def __init__(self, scales, ratios, fg_threshold, bg_threshold,
batch_size_per_image, positive_fraction,
pre_nms_top_n_in_train, post_nms_top_n_in_train,
pre_nms_top_n_in_test, post_nms_top_n_in_test, nms_thresh,
**kwargs):
super(RegionProposalNetwork, self).__init__(**kwargs)
self.scales = scales
self.ratios = ratios
self.max_num_anchors_per_position = 0
for k, _scales in scales.items():
num_anchors_per_position = 0
_ratios = ratios[k]
for i, scale in enumerate(_scales):
num_anchors_per_position += len(_ratios[i])
if num_anchors_per_position > self.max_num_anchors_per_position:
self.max_num_anchors_per_position = num_anchors_per_position
with self.name_scope():
self.head = nn.Conv2D(256, 3, padding=1, activation="relu")
self.object_cls = nn.Conv2D(self.max_num_anchors_per_position, 1)
self.object_reg = nn.Conv2D(self.max_num_anchors_per_position * 4,
1)
self._anchors = dict()
self.fg_threshold = fg_threshold
self.bg_threshold = bg_threshold
self.batch_size_per_image = batch_size_per_image
self.positive_fraction = positive_fraction
self.pre_nms_top_n_in_train = pre_nms_top_n_in_train
self.post_nms_top_n_in_train = post_nms_top_n_in_train
self.pre_nms_top_n_in_test = pre_nms_top_n_in_test
self.post_nms_top_n_in_test = post_nms_top_n_in_test
self.nms_thresh = nms_thresh
self.object_cls_loss = gloss.SigmoidBCELoss()
self.object_reg_loss = gloss.HuberLoss()
def __init__(self, ctx=mx.cpu(), warmup=10, runs=50, inputs=None):
# Set the default Inputs.
# Default prediction is (32, 1000, 1) to mimic a prediction of batch_size=32 and 1000 class classification.
default_parameters = {
"pred": (32, 1000, 1),
"pred_initializer": nd.ones,
"label": (32, 1000, 1),
"label_initializer": nd.zeros,
"weight": 1.0,
"run_backward": False,
"dtype": "float32"
}
super().__init__(ctx=ctx,
warmup=warmup,
runs=runs,
default_parameters=default_parameters,
custom_parameters=inputs)
# Create a random prediction and label tensor
self.pred = get_mx_ndarray(ctx=self.ctx,
in_tensor=self.inputs["pred"],
dtype=self.inputs["dtype"],
initializer=self.inputs["pred_initializer"],
attach_grad=self.inputs["run_backward"])
self.label = get_mx_ndarray(
ctx=self.ctx,
in_tensor=self.inputs["label"],
dtype=self.inputs["dtype"],
initializer=self.inputs["label_initializer"],
attach_grad=self.inputs["run_backward"])
self.block = loss.SigmoidBCELoss(from_sigmoid=False,
weight=self.inputs["weight"],
batch_axis=0)
self.block.initialize(ctx=self.ctx)
def build_model(self):
# DataLoader
train_transform = transforms.Compose([
transforms.RandomFlipLeftRight(),
transforms.Resize((self.img_size + 30, self.img_size + 30)),
transforms.RandomResizedCrop(self.img_size),
transforms.ToTensor(),
transforms.Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5))
])
test_transform = transforms.Compose([
transforms.Resize((self.img_size, self.img_size)),
transforms.ToTensor(),
transforms.Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5))
])
self.trainA = ImageFolder(
os.path.join('dataset', self.dataset, 'trainA'), train_transform)
self.trainB = ImageFolder(
os.path.join('dataset', self.dataset, 'trainB'), train_transform)
self.testA = ImageFolder(
os.path.join('dataset', self.dataset, 'testA'), test_transform)
self.testB = ImageFolder(
os.path.join('dataset', self.dataset, 'testB'), test_transform)
self.trainA_loader = DataLoader(self.trainA,
batch_size=self.batch_size,
shuffle=True,
num_workers=self.num_workers)
self.trainB_loader = DataLoader(self.trainB,
batch_size=self.batch_size,
