"""main.py""" import argparse import numpy as np from solver import Solver from utils import str2bool import os def main(args): net = Solver(args) if args.train: #os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID" #os.environ['CUDA_VISIBLE_DEVICES'] = "6" import torch torch.backends.cudnn.enabled = True torch.backends.cudnn.benchmark = True #torch.cuda.set_device(2) seed = args.seed torch.manual_seed(seed) torch.cuda.manual_seed(seed) np.random.seed(seed) net.train() else: # Instead of calling traverse here (as before), we call reconstruct to see how the images are reconstructed. # We also need to compute the KL Divergence and reconstruction loss. (See if we should use different flags) # for this reconstruction (which needs decoder net) and just for KLD (just encoder is enough). #net.traverse() os.environ['CUDA_VISIBLE_DEVICES'] = "" import torch torch.backends.cudnn.enabled = True torch.backends.cudnn.benchmark = True if args.is_audit == True: net.audit() else: net.test() if __name__ == "__main__": parser = argparse.ArgumentParser(description='toy Beta-VAE') parser.add_argument('--train', default=True, type=str2bool, help='train or traverse') parser.add_argument('--is_audit', default=False, type=str2bool, help='audit or not') parser.add_argument('--audit_classes', default=2, type=int, help='number of audit classes') parser.add_argument('--only_random', default=False, type=str2bool, help='Use model to just generate random images') parser.add_argument('--demo_test', default=False, type=str2bool, help='Save individual pictures or not for downstream API demographic test') parser.add_argument('--seed', default=1, type=int, help='random seed') parser.add_argument('--use_cuda', default=True, type=str2bool, help='enable cuda') parser.add_argument('--max_iter', default=1e6, type=float, help='maximum training iteration') parser.add_argument('--batch_size', default=64, type=int, help='batch size') parser.add_argument('--z_dim', default=10, type=int, help='dimension of the representation z') parser.add_argument('--beta', default=4, type=float, help='beta parameter for KL-term in original beta-VAE') parser.add_argument('--objective', default='H', type=str, help='beta-vae objective proposed in Higgins et al. or Burgess et al. H/B') parser.add_argument('--model', default='H', type=str, help='model proposed in Higgins et al. or Burgess et al. H/B') parser.add_argument('--gamma', default=1000, type=float, help='gamma parameter for KL-term in understanding beta-VAE') parser.add_argument('--C_max', default=25, type=float, help='capacity parameter(C) of bottleneck channel') parser.add_argument('--C_stop_iter', default=1e5, type=float, help='when to stop increasing the capacity') parser.add_argument('--lr', default=1e-4, type=float, help='learning rate') parser.add_argument('--beta1', default=0.9, type=float, help='Adam optimizer beta1') parser.add_argument('--beta2', default=0.999, type=float, help='Adam optimizer beta2') parser.add_argument('--dset_dir', default='data', type=str, help='dataset directory') parser.add_argument('--dataset', default='CelebA', type=str, help='dataset name') parser.add_argument('--image_size', default=64, type=int, help='image size. now only (64,64) is supported') parser.add_argument('--num_workers', default=2, type=int, help='dataloader num_workers') parser.add_argument('--viz_on', default=True, type=str2bool, help='enable visdom visualization') parser.add_argument('--viz_name', default='main', type=str, help='visdom env name') parser.add_argument('--viz_port', default=8097, type=str, help='visdom port number') parser.add_argument('--save_output', default=True, type=str2bool, help='save traverse images and gif') parser.add_argument('--output_dir', default='outputs', type=str, help='output directory') parser.add_argument('--gather_step', default=1000, type=int, help='numer of iterations after which data is gathered for visdom') parser.add_argument('--display_step', default=10000, type=int, help='number of iterations after which loss data is printed and visdom is updated') parser.add_argument('--save_step', default=10000, type=int, help='number of iterations after which a checkpoint is saved') parser.add_argument('--ckpt_dir', default='checkpoints', type=str, help='checkpoint directory') parser.add_argument('--ckpt_name', default='last', type=str, help='load previous checkpoint. insert checkpoint filename') parser.add_argument('--attr', default='male', type=str, help='enter the attribute of CelebA to test upon.') parser.add_argument('--do_modify', default=False, type=str2bool, help='flag to say if the training objective needs to call API and change capacity') # MORE NEW ONES parser.add_argument('--modify_step', default=500001, type=int, help='at which step to modify objective to add more capacity to selected dimensions') parser.add_argument('--modify_increase_step', default=20000, type=int, help='if we do incremental increase of capacity then for how many steps to increase it') parser.add_argument('--modify_type', default='d', type=str, help='choose between (i)ncremental or (d)irect increase of capacity') #Conditioning parser.add_argument('--condition', default=False, type=str2bool, help='flag to decide on Condition VAE or not') args = parser.parse_args() main(args)