本文整理汇总了Python中model.Model.cleargrads方法的典型用法代码示例。如果您正苦于以下问题：Python Model.cleargrads方法的具体用法？Python Model.cleargrads怎么用？Python Model.cleargrads使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类model.Model的用法示例。
在下文中一共展示了Model.cleargrads方法的3个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: main
# 需要导入模块: from model import Model [as 别名]
# 或者: from model.Model import cleargrads [as 别名]
def main():
parser = argparse.ArgumentParser()
parser.add_argument("--batchsize", "-b", type=int, default=64)
parser.add_argument("--total-epochs", "-e", type=int, default=300)
parser.add_argument("--gpu-device", "-g", type=int, default=0)
parser.add_argument("--grad-clip", "-gc", type=float, default=5)
parser.add_argument("--learning-rate", "-lr", type=float, default=0.0001)
parser.add_argument("--momentum", "-mo", type=float, default=0.5)
parser.add_argument("--optimizer", "-opt", type=str, default="adam")
parser.add_argument("--model", "-m", type=str, default="model.hdf5")
args = parser.parse_args()
mnist_train, mnist_test = chainer.datasets.get_mnist()
images_train, labels_train = mnist_train._datasets
images_test, labels_test = mnist_test._datasets
# normalize
images_train = (images_train - 0.5) * 2
images_test = (images_test - 0.5) * 2
dataset = Dataset(train=(images_train, labels_train), test=(images_test, labels_test))
total_iterations_train = len(images_train) // args.batchsize
model = Model()
model.load(args.model)
# optimizers
optimizer_encoder = Optimizer(args.optimizer, args.learning_rate, args.momentum)
optimizer_encoder.setup(model.encoder)
if args.grad_clip > 0:
optimizer_encoder.add_hook(GradientClipping(args.grad_clip))
optimizer_decoder = Optimizer(args.optimizer, args.learning_rate, args.momentum)
optimizer_decoder.setup(model.decoder)
if args.grad_clip > 0:
optimizer_decoder.add_hook(GradientClipping(args.grad_clip))
optimizer_discriminator = Optimizer(args.optimizer, args.learning_rate, args.momentum)
optimizer_discriminator.setup(model.discriminator)
if args.grad_clip > 0:
optimizer_discriminator.add_hook(GradientClipping(args.grad_clip))
using_gpu = False
if args.gpu_device >= 0:
cuda.get_device(args.gpu_device).use()
model.to_gpu()
using_gpu = True
xp = model.xp
# 0 -> true sample
# 1 -> generated sample
class_true = np.zeros(args.batchsize, dtype=np.int32)
class_fake = np.ones(args.batchsize, dtype=np.int32)
if using_gpu:
class_true = cuda.to_gpu(class_true)
class_fake = cuda.to_gpu(class_fake)
training_start_time = time.time()
for epoch in range(args.total_epochs):
sum_loss_generator = 0
sum_loss_discriminator = 0
sum_loss_autoencoder = 0
sum_discriminator_confidence_true = 0
sum_discriminator_confidence_fake = 0
epoch_start_time = time.time()
dataset.shuffle()
# training
for itr in range(total_iterations_train):
# update model parameters
with chainer.using_config("train", True):
x_l, y_l, y_onehot_l = dataset.sample_minibatch(args.batchsize, gpu=using_gpu)
### reconstruction phase ###
if True:
z_fake_l = model.encode_x_z(x_l)
x_reconstruction_l = model.decode_yz_x(y_onehot_l, z_fake_l)
loss_reconstruction = F.mean_squared_error(x_l, x_reconstruction_l)
model.cleargrads()
loss_reconstruction.backward()
optimizer_encoder.update()
optimizer_decoder.update()
### adversarial phase ###
if True:
z_fake_l = model.encode_x_z(x_l)
z_true_batch = sampler.gaussian(args.batchsize, model.ndim_z, mean=0, var=1)
if using_gpu:
z_true_batch = cuda.to_gpu(z_true_batch)
dz_true = model.discriminate_z(z_true_batch, apply_softmax=False)
dz_fake = model.discriminate_z(z_fake_l, apply_softmax=False)
discriminator_confidence_true = float(xp.mean(F.softmax(dz_true).data[:, 0]))
discriminator_confidence_fake = float(xp.mean(F.softmax(dz_fake).data[:, 1]))
loss_discriminator = F.softmax_cross_entropy(dz_true, class_true) + F.softmax_cross_entropy(dz_fake, class_fake)
model.cleargrads()
loss_discriminator.backward()
#.........这里部分代码省略.........
示例2: main
# 需要导入模块: from model import Model [as 别名]
# 或者: from model.Model import cleargrads [as 别名]
#.........这里部分代码省略.........