shuffle=True,
num_workers=self.num_workers)
self.testA_loader = DataLoader(self.testA, batch_size=1, shuffle=False)
self.testB_loader = DataLoader(self.testB, batch_size=1, shuffle=False)
""" Define Generator, Discriminator """
self.genA2B = ResnetGenerator(input_nc=3,
output_nc=3,
ngf=self.ch,
n_blocks=self.n_res,
img_size=self.img_size,
light=self.light)
self.genB2A = ResnetGenerator(input_nc=3,
output_nc=3,
ngf=self.ch,
n_blocks=self.n_res,
img_size=self.img_size,
light=self.light)
self.disGA = Discriminator(input_nc=3, ndf=self.ch, n_layers=7)
self.disGB = Discriminator(input_nc=3, ndf=self.ch, n_layers=7)
self.disLA = Discriminator(input_nc=3, ndf=self.ch, n_layers=5)
self.disLB = Discriminator(input_nc=3, ndf=self.ch, n_layers=5)
self.whole_model = nn.HybridSequential()
self.whole_model.add(*[
self.genA2B, self.genB2A, self.disGA, self.disGB, self.disLA,
self.disLB
])
self.whole_model.hybridize(static_alloc=False, static_shape=False)
""" Define Loss """
self.L1_loss = gloss.L1Loss()
self.MSE_loss = gloss.L2Loss(weight=2)
self.BCE_loss = gloss.SigmoidBCELoss()
""" Initialize Parameters"""
params = self.whole_model.collect_params()
block = self.whole_model
if not self.debug:
force_init(block.collect_params('.*?_weight'), KaimingUniform())
force_init(block.collect_params('.*?_bias'),
BiasInitializer(params))
block.collect_params('.*?_rho').initialize()
block.collect_params('.*?_gamma').initialize()
block.collect_params('.*?_beta').initialize()
block.collect_params('.*?_state_.*?').initialize()
else:
pass
block.collect_params().reset_ctx(self.dev)
""" Trainer """
self.G_params = param_dicts_merge(
self.genA2B.collect_params(),
self.genB2A.collect_params(),
)
self.G_optim = gluon.Trainer(
self.G_params,
'adam',
dict(learning_rate=self.lr,
beta1=0.5,
beta2=0.999,
wd=self.weight_decay),
)
self.D_params = param_dicts_merge(self.disGA.collect_params(),
self.disGB.collect_params(),
self.disLA.collect_params(),
self.disLB.collect_params())
self.D_optim = gluon.Trainer(
self.D_params,
'adam',
dict(learning_rate=self.lr,
beta1=0.5,
beta2=0.999,
wd=self.weight_decay),
)
""" Define Rho clipper to constraint the value of rho in AdaILN and ILN"""
self.Rho_clipper = RhoClipper(0, 1)
def __init__(self):
super(MyLoss3, self).__init__()
self.loss1 = loss.SoftmaxCELoss()
self.loss2 = loss.SigmoidBCELoss()
def __init__(self):
super(MyLoss, self).__init__()
self.loss = loss.SigmoidBCELoss()
transform=transforms.Compose([transforms.Resize(64), transforms.CenterCrop(64),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5),
(0.5, 0.5, 0.5))]))
data_loader = DataLoader(dataset, batch_size=batch_size, shuffle=True, last_batch='discard', num_workers=4)
netG = generator.Generator()
netD = discriminator.Discriminator()
netG.initialize(init=init.Normal(sigma=0.02))
netD.initialize(init=init.Normal(sigma=0.02))
trainerG = Trainer(netG.collect_params(), 'adam', {'learning_rate': lr, 'momentum': momentum})
trainerD = Trainer(netD.collect_params(), 'adam', {'learning_rate': lr, 'momentum': momentum})
loss = gloss.SigmoidBCELoss()
for epoch in range(epoches):
for i, batch in enumerate(data_loader):
data_real = batch[0]
labels_real = nd.ones(shape=(batch_size, ))
z = nd.random.randn(batch_size, 100, 1, 1)
data_fake = netG(z)
labels_fake = nd.zeros(shape=(batch_size, ))
with autograd.record():
preds_real = netD(data_real)
lo_real = loss(preds_real, labels_real)
preds_fake = netD(data_fake)
lo_fake = loss(preds_fake, labels_fake)
err_D = preds_real + preds_fake
