def load_models(load_path):
model_args = json.load(open(os.path.join(load_path, 'options.json'), 'r'))
vars(args).update(model_args)
autoencoder = Seq2Seq(emsize=args.emsize,
nhidden=args.nhidden,
ntokens=args.ntokens,
nlayers=args.nlayers,
noise_r=args.noise_r,
hidden_init=args.hidden_init,
dropout=args.dropout,
gpu=args.cuda)
gan_gen = MLP_G(ninput=args.z_size,
noutput=args.nhidden,
layers=args.arch_g)
gan_disc = MLP_D(ninput=args.nhidden, noutput=1, layers=args.arch_d)
autoencoder = autoencoder.cuda()
gan_gen = gan_gen.cuda()
gan_disc = gan_disc.cuda()
word2idx = json.load(open(os.path.join(args.save, 'vocab.json'), 'r'))
idx2word = {v: k for k, v in word2idx.items()}
print('Loading models from {}'.format(args.save))
loaded = torch.load(os.path.join(args.save, "model.pt"))
autoencoder.load_state_dict(loaded.get('ae'))
gan_gen.load_state_dict(loaded.get('gan_g'))
gan_disc.load_state_dict(loaded.get('gan_d'))
return model_args, idx2word, autoencoder, gan_gen, gan_disc
if opt.MLP == True:
netG = MLP_G(s_sample, nz, nc, ngf, ngpu)
netD = MLP_D(s_sample, nz, nc, ngf, ngpu)
else:
netG = DCGAN_G(s_sample, nz, nc, ngf, ngpu)
netD = DCGAN_D(s_sample, nz, nc, ndf, ngpu)
#experiments/ch128_lr0005_tanh/netD_epoch_47.pth
epoch_load = opt.epoch_st - 1
wass_loss = []
if opt.load_weights == True:
netG.load_state_dict(
torch.load(opt.experiment + 'netG_epoch_' + str(epoch_load) +
'.pth'))
netD.load_state_dict(
torch.load(opt.experiment + 'netD_epoch_' + str(epoch_load) +
'.pth'))
wass_loss = pd.read_csv(opt.experiment + 'loss.csv', header=None)
wass_loss = wass_loss[wass_loss.columns[0]].tolist()
device = torch.device("cuda" if opt.cuda else "cpu")
#part, datapath, s_sample, nsamples, transform, d2
partition = {'train': [x for x in range(0, n_samples)]}
dataset = HydrogenDataset(part=partition,
torch.load('{}/autoencoder_model.pt'.format(args.outf),
map_location=lambda storage, loc: storage))
if os.path.isfile('{}/classifier_model.pt'.format(args.outf)):
classifier.load_state_dict(
torch.load('{}/classifier_model.pt'.format(args.outf),
map_location=lambda storage, loc: storage))
if os.path.isfile('{}/gan_disc_model.pt'.format(args.outf)):
gan_disc.load_state_dict(
torch.load('{}/gan_disc_model.pt'.format(args.outf),
map_location=lambda storage, loc: storage))
if os.path.isfile('{}/gan_gen_model.pt'.format(args.outf)):
gan_gen.load_state_dict(
torch.load('{}/gan_gen_model.pt'.format(args.outf),
map_location=lambda storage, loc: storage))
if args.cuda:
autoencoder = autoencoder.cuda()
gan_gen = gan_gen.cuda()
gan_disc = gan_disc.cuda()
classifier = classifier.cuda()
criterion_ce = criterion_ce.cuda()
###############################################################################
# Training code
###############################################################################
def save_model():