"""
Modified from https://github.com/iamhankai/ghostnet.pytorch/blob/master/ghost_net.py
"""
import math
from typing import Any
import oneflow as flow
import oneflow.nn as nn
import oneflow.nn.functional as F
from .registry import ModelCreator
from .utils import load_state_dict_from_url
from .helpers import make_divisible
__all__ = ["ghostnet"]
model_urls = {
"ghostnet": "https://oneflow-public.oss-cn-beijing.aliyuncs.com/model_zoo/flowvision/classification/GhostNet/ghostnet.zip",
}
def hard_sigmoid(x, inplace: bool = False):
if inplace:
return x.add_(3.0).clamp_(0.0, 6.0).div_(6.0)
else:
# F.hardtanh(x, min_val=0, max_val=6) == F.relu6(x)
return F.hardtanh(x + 3.0, min_val=0.0, max_val=6.0) / 6.0
# return F.relu6(x + 3.) / 6.#TODO lack F.relu6
class SqueezeExcite(nn.Module):
def __init__(
self,
in_chs,
se_ratio=0.25,
reduced_base_chs=None,
act_layer=nn.ReLU,
gate_fn=hard_sigmoid,
divisor=4,
**_
):
super(SqueezeExcite, self).__init__()
self.gate_fn = gate_fn
reduced_chs = make_divisible((reduced_base_chs or in_chs) * se_ratio, divisor)
self.avg_pool = nn.AdaptiveAvgPool2d(1)
self.conv_reduce = nn.Conv2d(in_chs, reduced_chs, 1, bias=True)
self.act1 = act_layer(inplace=True)
self.conv_expand = nn.Conv2d(reduced_chs, in_chs, 1, bias=True)
def forward(self, x):
x_se = self.avg_pool(x)
x_se = self.conv_reduce(x_se)
x_se = self.act1(x_se)
x_se = self.conv_expand(x_se)
x = x * self.gate_fn(x_se)
return x
class ConvBnAct(nn.Module):
def __init__(self, in_chs, out_chs, kernel_size, stride=1, act_layer=nn.ReLU):
super(ConvBnAct, self).__init__()
self.conv = nn.Conv2d(
in_chs, out_chs, kernel_size, stride, kernel_size // 2, bias=False
)
self.bn1 = nn.BatchNorm2d(out_chs)
self.act1 = act_layer(inplace=True)
def forward(self, x):
x = self.conv(x)
x = self.bn1(x)
x = self.act1(x)
return x
class GhostModule(nn.Module):
def __init__(
self, inp, oup, kernel_size=1, ratio=2, dw_size=3, stride=1, relu=True
):
super(GhostModule, self).__init__()
self.oup = oup
init_channels = math.ceil(oup / ratio)
new_channels = init_channels * (ratio - 1)
self.primary_conv = nn.Sequential(
nn.Conv2d(
inp, init_channels, kernel_size, stride, kernel_size // 2, bias=False
),
nn.BatchNorm2d(init_channels),
nn.ReLU(inplace=True) if relu else nn.Sequential(),
)
self.cheap_operation = nn.Sequential(
nn.Conv2d(
init_channels,
new_channels,
dw_size,
1,
dw_size // 2,
groups=init_channels,
bias=False,
),
nn.BatchNorm2d(new_channels),
nn.ReLU(inplace=True) if relu else nn.Sequential(),
)
def forward(self, x):
x1 = self.primary_conv(x)
x2 = self.cheap_operation(x1)
out = flow.cat([x1, x2], dim=1)
return out[:, : self.oup, :, :]
class GhostBottleneck(nn.Module):
""" Ghost bottleneck w/ optional SE"""
def __init__(
self,
in_chs,
mid_chs,
out_chs,
dw_kernel_size=3,
stride=1,
act_layer=nn.ReLU,
se_ratio=0.0,
):
super(GhostBottleneck, self).__init__()
has_se = se_ratio is not None and se_ratio > 0.0
self.stride = stride
# Point-wise expansion
self.ghost1 = GhostModule(in_chs, mid_chs, relu=True)
# Depth-wise convolution
if self.stride > 1:
self.conv_dw = nn.Conv2d(
mid_chs,
mid_chs,
dw_kernel_size,
stride=stride,
padding=(dw_kernel_size - 1) // 2,
groups=mid_chs,
bias=False,
)
self.bn_dw = nn.BatchNorm2d(mid_chs)
# Squeeze-and-excitation
if has_se:
self.se = SqueezeExcite(mid_chs, se_ratio=se_ratio)
else:
self.se = None
# Point-wise linear projection
self.ghost2 = GhostModule(mid_chs, out_chs, relu=False)
# shortcut
if in_chs == out_chs and self.stride == 1:
self.shortcut = nn.Sequential()
else:
self.shortcut = nn.Sequential(
nn.Conv2d(
in_chs,
in_chs,
dw_kernel_size,
stride=stride,
padding=(dw_kernel_size - 1) // 2,
groups=in_chs,
bias=False,
),
nn.BatchNorm2d(in_chs),
nn.Conv2d(in_chs, out_chs, 1, stride=1, padding=0, bias=False),
nn.BatchNorm2d(out_chs),
)
def forward(self, x):
residual = x
# 1st ghost bottleneck
x = self.ghost1(x)
# Depth-wise convolution
if self.stride > 1:
x = self.conv_dw(x)
x = self.bn_dw(x)
# Squeeze-and-excitation
if self.se is not None:
x = self.se(x)
# 2nd ghost bottleneck
x = self.ghost2(x)
x += self.shortcut(residual)
return x
class GhostNet(nn.Module):
def __init__(self, cfgs, num_classes=1000, width=1.0, dropout=0.2):
super(GhostNet, self).__init__()
# setting of inverted residual blocks
self.cfgs = cfgs
self.dropout = dropout
# building first layer
output_channel = make_divisible(16 * width, 4)
self.conv_stem = nn.Conv2d(3, output_channel, 3, 2, 1, bias=False)
self.bn1 = nn.BatchNorm2d(output_channel)
self.act1 = nn.ReLU(inplace=True)
input_channel = output_channel
# building inverted residual blocks
stages = []
block = GhostBottleneck
for cfg in self.cfgs:
layers = []
for k, exp_size, c, se_ratio, s in cfg:
output_channel = make_divisible(c * width, 4)
hidden_channel = make_divisible(exp_size * width, 4)
layers.append(
block(
input_channel,
hidden_channel,
output_channel,
k,
s,
se_ratio=se_ratio,
)
)
input_channel = output_channel
stages.append(nn.Sequential(*layers))
output_channel = make_divisible(exp_size * width, 4)
stages.append(nn.Sequential(ConvBnAct(input_channel, output_channel, 1)))
input_channel = output_channel
self.blocks = nn.Sequential(*stages)
# building last several layers
output_channel = 1280
self.global_pool = nn.AdaptiveAvgPool2d((1, 1))
self.conv_head = nn.Conv2d(input_channel, output_channel, 1, 1, 0, bias=True)
self.act2 = nn.ReLU(inplace=True)
self.classifier = nn.Linear(output_channel, num_classes)
def forward(self, x):
x = self.conv_stem(x)
x = self.bn1(x)
x = self.act1(x)
x = self.blocks(x)
x = self.global_pool(x)
x = self.conv_head(x)
x = self.act2(x)
x = x.view(x.size(0), -1)
if self.dropout > 0.0:
x = F.dropout(x, p=self.dropout, training=self.training)
x = self.classifier(x)
return x
[docs]@ModelCreator.register_model
def ghostnet(pretrained: bool = False, progress: bool = True, **kwargs: Any):
"""
Constructs the GhostNet model.
.. note::
GhostNet model from `GhostNet: More Features from Cheap Operations <https://arxiv.org/abs/1911.11907>`_.
Args:
pretrained (bool): Whether to download the pre-trained model on ImageNet. Default: ``False``
progress (bool): If True, displays a progress bar of the download to stderr. Default: ``True``
For example:
.. code-block:: python
>>> import flowvision
>>> ghostnet = flowvision.models.ghostnet(pretrained=True, progress=True)
"""
cfgs = [
# k, t, c, SE, s
# stage1
[[3, 16, 16, 0, 1]],
# stage2
[[3, 48, 24, 0, 2]],
[[3, 72, 24, 0, 1]],
# stage3
[[5, 72, 40, 0.25, 2]],
[[5, 120, 40, 0.25, 1]],
# stage4
[[3, 240, 80, 0, 2]],
[
[3, 200, 80, 0, 1],
[3, 184, 80, 0, 1],
[3, 184, 80, 0, 1],
[3, 480, 112, 0.25, 1],
[3, 672, 112, 0.25, 1],
],
# stage5
[[5, 672, 160, 0.25, 2]],
[
[5, 960, 160, 0, 1],
[5, 960, 160, 0.25, 1],
[5, 960, 160, 0, 1],
[5, 960, 160, 0.25, 1],
],
]
model = GhostNet(cfgs, **kwargs)
if pretrained:
arch = "ghostnet"
if model_urls.get(arch, None) is None:
raise ValueError(
"No checkpoint is available for model type {}".format(arch)
)
state_dict = load_state_dict_from_url(model_urls[arch], progress=progress)
model.load_state_dict(state_dict)
return model