sum_loss_autoencoder = 0
sum_loss_supervised = 0
sum_loss_linear_transformation = 0
sum_discriminator_z_confidence_true = 0
sum_discriminator_z_confidence_fake = 0
sum_discriminator_y_confidence_true = 0
sum_discriminator_y_confidence_fake = 0
epoch_start_time = time.time()
dataset.shuffle()
# training
for itr in range(total_iterations_train):
# update model parameters
with chainer.using_config("train", True):
# sample minibatch
x_u = dataset.sample_unlabeled_minibatch(args.batchsize, gpu=using_gpu)
x_l, y_l, _ = dataset.sample_labeled_minibatch(args.batchsize, gpu=using_gpu)
### reconstruction phase ###
if True:
y_onehot_u, z_u = model.encode_x_yz(x_u, apply_softmax_y=True)
repr_u = model.encode_yz_representation(y_onehot_u, z_u)
x_reconstruction_u = model.decode_representation_x(repr_u)
loss_reconstruction_u = F.mean_squared_error(x_u, x_reconstruction_u)
y_onehot_l, z_l = model.encode_x_yz(x_l, apply_softmax_y=True)
repr_l = model.encode_yz_representation(y_onehot_l, z_l)
x_reconstruction_l = model.decode_representation_x(repr_l)
loss_reconstruction_l = F.mean_squared_error(x_l, x_reconstruction_l)
loss_reconstruction = loss_reconstruction_u + loss_reconstruction_l
model.cleargrads()
loss_reconstruction.backward()
optimizer_encoder.update()
optimizer_decoder.update()
sum_loss_autoencoder += float(loss_reconstruction.data)
### adversarial phase ###
if True:
y_onehot_fake_u, z_fake_u = model.encode_x_yz(x_u, apply_softmax_y=True)
z_true = sampler.gaussian(args.batchsize, model.ndim_y, mean=0, var=1)
y_onehot_true = sampler.onehot_categorical(args.batchsize, model.ndim_y)
if using_gpu:
z_true = cuda.to_gpu(z_true)
y_onehot_true = cuda.to_gpu(y_onehot_true)
dz_true = model.discriminate_z(z_true, apply_softmax=False)
dz_fake = model.discriminate_z(z_fake_u, apply_softmax=False)
dy_true = model.discriminate_y(y_onehot_true, apply_softmax=False)
dy_fake = model.discriminate_y(y_onehot_fake_u, apply_softmax=False)
discriminator_z_confidence_true = float(xp.mean(F.softmax(dz_true).data[:, 0]))
discriminator_z_confidence_fake = float(xp.mean(F.softmax(dz_fake).data[:, 1]))
discriminator_y_confidence_true = float(xp.mean(F.softmax(dy_true).data[:, 0]))
discriminator_y_confidence_fake = float(xp.mean(F.softmax(dy_fake).data[:, 1]))
loss_discriminator_z = F.softmax_cross_entropy(dz_true, class_true) + F.softmax_cross_entropy(dz_fake, class_fake)
loss_discriminator_y = F.softmax_cross_entropy(dy_true, class_true) + F.softmax_cross_entropy(dy_fake, class_fake)
loss_discriminator = loss_discriminator_z + loss_discriminator_y
model.cleargrads()
loss_discriminator.backward()示例3: main
# 需要导入模块: from model import Model [as 别名]
# 或者: from model.Model import cleargrads [as 别名]
#.........这里部分代码省略.........
if using_gpu:
class_true = cuda.to_gpu(class_true)
class_fake = cuda.to_gpu(class_fake)
training_start_time = time.time()
for epoch in range(args.total_epochs):
sum_loss_generator = 0
sum_loss_discriminator = 0
sum_loss_autoencoder = 0
sum_loss_cluster_head = 0
sum_discriminator_z_confidence_true = 0
sum_discriminator_z_confidence_fake = 0
sum_discriminator_y_confidence_true = 0
sum_discriminator_y_confidence_fake = 0
epoch_start_time = time.time()
dataset.shuffle()
# training
for itr in range(total_iterations_train):
# update model parameters
with chainer.using_config("train", True):
# sample minibatch
x_u, _, _ = dataset.sample_minibatch(args.batchsize, gpu=using_gpu)
### reconstruction phase ###
if True:
y_onehot_u, z_u = model.encode_x_yz(x_u, apply_softmax_y=True)
repr_u = model.encode_yz_representation(y_onehot_u, z_u)
x_reconstruction_u = model.decode_representation_x(repr_u)
loss_reconstruction = F.mean_squared_error(x_u, x_reconstruction_u)
model.cleargrads()
loss_reconstruction.backward()
optimizer_encoder.update()
optimizer_cluster_head.update()
optimizer_decoder.update()
### adversarial phase ###
if True:
y_onehot_fake_u, z_fake_u = model.encode_x_yz(x_u, apply_softmax_y=True)
z_true = sampler.gaussian(args.batchsize, model.ndim_z, mean=0, var=1)
y_onehot_true = sampler.onehot_categorical(args.batchsize, model.ndim_y)
if using_gpu:
z_true = cuda.to_gpu(z_true)
y_onehot_true = cuda.to_gpu(y_onehot_true)
dz_true = model.discriminate_z(z_true, apply_softmax=False)
dz_fake = model.discriminate_z(z_fake_u, apply_softmax=False)
dy_true = model.discriminate_y(y_onehot_true, apply_softmax=False)
dy_fake = model.discriminate_y(y_onehot_fake_u, apply_softmax=False)
discriminator_z_confidence_true = float(xp.mean(F.softmax(dz_true).data[:, 0]))
discriminator_z_confidence_fake = float(xp.mean(F.softmax(dz_fake).data[:, 1]))
discriminator_y_confidence_true = float(xp.mean(F.softmax(dy_true).data[:, 0]))
discriminator_y_confidence_fake = float(xp.mean(F.softmax(dy_fake).data[:, 1]))
loss_discriminator_z = F.softmax_cross_entropy(dz_true, class_true) + F.softmax_cross_entropy(dz_fake, class_fake)
loss_discriminator_y = F.softmax_cross_entropy(dy_true, class_true) + F.softmax_cross_entropy(dy_fake, class_fake)
loss_discriminator = loss_discriminator_z + loss_discriminator_y
model.cleargrads()
loss_discriminator.backward()
optimizer_discriminator_z.update()