def train(opt):
opt.experiment = os.path.join(root_dir, opt.experiment)
if not os.path.exists(opt.experiment):
os.makedirs(opt.experiment)
opt.save_model = os.path.join(opt.experiment, opt.save_model)
if opt.load_model is not None:
opt.load_model = os.path.join(opt.experiment, opt.load_model)
opt.log_path = os.path.join(opt.experiment, 'log.train')
opt.logger = make_logger(opt.log_path)
# memory info
print("encoder word2idx number: {}".format(opt.enc_word_vocab_size))
print("decoder word2idx number: {}".format(opt.dec_word_vocab_size))
# Model definition
model = make_model(opt)
if opt.load_word_emb:
if opt.enlarge_word_vocab:
enc_emb = opt.memory['word2idx_w_glove_emb']
else:
enc_emb = opt.memory['word2idx_emb']
dec_emb = opt.memory['word2idx_emb']
model.enc_word_emb.init_weight_from_pre_emb(enc_emb, opt.fix_word_emb)
model.dec_word_emb.init_weight_from_pre_emb(dec_emb, opt.fix_word_emb)
if opt.enc_word_vocab_size == opt.dec_word_vocab_size:
model.dec_word_emb.embedding.weight.data = model.enc_word_emb.embedding.weight.data
model.dec_word_emb.embedding.weight.requires_grad = model.enc_word_emb.embedding.weight.requires_grad
if opt.load_model is not None:
chkpt = torch.load(opt.load_model, map_location = lambda storage, log: storage)
model.load_state_dict(chkpt)
if opt.cuda:
model = model.cuda()
print(model)
# optimizer details
optimizer = Optim(opt.optim, opt.lr, max_grad_norm=opt.max_norm)
optimizer.set_parameters(model.named_parameters())
print("training parameters number: {}".format(len(optimizer.params)))
nll_criterion = nn.NLLLoss(reduction='sum')
if opt.cuda:
nll_criterion = nll_criterion.cuda()
# training procedure
train_iter = DADataset(opt.data_root + opt.train_file, opt.memory, opt.cuda, True)
valid_iter = DADataset(opt.data_root + opt.valid_file, opt.memory, opt.cuda, False)
trainer = DATrainer(model, nll_criterion, optimizer, opt.logger, cuda=opt.cuda)
trainer.train(opt.epochs, opt.batch_size, train_iter, valid_iter, opt.save_model)
def train(args):
max_images_num = data_reader.max_images_num()
shuffle = True
if args.run_ce:
np.random.seed(10)
fluid.default_startup_program().random_seed = 90
max_images_num = 1
shuffle = False
data_shape = [-1] + data_reader.image_shape()
input_A = fluid.layers.data(name='input_A',
shape=data_shape,
dtype='float32')
input_B = fluid.layers.data(name='input_B',
shape=data_shape,
dtype='float32')
fake_pool_A = fluid.layers.data(name='fake_pool_A',
shape=data_shape,
dtype='float32')
fake_pool_B = fluid.layers.data(name='fake_pool_B',
shape=data_shape,
dtype='float32')
g_A_trainer = GATrainer(input_A, input_B)
g_B_trainer = GBTrainer(input_A, input_B)
d_A_trainer = DATrainer(input_A, fake_pool_A)
d_B_trainer = DBTrainer(input_B, fake_pool_B)
# prepare environment
place = fluid.CPUPlace()
if args.use_gpu:
place = fluid.CUDAPlace(0)
exe = fluid.Executor(place)
exe.run(fluid.default_startup_program())
A_pool = ImagePool()
B_pool = ImagePool()
A_reader = paddle.batch(data_reader.a_reader(shuffle=shuffle),
args.batch_size)()
B_reader = paddle.batch(data_reader.b_reader(shuffle=shuffle),
args.batch_size)()
if not args.run_ce:
A_test_reader = data_reader.a_test_reader()
B_test_reader = data_reader.b_test_reader()
def test(epoch):
out_path = args.output + "/test"
if not os.path.exists(out_path):
os.makedirs(out_path)
i = 0
for data_A, data_B in zip(A_test_reader(), B_test_reader()):
A_name = data_A[1]
B_name = data_B[1]
tensor_A = fluid.LoDTensor()
tensor_B = fluid.LoDTensor()
tensor_A.set(data_A[0], place)
tensor_B.set(data_B[0], place)
fake_A_temp, fake_B_temp, cyc_A_temp, cyc_B_temp = exe.run(
g_A_trainer.infer_program,
fetch_list=[
g_A_trainer.fake_A, g_A_trainer.fake_B, g_A_trainer.cyc_A,
g_A_trainer.cyc_B
],
feed={
"input_A": tensor_A,
"input_B": tensor_B
})
fake_A_temp = np.squeeze(fake_A_temp[0]).transpose([1, 2, 0])
fake_B_temp = np.squeeze(fake_B_temp[0]).transpose([1, 2, 0])
cyc_A_temp = np.squeeze(cyc_A_temp[0]).transpose([1, 2, 0])
cyc_B_temp = np.squeeze(cyc_B_temp[0]).transpose([1, 2, 0])
input_A_temp = np.squeeze(data_A[0]).transpose([1, 2, 0])
input_B_temp = np.squeeze(data_B[0]).transpose([1, 2, 0])
imsave(out_path + "/fakeB_" + str(epoch) + "_" + A_name,
((fake_B_temp + 1) * 127.5).astype(np.uint8))
imsave(out_path + "/fakeA_" + str(epoch) + "_" + B_name,
