This implements the paper:
Golnaz Ghiasi, Tsung-Yi Lin, Ruoming Pang, Quoc V. Le.
NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection.
(https://arxiv.org/abs/1904.07392)
Args
input_specs
A dict of input specifications. A dictionary consists of
{level: TensorShape} from a backbone.
min_level
An int of minimum level in FPN output feature maps.
max_level
An int of maximum level in FPN output feature maps.
block_specs
a list of BlockSpec objects that specifies the NAS-FPN
network topology. By default, the previously discovered architecture is
used.
num_filters
An int number of filters in FPN layers.
num_repeats
number of repeats for feature pyramid network.
use_separable_conv
A bool. If True use separable convolution for
convolution in FPN layers.
activation
A str name of the activation function.
use_sync_bn
A bool. If True, use synchronized batch normalization.
norm_momentum
A float of normalization momentum for the moving average.
norm_epsilon
A float added to variance to avoid dividing by zero.
kernel_initializer
A str name of kernel_initializer for convolutional
layers.