WassersteinGAN triaining CelebA problem:MemoryError

[firestonelib]

when I run : python main.py --backend tensorflow --generator deconv --dset celebA --lr_G 1E-3 --lr_D 1E-3 --clamp_lower -0.5 --clamp_upper 0.5 --batch_size 512 --noise_dim 128 It traceback:

Traceback (most recent call last):
  File "main.py", line 85, in <module>
    launch_training(**d_params)
  File "main.py", line 11, in launch_training
    train_WGAN.train(**kwargs)
  File "/mnt/data1/daniel/codes/GAN/DeepLearningImplementations/WassersteinGAN/src/model/train_WGAN.py", line 47, in train
    X_real_train = data_utils.load_image_dataset(dset, img_dim, image_dim_ordering)
  File "../utils/data_utils.py", line 94, in load_image_dataset
    X_real_train = load_celebA(img_dim, image_dim_ordering)
  File "../utils/data_utils.py", line 83, in load_celebA
    X_real_train = normalization(X_real_train, image_dim_ordering)
  File "../utils/data_utils.py", line 16, in normalization
    X = (X - 0.5) / 0.5
MemoryError

Anybody help?

[firestonelib]

@tdeboissiere

[tdeboissiere]

Looks like you're short on RAM. In the load image dataset, you may choose to load only a fraction of the dataset in memory.

In the Colorful folder, there is code to load data on the fly. This removes the RAM limitation at the cost of slower training.

[firestonelib]

@tdeboissiere which code and how to use it?

[tdeboissiere]

In the README there : https://github.com/tdeboissiere/DeepLearningImplementations/tree/master/Colorful/src/model, you'll find the "training_mode" command line argument. From there you can trace back the code to load on the fly.