osciiart / deepaa Goto Github PK

View Code? Open in Web Editor NEW

1.5K 40.0 102.0 19.51 MB

make ASCII Art by Deep Learning

License: MIT License

Python 100.00%

deep-learning keras tensorflow ascii-art python

deepaa's Introduction

DeepAA

This is convolutional neural networks generating ASCII art. This repository is under construction.

This work is accepted by NIPS 2017 Workshop, Machine Learning for Creativity and Design The paper: ASCII Art Synthesis with Convolutional Networks

Web application (using previous version model) (by tar-bin)

Change log

2017/12/2 added light model

Requirements

TensorFlow (1.3.0)
Keras (2.0.8)
NumPy (1.13.3)
Pillow (4.2.1)
Pandas (0.18.0)
Scikit-learn (0.19.0)
h5py (2.7.1)
model's weight (download it from here and place it in dir model.)
training data (additional, download it from here, extract it and place the extracted directory in dir data.) )

How to use

please change the line 15 of output.py

image_path = 'sample images/original images/21 original.png' # put the path of the image that you convert.

into the path of image file that you use. You should use a grayscale line image.

then run output.py . converted images will be output at output/ .

You can select light model by change the line 13, 14 of output.py into

model_path = "model/model_light.json"
weight_path = "model/weight_light.hdf5"

License

The pre-trained models and the other files we have provided are licensed under the MIT License.

deepaa's People

Contributors

Stargazers

Watchers

Forkers

tar-bin fang320 wanwanland embeddedsamurai ry-team scrpgil mikalv gyzhangqm jdc08161063 burness huzqujm mikigom eggintheshell zumbalamambo kastnerkyle iamvon riktimmondal vetoplayer manguluka wakame1367 shubhampachori12110095 tngamemo xavrb johnjohnsp1 nonlining thedevankit hhy5277 crownhuang linecode shashi007 jithinraj skylabspune suizman zgodongw anthonymcqueen21 yesihack 19ai raymondseger rockystevejobs cccnoob barseghyanartur cameronnapoli zeph1912 mlopezm zhangxiaowen alguevara7 githubcrj zgsxwsdxg drericebert zky001 boborz m4rm0k zhangyang5511 facepainter leucotic zhonghuihuo grseb9s emezac emanon42 happy-forks monkeystone praveenmunagapati ramananm wwwmewww stevenlol shuizhilinxin xyionwu buaazb jackxu9527 donadonny neosun100 wkflyerman xielm12 iveskins m-elswah motacapla talkuhulk chine007 hakanaku1234 stastechno taroorat zhangfaquan 5l1v3r1 zenahr gl-prout lilykissme ternence-li chloekurumi kalvin807 jakehlee jrkolsby dfmjndm c0ntr07 mosaicthej kabeer11000 al-swaiti xlavaxmasterx n317 asciiart-development qindapao

deepaa's Issues

Font?

I was wondering which font would be best for output.
I generated ascii art someting like this:

　  ,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,　　　
　　|　　　　　　　　　　　　　　　　　　　　　 | 　　　
　　|　　'|''''''''''''''''''''''''''''''''''''''''''''''''''''''''''|　 　 |　　　
　　|　　:|　　,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,-,,,,　　 |　 　 |　　　
　　|　　:|　　 |　　　　　　　　　　]|　　|　 　 |　　　
　　|　　:|　　 |　　　　　　　　　　:|　　:|　 　 |　　　
　　|　　:|　　 |　　　　　　　　　　:|　　:|　 　 |　　　
　　|　　:|　　 |　　　　　　　 　　 l|　　 |　 　 |　　　
　　|　　:| 　 └――――――-┘　 |　 　 |　　　
　　|　　.|＿＿＿＿＿＿＿＿＿＿__,|　 　 |　　　
　  |　　　　　　　　　　　　　　　　　　　　　 :|　　　
　　|-----------------------------┘

and I think fixed width font is not proper for this.

I was trying to download the weights file over google drive and it asked for me to request access. I believe there is a way to set it to not make people request access, but still not be able to edit the file. That will make it so you don't have to give access to anyone who wants to download in the future.

Thanks for the cool program!

deepaa_output.pyを実行時にmodel_from_jsonで実行時例外が発生しますー。

pip でtensorflowとKerasはインストールしましたー。

#スタックトレース

Using TensorFlow backend.
Traceback (most recent call last):
File "C:/Users/(ユーザー名)/Downloads/DeepAA-master/deepaa_output.py", line 24, in
model = model_from_json(json_string)
File "C:\Program Files\Anaconda3\lib\site-packages\keras\models.py", line 325, in model_from_json
return layer_module.deserialize(config, custom_objects=custom_objects)
File "C:\Program Files\Anaconda3\lib\site-packages\keras\layers_init_.py", line 46, in deserialize
printable_module_name='layer')
File "C:\Program Files\Anaconda3\lib\site-packages\keras\utils\generic_utils.py", line 140, in deserialize_keras_object
list(custom_objects.items())))
File "C:\Program Files\Anaconda3\lib\site-packages\keras\engine\topology.py", line 2370, in from_config
process_layer(layer_data)
File "C:\Program Files\Anaconda3\lib\site-packages\keras\engine\topology.py", line 2339, in process_layer
custom_objects=custom_objects)
File "C:\Program Files\Anaconda3\lib\site-packages\keras\layers_init_.py", line 46, in deserialize
printable_module_name='layer')
File "C:\Program Files\Anaconda3\lib\site-packages\keras\utils\generic_utils.py", line 141, in deserialize_keras_object
return cls.from_config(config['config'])
File "C:\Program Files\Anaconda3\lib\site-packages\keras\engine\topology.py", line 1202, in from_config
return cls(**config)
TypeError: init() got an unexpected keyword argument 'input_dtype'

#環境
Python 3.5.2 |Anaconda custom (64-bit)| (default, Jul 5 2016, 11:41:13) [MSC v.1900 64 bit (AMD64)] on win32
依存ライブラリのバージョン

tensorflow (1.0.1)
Keras (2.0.1)
numpy (1.12.0)
Pillow (3.3.1)

Missing weight.hdf5

Large file size so file wasn't uploaded: https://github.com/OsciiArt/DeepAA/blob/master/model/weight.hdf5

Possibly supply file in releases or upload elsewhere.

It looks very nice

Sorry, I can not understand Japanese language. I think your work looks promising 👍 I've also written some codes trying to achieve the results as Xu did in her article, but what I got is pretty messy as in the following image(70 chars a line) 😥

Hope you can write an article explaining the details about how you train the model 😁

No "model/weight.hdf5" file

Link to training data is actually to the weight.hdf5 file

The bullet point "training data (additional, download it from [here], extract it and place the extracted directory in dir data.) )" in the readme seems like it should link to a training data file but it actually links to the same weights.hdf5 file as in the previous bullet point.

typo

make Ascii Art by Deep Learing

Learing -> Learning