преимущественно артефакты сжатия JPEG). Теперь также поддерживаются фотографии.
diff --git a/assets/index.tr.html b/assets/index.tr.html index 45de980..e9ff949 100644 --- a/assets/index.tr.html +++ b/assets/index.tr.html @@ -53,6 +53,10 @@ 简体中文 + / + + 한국어 +
Derin Sarmalı Sinirsel Ağ ile çalışan anime stili çalışmalar için süper çözünürlük yükselticidir. Normal fotoğrafları da destekler.
diff --git a/assets/index.zh-CN.html b/assets/index.zh-CN.html index 48bc324..9e00b98 100644 --- a/assets/index.zh-CN.html +++ b/assets/index.zh-CN.html @@ -53,6 +53,10 @@ 简体中文 + / + + 한국어 +
本程序使用卷积神经网络对动漫风格的图片进行放大操作(支持照片)。
diff --git a/lib/w2nn.lua b/lib/w2nn.lua index fe201d6..3491711 100644 --- a/lib/w2nn.lua +++ b/lib/w2nn.lua @@ -13,7 +13,10 @@ end if w2nn then return w2nn else - pcall(load_cunn) + local state, ret = pcall(load_cunn) + if not state then + error("Failed to load CUDA modules. Please check the CUDA Settings.\n---\n" .. ret) + end pcall(load_cudnn) w2nn = {} diff --git a/web.lua b/web.lua index ab3ef3f..c975d0c 100644 --- a/web.lua +++ b/web.lua @@ -347,6 +347,7 @@ local index_fr = file.read(path.join(ROOT, "assets", "index.fr.html")) local index_de = file.read(path.join(ROOT, "assets", "index.de.html")) local index_tr = file.read(path.join(ROOT, "assets", "index.tr.html")) local index_zh_cn = file.read(path.join(ROOT, "assets", "index.zh-CN.html")) +local index_ko = file.read(path.join(ROOT, "assets", "index.ko.html")) local index_en = file.read(path.join(ROOT, "assets", "index.html")) function FormHandler:get() local lang = self.request.headers:get("Accept-Language") @@ -371,6 +372,8 @@ function FormHandler:get() self:write(index_tr) elseif langs[1] == "zh-CN" or langs[1] == "zh" then self:write(index_zh_cn) + elseif langs[1] == "ko" then + self:write(index_ko) else self:write(index_en) end diff --git a/webgen/gen.rb b/webgen/gen.rb old mode 100644 new mode 100755 diff --git a/webgen/locales/de.yml b/webgen/locales/de.yml index 1a6d33e..76b60d2 100644 --- a/webgen/locales/de.yml +++ b/webgen/locales/de.yml @@ -7,19 +7,19 @@ type_url: URL hier eintragen choose_file: Oder wählen Sie eine Datei aus file_limits: "Beschränkungen: Größe: 5MB, Rauschunterdrückung: 3000x3000px, maximale Hochskalierung: 1500x1500px." style: Stil -artwork: Kunst +artwork: Illustration photo: Foto noise_reduction: Rauschunterdrückung expect_jpeg: verursacht möglicherweise JPEG Artifakte nr_none: Keine nr_medium: Mittel nr_high: Hoch -nr_highest: Am Höchsten +nr_highest: Höchste nr_hint: "Sie sollten Rauschunterdrückung nutzen, wenn das Bild an sich viel Bildrauschen aufweist. Ansonsten könnte es den entgegensetzten Effekt haben." upscaling: Hochskalierung up_none: Keine button_convert: Konvertieren button_download: Herunterladen hints: - - "Wenn Sie Firefox benutzen, benutzen Sie bitte SRTG+S um das Bild zu speichern. Herunterladen funktioniert bei Firefox leider nicht." + - "Wenn Sie Firefox benutzen, benutzen Sie bitte STRG+S um das Bild zu speichern. Herunterladen funktioniert bei Firefox leider nicht." \ No newline at end of file diff --git a/webgen/locales/ko.yml b/webgen/locales/ko.yml new file mode 100644 index 0000000..c8e6d06 --- /dev/null +++ b/webgen/locales/ko.yml @@ -0,0 +1,24 @@ +--- +description: 컨볼루젼 신경망(CNN) 시스템을 통한 딥 러닝으로 2차원 이미지의 해상도를 개선합니다. 그림 뿐만 아니라 사진에도 대응합니다. +show_demonstration: 실제 데모 보기 +go_to_github: GitHub에서 보기 +image_choosing: 이미지 선택 +type_url: URL 입력 +choose_file: 또는 파일 업로드 +file_limits: "제한: 크기: 5MB, 노이즈 감소: 3000x3000px, 업스케일링: 1500x1500px." +style: 스타일 +artwork: 그림 +photo: 사진 +noise_reduction: 노이즈 감소 +expect_jpeg: JPEG 아티팩트 제외 +nr_none: 없음 +nr_medium: 중간 +nr_high: 높음 +nr_highest: 최상 +nr_hint: "실제로 노이즈가 있는 이미지에만 사용해야 하며, 그렇지 않을 경우 사진의 세세한 부분이 뭉개질 수 있습니다." +upscaling: 업스케일링 +up_none: 없음 +button_convert: 변환 +button_download: 다운로드 +hints: + - "FireFox에서 이미지를 저장하려면 Ctrl+S를 누르세요. 오른쪽 클릭 > \"이미지 저장\"을 이용하면 정상적으로 동작하지 않습니다." diff --git a/webgen/templates/index.html.erb b/webgen/templates/index.html.erb index a047248..20f1af9 100644 --- a/webgen/templates/index.html.erb +++ b/webgen/templates/index.html.erb @@ -53,6 +53,10 @@ 简体中文 + / + + 한국어 +
<%= t[:description] %>
@@ -157,6 +161,7 @@ + <% if false # comment out %>