def test_make_divisible():
# test min_value is None
result = make_divisible(34, 8, None)
assert result == 32
# test when new_value > min_ratio * value
result = make_divisible(10, 8, min_ratio=0.9)
assert result == 16
# test min_value = 0.8
result = make_divisible(33, 8, min_ratio=0.8)
assert result == 32
def make_layer(self):
# Without the first and the final conv block.
layer_setting = self.layer_setting[1:-1]
total_num_blocks = sum([len(x) for x in layer_setting])
block_idx = 0
dpr = [
x.item()
for x in torch.linspace(0, self.drop_path_rate, total_num_blocks)
] # stochastic depth decay rule
for layer_cfg in layer_setting:
layer = []
for i, block_cfg in enumerate(layer_cfg):
(kernel_size, out_channels, se_ratio, stride, expand_ratio,
block_type) = block_cfg
mid_channels = int(self.in_channels * expand_ratio)
out_channels = make_divisible(out_channels, 8)
if se_ratio <= 0:
se_cfg = None
else:
se_cfg = dict(channels=mid_channels,
ratio=expand_ratio * se_ratio,
divisor=1,
act_cfg=(self.act_cfg, dict(type='Sigmoid')))
if block_type == 1: # edge tpu
if i > 0 and expand_ratio == 3:
with_residual = False
expand_ratio = 4
else:
with_residual = True
mid_channels = int(self.in_channels * expand_ratio)
if se_cfg is not None:
se_cfg = dict(channels=mid_channels,
ratio=se_ratio * expand_ratio,
divisor=1,
act_cfg=(self.act_cfg,
dict(type='Sigmoid')))
block = partial(EdgeResidual, with_residual=with_residual)
else:
block = InvertedResidual
layer.append(
block(in_channels=self.in_channels,
out_channels=out_channels,
mid_channels=mid_channels,
kernel_size=kernel_size,
stride=stride,
se_cfg=se_cfg,
conv_cfg=self.conv_cfg,
norm_cfg=self.norm_cfg,
act_cfg=self.act_cfg,
drop_path_rate=dpr[block_idx],
with_cp=self.with_cp))
self.in_channels = out_channels
block_idx += 1
self.layers.append(Sequential(*layer))
def model_scaling(layer_setting, arch_setting):
"""Scaling operation to the layer's parameters according to the
arch_setting."""
# scale width
new_layer_setting = copy.deepcopy(layer_setting)
for layer_cfg in new_layer_setting:
for block_cfg in layer_cfg:
block_cfg[1] = make_divisible(block_cfg[1] * arch_setting[0], 8)
# scale depth
split_layer_setting = [new_layer_setting[0]]
for layer_cfg in new_layer_setting[1:-1]:
tmp_index = [0]
for i in range(len(layer_cfg) - 1):
if layer_cfg[i + 1][1] != layer_cfg[i][1]:
tmp_index.append(i + 1)
tmp_index.append(len(layer_cfg))
for i in range(len(tmp_index) - 1):
split_layer_setting.append(layer_cfg[tmp_index[i]:tmp_index[i +
1]])
split_layer_setting.append(new_layer_setting[-1])
num_of_layers = [len(layer_cfg) for layer_cfg in split_layer_setting[1:-1]]
new_layers = [
int(math.ceil(arch_setting[1] * num)) for num in num_of_layers
]
merge_layer_setting = [split_layer_setting[0]]
for i, layer_cfg in enumerate(split_layer_setting[1:-1]):
if new_layers[i] <= num_of_layers[i]:
tmp_layer_cfg = layer_cfg[:new_layers[i]]
else:
tmp_layer_cfg = copy.deepcopy(layer_cfg) + [layer_cfg[-1]] * (
new_layers[i] - num_of_layers[i])
if tmp_layer_cfg[0][3] == 1 and i != 0:
merge_layer_setting[-1] += tmp_layer_cfg.copy()
else:
merge_layer_setting.append(tmp_layer_cfg.copy())
merge_layer_setting.append(split_layer_setting[-1])
return merge_layer_setting
def __init__(self,
widen_factor=1.,
out_indices=(7, ),
frozen_stages=-1,
conv_cfg=None,
norm_cfg=dict(type='BN'),
act_cfg=dict(type='ReLU6'),
norm_eval=False,
with_cp=False):
super(MobileNetV2, self).__init__()
self.widen_factor = widen_factor
self.out_indices = out_indices
