def build_model(self) -> nn.Module:
model = nn.Sequential(
nn.Conv2d(NUM_CHANNELS, IMAGE_SIZE, kernel_size=(3, 3)),
nn.ReLU(),
nn.Conv2d(32, 32, kernel_size=(3, 3)),
nn.ReLU(),
nn.MaxPool2d((2, 2)),
nn.Dropout2d(self.context.get_hparam("layer1_dropout")),
nn.Conv2d(32, 64, (3, 3), padding=1),
nn.ReLU(),
nn.Conv2d(64, 64, (3, 3)),
nn.ReLU(),
nn.MaxPool2d((2, 2)),
nn.Dropout2d(self.context.get_hparam("layer2_dropout")),
Flatten(),
nn.Linear(2304, 512),
nn.ReLU(),
nn.Dropout2d(self.context.get_hparam("layer3_dropout")),
nn.Linear(512, NUM_CLASSES),
nn.Softmax(dim=0),
)
# If loading backbone weights, do not call reset_parameters() or
# call before loading the backbone weights.
reset_parameters(model)
return model
def build_model(self) -> nn.Module:
model = MultiNet(self.context)
# If loading backbone weights, do not call reset_parameters() or
# call before loading the backbone weights.
reset_parameters(model)
return model
def __init__(self, context):
super(XORNet, self).__init__()
self.main_net = nn.Sequential(
nn.Linear(2, context.get_hparam("hidden_size")),
nn.Sigmoid(),
nn.Linear(context.get_hparam("hidden_size"), 1),
nn.Sigmoid(),
)
pytorch.reset_parameters(self.main_net)
def build_model(self) -> nn.Module:
genotype = self.get_genotype_from_hps()
model = Network(
self.hparams["init_channels"],
10, # num_classes
self.hparams["layers"],
self.hparams["auxiliary"],
genotype,
)
print("param size = {} MB".format(utils.count_parameters_in_MB(model)))
size = 0
for p in model.parameters():
size += p.nelement()
print("param count: {}".format(size))
# If loading backbone weights, do not call reset_parameters() or
# call before loading the backbone weights.
reset_parameters(model)
return model
def build_model(self) -> nn.Module:
genotype = Genotype(
normal=[
("skip_connect", 1),
("skip_connect", 0),
("sep_conv_3x3", 2),
("sep_conv_3x3", 1),
("sep_conv_5x5", 2),
("sep_conv_3x3", 0),
("sep_conv_5x5", 3),
("sep_conv_5x5", 2),
],
normal_concat=range(2, 6),
reduce=[
("max_pool_3x3", 1),
("sep_conv_3x3", 0),
("sep_conv_5x5", 1),
("dil_conv_5x5", 2),
("sep_conv_3x3", 1),
("sep_conv_3x3", 3),
("sep_conv_5x5", 1),
("max_pool_3x3", 2),
],
reduce_concat=range(2, 6),
)
activation_function = activation_map[self.context.get_hparam("activation")]
model = NetworkImageNet(
genotype,
activation_function,
self.context.get_hparam("init_channels"),
self.context.get_hparam("num_classes"),
self.context.get_hparam("layers"),
auxiliary=self.context.get_hparam("auxiliary"),
do_SE=self.context.get_hparam("do_SE"),
)
# If loading backbone weights, do not call reset_parameters() or
# call before loading the backbone weights.
reset_parameters(model)
return model
def build_model(self) -> nn.Module:
genotype = self.get_genotype_from_hps()
model = RNNModel(
self.ntokens,
self.hparams.emsize,
self.hparams.nhid,
self.hparams.nhidlast,
self.hparams.dropout,
self.hparams.dropouth,
self.hparams.dropoutx,
self.hparams.dropouti,
self.hparams.dropoute,
genotype=genotype,
)
total_params = sum(x.data.nelement() for x in model.parameters())
logging.info("Model total parameters: {}".format(total_params))
# If loading backbone weights, do not call reset_parameters() or
# call before loading the backbone weights.
reset_parameters(model)
return model
def build_model(self) -> nn.Module:
model = nn.Sequential(
nn.Conv2d(1, self.context.get_hparam("n_filters1"), 3, 1),
nn.ReLU(),
nn.Conv2d(
self.context.get_hparam("n_filters1"), self.context.get_hparam("n_filters2"), 3,
),
nn.ReLU(),
nn.MaxPool2d(2),
nn.Dropout2d(self.context.get_hparam("dropout1")),
Flatten(),
nn.Linear(144 * self.context.get_hparam("n_filters2"), 128),
nn.ReLU(),
nn.Dropout2d(self.context.get_hparam("dropout2")),
nn.Linear(128, 10),
nn.LogSoftmax(),
)
# If loading backbone weights, do not call reset_parameters() or
# call before loading the backbone weights.
reset_parameters(model)
return model
