Weize Quan

In https://github.com/ayoolaolafenwa/PixelLib/tree/master/pixellib/semantic/__init__.py line 835, "masks": label_mask -> "masks": masks?

The function of util.deprocessLAB(L, AB)

1

In util.lua, L2 = L2:add(1):mul(50.0) # let L2 ~[0.0, 100.0]. It is reasonable. AB2 = AB2:mul(110.0) # let AB2 ~[-110.0, 110] ? if so, why not [-128,0 127.0]?

Hi, i run your code, and the log file store in logs/cifar100-16-0.0001-0.0001/events.out.tfevents.1510472514.nlpr. And then i run the command line: tensorboard --logdir=logs/cifar100-16-0.0001-0.0001, the output result: TensorBoard 0.1.4 at http://nlpr:6006 (Press CTRL+C...

Hello, I try to run your code. However, i cannot find the download link for, would you mind sharing me this link. In addition, i want to check is the...

How to output the normal map with blender_script.py?

2

Thanks for sharing the rendering code. How to export the normal map based on blender_script.py?

DatasetNoPair

1

If the pair_constraint = false, the code will use DatasetNoPair. Like DatasetPair, the DatasetNoPair also can call transform (RandomRot, RandomFlip). In paired mode, the cover and stego images will be...

use_batch_norm

1

in train_loader, pair_constraint=not(args.use_batch_norm), Why set pair_constraint as False when use batch normalization? In your implementation, the image don't be normalized to [0.0,1.0]?

train/val/test batch

6

Reading the class train(self, nb_train_batch, nb_test_batch, nb_validation_batch, validation_frequency = 10, show_filters = False): , your shared code now is used to train on patches (100x100), and also val/test on patches....