for index in out_indices:
if index not in range(0, 8):
raise ValueError('the item in out_indices must in '
f'range(0, 8). But received {index}')
if frozen_stages not in range(-1, 8):
raise ValueError('frozen_stages must be in range(-1, 8). '
f'But received {frozen_stages}')
self.out_indices = out_indices
self.frozen_stages = frozen_stages
self.conv_cfg = conv_cfg
self.norm_cfg = norm_cfg
self.act_cfg = act_cfg
self.norm_eval = norm_eval
self.with_cp = with_cp
self.in_channels = make_divisible(32 * widen_factor, 8)
self.conv1 = ConvModule(
in_channels=3,
out_channels=self.in_channels,
kernel_size=3,
stride=2,
padding=1,
conv_cfg=self.conv_cfg,
norm_cfg=self.norm_cfg,
act_cfg=self.act_cfg)
self.layers = []
for i, layer_cfg in enumerate(self.arch_settings):
expand_ratio, channel, num_blocks, stride = layer_cfg
out_channels = make_divisible(channel * widen_factor, 8)
inverted_res_layer = self.make_layer(
out_channels=out_channels,
num_blocks=num_blocks,
stride=stride,
expand_ratio=expand_ratio)
layer_name = f'layer{i + 1}'
self.add_module(layer_name, inverted_res_layer)
self.layers.append(layer_name)
if widen_factor > 1.0:
self.out_channel = int(1280 * widen_factor)
else:
self.out_channel = 1280
layer = ConvModule(
in_channels=self.in_channels,
out_channels=self.out_channel,
kernel_size=1,
stride=1,
padding=0,
conv_cfg=self.conv_cfg,
norm_cfg=self.norm_cfg,
act_cfg=self.act_cfg)
self.add_module('conv2', layer)
self.layers.append('conv2')
def __init__(self,
groups=3,
widen_factor=1.0,
out_indices=(2, ),
frozen_stages=-1,
conv_cfg=None,
norm_cfg=dict(type='BN'),
act_cfg=dict(type='ReLU'),
norm_eval=False,
with_cp=False,
init_cfg=None):
super(ShuffleNetV1, self).__init__(init_cfg)
self.init_cfg = init_cfg
self.stage_blocks = [4, 8, 4]
self.groups = groups
for index in out_indices:
if index not in range(0, 3):
raise ValueError('the item in out_indices must in '
f'range(0, 3). But received {index}')
if frozen_stages not in range(-1, 3):
raise ValueError('frozen_stages must be in range(-1, 3). '
f'But received {frozen_stages}')
self.out_indices = out_indices
self.frozen_stages = frozen_stages
self.conv_cfg = conv_cfg
self.norm_cfg = norm_cfg
self.act_cfg = act_cfg
self.norm_eval = norm_eval
self.with_cp = with_cp
if groups == 1:
channels = (144, 288, 576)
elif groups == 2:
channels = (200, 400, 800)
elif groups == 3:
channels = (240, 480, 960)
elif groups == 4:
channels = (272, 544, 1088)
elif groups == 8:
channels = (384, 768, 1536)
else:
raise ValueError(f'{groups} groups is not supported for 1x1 '
'Grouped Convolutions')
channels = [make_divisible(ch * widen_factor, 8) for ch in channels]
self.in_channels = int(24 * widen_factor)
self.conv1 = ConvModule(in_channels=3,
out_channels=self.in_channels,
kernel_size=3,
stride=2,
padding=1,
conv_cfg=conv_cfg,
norm_cfg=norm_cfg,
act_cfg=act_cfg)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layers = nn.ModuleList()
for i, num_blocks in enumerate(self.stage_blocks):
first_block = True if i == 0 else False
layer = self.make_layer(channels[i], num_blocks, first_block)
self.layers.append(layer)
def __init__(self,
arch='b0',
drop_path_rate=0.,
out_indices=(6, ),
frozen_stages=0,
conv_cfg=dict(type='Conv2dAdaptivePadding'),
norm_cfg=dict(type='BN', eps=1e-3),
act_cfg=dict(type='Swish'),
norm_eval=False,
with_cp=False,
init_cfg=[
dict(type='Kaiming', layer='Conv2d'),
dict(type='Constant',
layer=['_BatchNorm', 'GroupNorm'],
val=1)
]):
super(EfficientNet, self).__init__(init_cfg)
