RetinexNet

RetinexNet copied to clipboard

I_delta is the enhanced I_low ? think u

potoyeee

Is it possible to release the evaluation code for fair comparison? Thank you.

zoezhou1999

version of python

1

It shows up some errors when I ran the code. The error is "Process finished with exit code -1073741819 (0xC0000005)". I don't think the version of the python I used...

KarelZhang

请问有数据集光照强度的具体值嘛

Aprilsongsong

z-huabao

Nice for sharing, howerver, Poor performance even using images in data/eval

2

感谢分享， 但是， CPU模式下，对data/eval /test下结果也不好，噪点非常明显 python3.6 main.py --use_gpu=0 --phase=test --test_dir=/home/***/下载/RetinexNet-master/test1/ --save_dir=/home/***/下载/RetinexNet-master/res1/ --decom=1 是还有其他参数吗？ 而且decom参数貌似没用啊

gxf1027

训练Decomposition模型时出现的问题

1

1. 训练时LOSS值一直稳定不变，应该和learning_rate没什么关系，无论怎么调整都不会变。 2. Decomposition模型输出的R_low和I_low会随着训练次数的增加逐渐变白，最后变成全白色。 这两个是什么原因？我是单独训练Decomposition，应该和这个没关系吧。

hhelicopter

unicorn343

In the beginning of DeconNet function, there are these two ines: _input_max = tf.reduce_max(input_im, axis=3, keepdims=True) input_im = concat([input_max, input_im])_ Could you tell what it does and what is the...

akshay-iyer

run "python man.py --phase=test" and produced no results

1

unicorn343