((fake_A_temp + 1) * 127.5).astype(np.uint8))
imsave(out_path + "/cycA_" + str(epoch) + "_" + A_name,
((cyc_A_temp + 1) * 127.5).astype(np.uint8))
imsave(out_path + "/cycB_" + str(epoch) + "_" + B_name,
((cyc_B_temp + 1) * 127.5).astype(np.uint8))
imsave(out_path + "/inputA_" + str(epoch) + "_" + A_name,
((input_A_temp + 1) * 127.5).astype(np.uint8))
imsave(out_path + "/inputB_" + str(epoch) + "_" + B_name,
((input_B_temp + 1) * 127.5).astype(np.uint8))
i += 1
def checkpoints(epoch):
out_path = args.output + "/checkpoints/" + str(epoch)
if not os.path.exists(out_path):
os.makedirs(out_path)
fluid.io.save_persistables(exe,
out_path + "/g_a",
main_program=g_A_trainer.program)
fluid.io.save_persistables(exe,
out_path + "/g_b",
main_program=g_B_trainer.program)
fluid.io.save_persistables(exe,
out_path + "/d_a",
main_program=d_A_trainer.program)
fluid.io.save_persistables(exe,
out_path + "/d_b",
main_program=d_B_trainer.program)
print("saved checkpoint to {}".format(out_path))
sys.stdout.flush()
def init_model():
assert os.path.exists(
args.init_model), "[%s] cann't be found." % args.init_mode
fluid.io.load_persistables(exe,
args.init_model + "/g_a",
main_program=g_A_trainer.program)
fluid.io.load_persistables(exe,
args.init_model + "/g_b",
main_program=g_B_trainer.program)
fluid.io.load_persistables(exe,
args.init_model + "/d_a",
main_program=d_A_trainer.program)
fluid.io.load_persistables(exe,
args.init_model + "/d_b",
main_program=d_B_trainer.program)
print("Load model from {}".format(args.init_model))
if args.init_model:
init_model()
losses = [[], []]
t_time = 0
build_strategy = fluid.BuildStrategy()
build_strategy.enable_inplace = False
build_strategy.memory_optimize = False
exec_strategy = fluid.ExecutionStrategy()
exec_strategy.num_threads = 1
exec_strategy.use_experimental_executor = True
g_A_trainer_program = fluid.CompiledProgram(
g_A_trainer.program).with_data_parallel(
loss_name=g_A_trainer.g_loss_A.name,
build_strategy=build_strategy,
exec_strategy=exec_strategy)
g_B_trainer_program = fluid.CompiledProgram(
g_B_trainer.program).with_data_parallel(
loss_name=g_B_trainer.g_loss_B.name,
build_strategy=build_strategy,
exec_strategy=exec_strategy)
d_B_trainer_program = fluid.CompiledProgram(
d_B_trainer.program).with_data_parallel(
loss_name=d_B_trainer.d_loss_B.name,
build_strategy=build_strategy,
exec_strategy=exec_strategy)
d_A_trainer_program = fluid.CompiledProgram(
d_A_trainer.program).with_data_parallel(
loss_name=d_A_trainer.d_loss_A.name,
build_strategy=build_strategy,
exec_strategy=exec_strategy)
for epoch in range(args.epoch):
batch_id = 0
for i in range(max_images_num):
data_A = next(A_reader)
data_B = next(B_reader)
tensor_A = fluid.LoDTensor()
tensor_B = fluid.LoDTensor()
tensor_A.set(data_A, place)
tensor_B.set(data_B, place)
s_time = time.time()
# optimize the g_A network
g_A_loss, fake_B_tmp = exe.run(
g_A_trainer_program,
fetch_list=[g_A_trainer.g_loss_A, g_A_trainer.fake_B],
feed={
"input_A": tensor_A,
"input_B": tensor_B
})
fake_pool_B = B_pool.pool_image(fake_B_tmp)
# optimize the d_B network
d_B_loss = exe.run(d_B_trainer_program,
fetch_list=[d_B_trainer.d_loss_B],
feed={
"input_B": tensor_B,
"fake_pool_B": fake_pool_B
})[0]
# optimize the g_B network
g_B_loss, fake_A_tmp = exe.run(
g_B_trainer_program,
fetch_list=[g_B_trainer.g_loss_B, g_B_trainer.fake_A],
feed={
"input_A": tensor_A,
"input_B": tensor_B
})
fake_pool_A = A_pool.pool_image(fake_A_tmp)
# optimize the d_A network
d_A_loss = exe.run(d_A_trainer_program,
fetch_list=[d_A_trainer.d_loss_A],
feed={
"input_A": tensor_A,
"fake_pool_A": fake_pool_A
})[0]
batch_time = time.time() - s_time
t_time += batch_time
print(
"epoch{}; batch{}; g_A_loss: {}; d_B_loss: {}; g_B_loss: {}; d_A_loss: {}; "
"Batch_time_cost: {}".format(epoch, batch_id, g_A_loss[0],
d_B_loss[0], g_B_loss[0],
d_A_loss[0], batch_time))
losses[0].append(g_A_loss[0])
losses[1].append(d_A_loss[0])
sys.stdout.flush()
batch_id += 1
if args.run_test and not args.run_ce:
test(epoch)
if args.save_checkpoints and not args.run_ce:
checkpoints(epoch)
if args.run_ce:
print("kpis,g_train_cost,{}".format(np.mean(losses[0])))
print("kpis,d_train_cost,{}".format(np.mean(losses[1])))
print("kpis,duration,{}".format(t_time / args.epoch))