ChromaGAN

ChromaGAN copied to clipboard

I cant get psnr in 25 by training this model ,atually only have 23.6.

1

I can't train to achieve the accuracy for PSNR shown in the paper,do you have some tricks?

XiaoluJiayou

Bumps [numpy](https://github.com/numpy/numpy) from 1.15.4 to 1.22.0. Release notes Sourced from numpy's releases. v1.22.0 NumPy 1.22.0 Release Notes NumPy 1.22.0 is a big release featuring the work of 153 contributors spread...

dependabot[bot]

Can not train model

2

I'm trying to retrain the model according to the instructions in the README.md file, ``` python SOURCE/ChromaGAN.py ``` then this error appears ``` Traceback (most recent call last): File "/home/yuuto/Persenal/ChromaGan/ChromaGAN/SOURCE/ChromaGAN.py",...

superhighlevel

Bumps [opencv-python](https://github.com/skvark/opencv-python) from 4.1.0 to 4.2.0.32. Release notes Sourced from opencv-python's releases. 4.2.0.32 opencv-python: https://pypi.org/project/opencv-python/ opencv-contrib-python: https://pypi.org/project/opencv-contrib-python/ opencv-python-headless: https://pypi.org/project/opencv-python-headless/ opencv-contrib-python-headless: https://pypi.org/project/opencv-contrib-python-headless/ OpenCV version 4.2.0. Changes: macOS environment updated from xcode8.3...

dependabot[bot]

G:\proj\YUs_Ai\02PYTORCH\04color\ChromaGAN-master\MODEL/imagenet/modelPretrained.h5 Traceback (most recent call last): File "ChromaGANPrint.py", line 112, in sample_images(not args.no_concatenate) File "ChromaGANPrint.py", line 58, in sample_images colorizationModel = load_model(save_path) File "G:\SUCAI\Anaconda3\envs\PY388\lib\site-packages\keras\engine\saving.py", line 492, in load_wrapper return load_function(*args,...

vbqgyy

Thanks for your code! The opencv-python version should be 4.1.0.25 instead of 4.1.0, which will lead to some error while preparing the environment.

Kasumigaoka-Utaha

Dense layer without activation?

7

In https://github.com/pvitoria/ChromaGAN/blob/30e975beccf1ab94f5c26b0ec3df7b34f22cb612/SOURCE/ChromaGAN.py#L209 there is no activation parameter designated in the Dense layer. In keras 2.3.1, the default activation is linear activation (i.e. no activation): ``` tf.keras.layers.Dense( units, activation=None, ... ```

owen8877

Converted Notebook to Python

2

Nice colorization model. I was able to replicate your results. I have also converted your notebook to a python version that can be run directly via command line.

edwin-yan

I was wondering if there is a chromagan project based on the PYTORCH framework

1colorworker

Bumps [keras](https://github.com/keras-team/keras) from 2.2.4 to 2.13.1. Release notes Sourced from keras's releases. Keras Release 2.13.1 What's Changed Fix timeseries_dataset_from_array counts when sequence_stride > 1 by @​basjacobs93 in keras-team/keras#17396 Fix doc...

dependabot[bot]