OpenOCR-Demo / openrec /modeling /encoders /rec_mobilenet_v3.py
topdu's picture
openocr demo
29f689c
raw
history blame
4.83 kB
import torch.nn as nn
from .det_mobilenet_v3 import ConvBNLayer, ResidualUnit, make_divisible
class MobileNetV3(nn.Module):
def __init__(self,
in_channels=3,
model_name='small',
scale=0.5,
large_stride=None,
small_stride=None,
**kwargs):
super(MobileNetV3, self).__init__()
if small_stride is None:
small_stride = [2, 2, 2, 2]
if large_stride is None:
large_stride = [1, 2, 2, 2]
assert isinstance(
large_stride,
list), 'large_stride type must ' 'be list but got {}'.format(
type(large_stride))
assert isinstance(
small_stride,
list), 'small_stride type must ' 'be list but got {}'.format(
type(small_stride))
assert len(
large_stride
) == 4, 'large_stride length must be ' '4 but got {}'.format(
len(large_stride))
assert len(
small_stride
) == 4, 'small_stride length must be ' '4 but got {}'.format(
len(small_stride))
if model_name == 'large':
cfg = [
# k, exp, c, se, nl, s,
[3, 16, 16, False, 'relu', large_stride[0]],
[3, 64, 24, False, 'relu', (large_stride[1], 1)],
[3, 72, 24, False, 'relu', 1],
[5, 72, 40, True, 'relu', (large_stride[2], 1)],
[5, 120, 40, True, 'relu', 1],
[5, 120, 40, True, 'relu', 1],
[3, 240, 80, False, 'hard_swish', 1],
[3, 200, 80, False, 'hard_swish', 1],
[3, 184, 80, False, 'hard_swish', 1],
[3, 184, 80, False, 'hard_swish', 1],
[3, 480, 112, True, 'hard_swish', 1],
[3, 672, 112, True, 'hard_swish', 1],
[5, 672, 160, True, 'hard_swish', (large_stride[3], 1)],
[5, 960, 160, True, 'hard_swish', 1],
[5, 960, 160, True, 'hard_swish', 1],
]
cls_ch_squeeze = 960
elif model_name == 'small':
cfg = [
# k, exp, c, se, nl, s,
[3, 16, 16, True, 'relu', (small_stride[0], 1)],
[3, 72, 24, False, 'relu', (small_stride[1], 1)],
[3, 88, 24, False, 'relu', 1],
[5, 96, 40, True, 'hard_swish', (small_stride[2], 1)],
[5, 240, 40, True, 'hard_swish', 1],
[5, 240, 40, True, 'hard_swish', 1],
[5, 120, 48, True, 'hard_swish', 1],
[5, 144, 48, True, 'hard_swish', 1],
[5, 288, 96, True, 'hard_swish', (small_stride[3], 1)],
[5, 576, 96, True, 'hard_swish', 1],
[5, 576, 96, True, 'hard_swish', 1],
]
cls_ch_squeeze = 576
else:
raise NotImplementedError('mode[' + model_name +
'_model] is not implemented!')
supported_scale = [0.35, 0.5, 0.75, 1.0, 1.25]
assert scale in supported_scale, 'supported scales are {} but input scale is {}'.format(
supported_scale, scale)
inplanes = 16
# conv1
self.conv1 = ConvBNLayer(
in_channels=in_channels,
out_channels=make_divisible(inplanes * scale),
kernel_size=3,
stride=2,
padding=1,
groups=1,
if_act=True,
act='hard_swish',
)
i = 0
block_list = []
inplanes = make_divisible(inplanes * scale)
for k, exp, c, se, nl, s in cfg:
block_list.append(
ResidualUnit(
in_channels=inplanes,
mid_channels=make_divisible(scale * exp),
out_channels=make_divisible(scale * c),
kernel_size=k,
stride=s,
use_se=se,
act=nl,
name='conv' + str(i + 2),
))
inplanes = make_divisible(scale * c)
i += 1
self.blocks = nn.Sequential(*block_list)
self.conv2 = ConvBNLayer(
in_channels=inplanes,
out_channels=make_divisible(scale * cls_ch_squeeze),
kernel_size=1,
stride=1,
padding=0,
groups=1,
if_act=True,
act='hard_swish',
)
self.pool = nn.MaxPool2d(kernel_size=2, stride=2, padding=0)
self.out_channels = make_divisible(scale * cls_ch_squeeze)
def forward(self, x):
x = self.conv1(x)
x = self.blocks(x)
x = self.conv2(x)
x = self.pool(x)
return x