state_dict = torch.load(f)
discard = [x for x in state_dict if x.startswith('fc1')]
state = model.state_dict()
state.update(state_dict)
try:
model.load_state_dict(state)
except Exception:
for key in discard:
state_dict.pop(key)
state = model.state_dict()
state.update(state_dict)
model.load_state_dict(state)
load_ext = True
if args.cuda:
model.cuda()
reconstruction_function = nn.MSELoss()
reconstruction_function.size_average = False
def loss_function(recon_x, x, mu, logvar):
BCE = reconstruction_function(recon_x, x)
# see Appendix B from VAE paper:
# Kingma and Welling. Auto-Encoding Variational Bayes. ICLR, 2014
# https://arxiv.org/abs/1312.6114
# 0.5 * sum(1 + log(sigma^2) - mu^2 - sigma^2)
KLD_element = mu.pow(2).add_(logvar.exp()).mul_(-1).add_(1).add_(logvar)
KLD = torch.sum(KLD_element).mul_(-0.5)
# print(kld_history)
# print(mse_history)
plt.figure(figsize=(40, 10))
plt.subplot(121)
plt.title('KLD loss')
plt.plot(kld_history)
plt.subplot(122)
plt.title('MSE loss')
plt.plot(mse_history)
plt.savefig(output_path+'/fig1_2.jpg')
model = VAE(64, 1e-5)
model.load_state_dict(torch.load('VAE/vae_state_model.pth'))
if cuda:
model = model.cuda()
# print(model)
data_for_tsne = []
label_for_tsne = []
mse = 0
for (data, label) in test_dataloader:
# print(data.size())
# if cuda:
# data = data.cuda()
# data = Variable(data.cuda())
# recon_img, mu, logvar = model(data)
# loss = model.loss_function(data, recon_img, mu, logvar)
# mse += torch.sum(model.latest_loss()[0])
if len(data_for_tsne) < 50:
data_for_tsne.append(data)