def encoder_test(seq_len=4, decoder_batch_size=2, model_name='xception'):
encoder = Encoder(seq_len=seq_len, decoder_batch_size=decoder_batch_size, model_name=model_name)
encoder.cuda()
encoder.eval()
with torch.no_grad():
images = []
for i in range(decoder_batch_size):
images.append(torch.rand((seq_len, 3, 299, 299)))
images = torch.stack(images).cuda()
features = encoder.forward(images)
split_features = []
for i in range(decoder_batch_size):
split_features.append(encoder._forward_old(images[i]))
split_features = torch.stack(split_features)
assert(torch.all(split_features == features) == 1)
print('encoder test passed!')
vis_fake_B_random = denorm(fake_B_random[0].detach()).cpu().data.numpy().astype(np.uint8)
axs[i + 1].imshow(vis_fake_B_random.transpose(1, 2, 0))
path = os.path.join(test_img_dir, 'epoch_' + str(epoch_id) + '_' + str(idx) + '.png')
if opt.__dict__['use_colab']:
plt.show()
else:
plt.savefig(path)
plt.close()
elif opt.__dict__['infer_encoded']:
"""
B -> encoded latent -> B
FID: 76.68991094315851
"""
z_mu, z_logvar = encoder.forward(rgb_tensor)
z_encoded = reparameterization(z_mu, z_logvar, device=gpu_id)
fake_B_encoded = generator.forward(real_A, z_encoded)
for i in range(batch_size):
vis_fake_B_encoded = \
denorm(fake_B_encoded[i].detach()).cpu().\
data.numpy().astype(np.uint8).transpose(1, 2, 0)
path = os.path.join(test_img_dir, 'gen/fake_B_' + str(idx) + '_' + str(i) + '.png')
plt.imsave(path, vis_fake_B_encoded)
path = os.path.join(test_img_dir, 'real/real_B_' + str(idx) + '_' + str(i) + '.png')
plt.imsave(path,
denorm(real_B[i].detach()).cpu().data.numpy().astype(np.uint8).transpose(1, 2, 0))
elif opt.__dict__['compute_lpips']:
lpips_batch_path = os.path.join(lpips_img_dir, str(idx))
# Adversarial ground truths
valid = Variable(torch.Tensor(
np.ones((real_A.size(0), *discriminator.output_shape))),
requires_grad=False).to(gpu_id)
fake = Variable(torch.Tensor(
np.zeros((real_A.size(0), *discriminator.output_shape))),
requires_grad=False).to(gpu_id)
# -------------------------------
# Forward ALL
# ------------------------------
encoder.train()
generator.train()
z_mu, z_logvar = encoder.forward(rgb_tensor)
z_encoded = reparameterization(z_mu, z_logvar, device=gpu_id)
fake_B_encoded = generator.forward(real_A, z_encoded)
z_random = torch.randn(real_A.shape[0], latent_dim).to(gpu_id)
fake_B_random = generator.forward(real_A, z_random)
z_mu_predict, z_logvar_predict = encoder.forward(fake_B_random)
# -------------------------------
# Train Generator and Encoder
# ------------------------------
for param in discriminator.parameters():
param.requires_grad = False
from layers import LSTM, FullConnected, TimeDistributed from models import Decoder, Encoder, Seq2seq, Sequential from utils import masking, padding rng.seed(123) # Preprocess data x1 = [2, 1, 1, 1, 2, 4, 2] x2 = [2, 1] x3 = [2, 1, 4, 3, 1] batch_value = np.asarray([x1, x2, x3]) vocab_size = 5 embedding_size = 4 encoder_hidden_size = 6 encoder = Encoder(vocab_size + 1, embedding_size, encoder_hidden_size) mask_value = masking(batch_value) padded_batch_value = padding(batch_value, 0) mask = shared(mask_value, name='mask') padded_batch = shared(padded_batch_value, name='padded_batch') H, C = encoder.forward(padded_batch, mask) (h1, c1) = encoder.forward2(x1) (h2, c2) = encoder.forward2(x2) (h3, c3) = encoder.forward2(x3) print(T.isclose(H, T.as_tensor_variable([h1, h2, h3])).eval()) print(T.isclose(C, T.as_tensor_variable([c1, c2, c3])).eval())
return files
dataset = CustomDataset(args)
dataset_loader = torch.utils.data.DataLoader(dataset=dataset, batch_size=args.batch_size, shuffle=False)
for epoch in range(1, args.epoch):
epoch_loss_rec = []
epoch_loss_kl = []
for batch_t in dataset_loader:
z_vector, z_mu, z_sigma = encoder.forward(batch_t)
decoded = decoder.forward(z_vector)
if args.show:
show(batch_t[0], decoded[0])
if args.load:
continue
loss_recunstruction = reconstruction_loss_fn(decoded, batch_t)
loss_kl = args.beta * 0.5 * (1.0 + torch.log(z_sigma**2) - z_mu**2 - z_sigma**2)
loss_kl = torch.mean(loss_kl)
loss = loss_recunstruction - loss_kl
optimizer.zero_grad()