assert arch in self.arch_settings, \
f'"{arch}" is not one of the arch_settings ' \
f'({", ".join(self.arch_settings.keys())})'
self.arch_setting = self.arch_settings[arch]
self.layer_setting = self.layer_settings[arch[:1]]
for index in out_indices:
if index not in range(0, len(self.layer_setting)):
raise ValueError('the item in out_indices must in '
f'range(0, {len(self.layer_setting)}). '
f'But received {index}')
if frozen_stages not in range(len(self.layer_setting) + 1):
raise ValueError('frozen_stages must be in range(0, '
f'{len(self.layer_setting) + 1}). '
f'But received {frozen_stages}')
self.drop_path_rate = drop_path_rate
self.out_indices = out_indices
self.frozen_stages = frozen_stages
self.conv_cfg = conv_cfg
self.norm_cfg = norm_cfg
self.act_cfg = act_cfg
self.norm_eval = norm_eval
self.with_cp = with_cp
self.layer_setting = model_scaling(self.layer_setting,
self.arch_setting)
block_cfg_0 = self.layer_setting[0][0]
block_cfg_last = self.layer_setting[-1][0]
self.in_channels = make_divisible(block_cfg_0[1], 8)
self.out_channels = block_cfg_last[1]
self.layers = nn.ModuleList()
self.layers.append(
ConvModule(in_channels=3,
out_channels=self.in_channels,
kernel_size=block_cfg_0[0],
stride=block_cfg_0[3],
padding=block_cfg_0[0] // 2,
conv_cfg=self.conv_cfg,
norm_cfg=self.norm_cfg,
act_cfg=self.act_cfg))
self.make_layer()
self.layers.append(
ConvModule(in_channels=self.in_channels,
out_channels=self.out_channels,
kernel_size=block_cfg_last[0],
stride=block_cfg_last[3],
padding=block_cfg_last[0] // 2,
conv_cfg=self.conv_cfg,
norm_cfg=self.norm_cfg,
act_cfg=self.act_cfg))
def __init__(self,
arch_settings=None,
conv_cfg=None,
norm_cfg=dict(type='BN'),
act_cfg=dict(type='ReLU6'),
norm_eval=False,
with_cp=False):
super(UDFMobileNetV2, self).__init__()
if arch_settings is None:
arch_settings = [[1, 32, 1, 2], [1, 16, 1, 1], [6, 24, 2, 2],
[6, 32, 3, 2], [6, 64, 4, 2], [6, 96, 3, 1],
[6, 160, 3, 2], [6, 320, 1, 1], [1, 1280, 1, 1]]
widen_factor = 1.0
self.widen_factor = widen_factor
assert len(arch_settings) >= 6
first_layer_cfg = arch_settings[0]
assert first_layer_cfg[0] == 1
assert first_layer_cfg[2] == 1
assert first_layer_cfg[3] == 2
last_layer_cfg = arch_settings[-1]
assert last_layer_cfg[0] == 1
assert last_layer_cfg[2] == 1
assert last_layer_cfg[3] == 1
self.out_indices = (len(arch_settings) - 2, )
self.frozen_stages = -1
self.conv_cfg = conv_cfg
self.norm_cfg = norm_cfg
self.act_cfg = act_cfg
self.norm_eval = norm_eval
self.with_cp = with_cp
self.in_channels = make_divisible(first_layer_cfg[1] * widen_factor, 8)
self.conv1 = ConvModule(in_channels=3,
out_channels=self.in_channels,
kernel_size=3,
stride=2,
padding=1,
conv_cfg=self.conv_cfg,
norm_cfg=self.norm_cfg,
act_cfg=self.act_cfg)
self.layers = []
for i, layer_cfg in enumerate(arch_settings[1:-1]):
expand_ratio, channel, num_blocks, stride = layer_cfg
out_channels = make_divisible(channel * widen_factor, 8)
inverted_res_layer = self.make_layer(out_channels=out_channels,
num_blocks=num_blocks,
stride=stride,
expand_ratio=expand_ratio)
layer_name = f'layer{i + 1}'
self.add_module(layer_name, inverted_res_layer)
self.layers.append(layer_name)
self.out_channel = int(last_layer_cfg[1] * widen_factor)
layer = ConvModule(in_channels=self.in_channels,
out_channels=self.out_channel,
kernel_size=1,
stride=1,
padding=0,
conv_cfg=self.conv_cfg,
norm_cfg=self.norm_cfg,
act_cfg=self.act_cfg)
self.add_module('conv2', layer)
self.layers.append('conv2')
