def __init__(self, in_, out_, expand,
kernel_size, stride, skip,
se_ratio, dc_ratio=0.2):
super().__init__()
mid_ = in_ * expand
self.expand_conv = conv_bn_act(in_, mid_, kernel_size=1, bias=False) if expand != 1 else nn.Identity()
self.depth_wise_conv = conv_bn_act(mid_, mid_,
kernel_size=kernel_size, stride=stride,
groups=mid_, bias=False)
self.se = SEModule(mid_, int(in_ * se_ratio)) if se_ratio > 0 else nn.Identity()
self.project_conv = nn.Sequential(
SamePadConv2d(mid_, out_, kernel_size=1, stride=1, bias=False),
nn.BatchNorm2d(out_, 1e-3, 0.01)
)
# if _block_args.id_skip:
# and all(s == 1 for s in self._block_args.strides)
# and self._block_args.input_filters == self._block_args.output_filters:
self.skip = skip and (stride == 1) and (in_ == out_)
# DropConnect
# self.dropconnect = DropConnect(dc_ratio) if dc_ratio > 0 else nn.Identity()
# Original TF Repo not using drop_rate
# https://github.com/tensorflow/tpu/blob/05f7b15cdf0ae36bac84beb4aef0a09983ce8f66/models/official/efficientnet/efficientnet_model.py#L408
self.dropconnect = nn.Identity()
def __init__(self,
width_coeff,
depth_coeff,
depth_div=8,
min_depth=None,
dropout_rate=0.2,
drop_connect_rate=0.2,
num_classes=1000):
super().__init__()
min_depth = min_depth or depth_div
def renew_ch(x):
if not width_coeff:
return x
x *= width_coeff
new_x = max(min_depth,
int(x + depth_div / 2) // depth_div * depth_div)
if new_x < 0.9 * x:
new_x += depth_div
return int(new_x)
def renew_repeat(x):
return int(math.ceil(x * depth_coeff))
self.stem = conv_bn_act(3,
renew_ch(32),
kernel_size=3,
stride=2,
bias=False)
self.blocks = nn.Sequential(
# input channel output expand k s skip se
MBBlock(renew_ch(32), renew_ch(16), 1, 3, 1, renew_repeat(1), True,
0.25, drop_connect_rate),
MBBlock(renew_ch(16), renew_ch(24), 6, 3, 2, renew_repeat(2), True,
0.25, drop_connect_rate),
MBBlock(renew_ch(24), renew_ch(40), 6, 5, 2, renew_repeat(2), True,
0.25, drop_connect_rate),
MBBlock(renew_ch(40), renew_ch(80), 6, 3, 2, renew_repeat(3), True,
0.25, drop_connect_rate),
MBBlock(renew_ch(80), renew_ch(112), 6, 5, 1, renew_repeat(3),
True, 0.25, drop_connect_rate),
MBBlock(renew_ch(112), renew_ch(192), 6, 5, 2, renew_repeat(4),
True, 0.25, drop_connect_rate),
MBBlock(renew_ch(192), renew_ch(320), 6, 3, 1, renew_repeat(1),
True, 0.25, drop_connect_rate))
self.head = nn.Sequential(
*conv_bn_act(renew_ch(320),
renew_ch(1280),
kernel_size=1,
bias=False), nn.AdaptiveAvgPool2d(1),
nn.Dropout2d(dropout_rate, True)
if dropout_rate > 0 else nn.Identity(), Flatten(),
nn.Linear(renew_ch(1280), num_classes))
self.init_weights()