def __init__(self, blocks_args=None, global_params=None):
super().__init__()
assert isinstance(blocks_args, list), 'blocks_args should be a list'
assert len(blocks_args) > 0, 'block args must be greater than 0'
self._global_params = global_params
self._blocks_args = blocks_args
# 获得一种卷积方法，固定了image_size
Conv2d = get_same_padding_conv2d(image_size=global_params.image_size)
# 获得标准化的参数
bn_mom = 1 - self._global_params.batch_norm_momentum
bn_eps = self._global_params.batch_norm_epsilon
# 网络主干部分开始
# 设定输入进来的是RGB三通道图像
in_channels = 3
# 利用round_filters可以使得通道数在扩张的时候可以被8整除
out_channels = round_filters(32, self._global_params)
# 卷积+标准化
self._conv_stem = Conv2d(in_channels, out_channels, kernel_size=3, stride=2, bias=False)
self._bn0 = nn.BatchNorm2d(num_features=out_channels, momentum=bn_mom, eps=bn_eps)
# 对每个block的参数进行修改
self._blocks = nn.ModuleList([])
for i in range(len(self._blocks_args)):
# 对每个block的参数进行修改，根据所选的efficient版本进行修改
self._blocks_args[i] = self._blocks_args[i]._replace(
input_filters=round_filters(self._blocks_args[i].input_filters, self._global_params),
output_filters=round_filters(self._blocks_args[i].output_filters, self._global_params),
num_repeat=round_repeats(self._blocks_args[i].num_repeat, self._global_params)
)
# 第一次大的Block里面的卷积需要考虑步长和输入进来的通道数！
self._blocks.append(MBConvBlock(self._blocks_args[i], self._global_params))
if self._blocks_args[i].num_repeat > 1:
self._blocks_args[i] = self._blocks_args[i]._replace(input_filters=self._blocks_args[i].output_filters,
stride=1)
for _ in range(self._blocks_args[i].num_repeat - 1):
self._blocks.append(MBConvBlock(self._blocks_args[i], self._global_params))
# 增加了head部分
in_channels = self._blocks_args[len(self._blocks_args) - 1].output_filters
out_channels = round_filters(1280, self._global_params) # 32倍降的输出通道
# 卷积+标准化
self._conv_head = Conv2d(in_channels, out_channels, kernel_size=1, bias=False)
self._bn1 = nn.BatchNorm2d(num_features=out_channels, momentum=bn_mom, eps=bn_eps)
# 最后的全连接层
self._avg_pooling = nn.AdaptiveAvgPool2d(1)
self._dropout = nn.Dropout(self._global_params.dropout_rate)
self._fc = nn.Linear(out_channels, self._global_params.num_classes)
# 进行swish激活函数
self._swish = MemoryEfficientSwish()
def from_pretrained(cls, model_name, load_weights=True, advprop=True, num_classes=1000, in_channels=3):
model = cls.from_name(model_name, override_params={'num_classes': num_classes})
if load_weights:
load_pretrained_weights(model, model_name, load_fc=(num_classes == 1000), advprop=advprop)
if in_channels != 3:
Conv2d = get_same_padding_conv2d(image_size = model._global_params.image_size)
out_channels = round_filters(32, model._global_params)
model._conv_stem = Conv2d(in_channels, out_channels, kernel_size=3, stride=2, bias=False)
return model
def __init__(self, blocks_args=None, global_params=None):
super().__init__()
assert isinstance(blocks_args, list), 'blocks_args should be a list'
assert len(blocks_args) > 0, 'block args must be greater than 0'
self._global_params = global_params
self._blocks_args = blocks_args
# 获得一种卷积方法
Conv2d = get_same_padding_conv2d(image_size=global_params.image_size)
# 获得标准化的参数
bn_mom = 1 - self._global_params.batch_norm_momentum
bn_eps = self._global_params.batch_norm_epsilon
#-------------------------------------------------#
# 网络主干部分开始
# 设定输入进来的是RGB三通道图像
# 利用round_filters可以使得通道可以被8整除
#-------------------------------------------------#
in_channels = 3
out_channels = round_filters(32, self._global_params)
#-------------------------------------------------#
# 创建stem部分
#-------------------------------------------------#
self._conv_stem = Conv2d(
in_channels, out_channels, kernel_size=3, stride=2, bias=False)
self._bn0 = nn.BatchNorm2d(
num_features=out_channels, momentum=bn_mom, eps=bn_eps)
#-------------------------------------------------#
# 在这个地方对大结构块进行循环
#-------------------------------------------------#
self._blocks = nn.ModuleList([])
for i in range(len(self._blocks_args)):
#-------------------------------------------------------------#
# 对每个block的参数进行修改，根据所选的efficient版本进行修改
#-------------------------------------------------------------#
self._blocks_args[i] = self._blocks_args[i]._replace(
input_filters=round_filters(self._blocks_args[i].input_filters, self._global_params),
output_filters=round_filters(self._blocks_args[i].output_filters, self._global_params),
num_repeat=round_repeats(self._blocks_args[i].num_repeat, self._global_params)
)
#-------------------------------------------------------------#
# 每个大结构块里面的第一个EfficientBlock
# 都需要考虑步长和输入通道数
#-------------------------------------------------------------#
self._blocks.append(MBConvBlock(self._blocks_args[i], self._global_params))
if self._blocks_args[i].num_repeat > 1:
self._blocks_args[i] = self._blocks_args[i]._replace(input_filters=self._blocks_args[i].output_filters, stride=1)
#---------------------------------------------------------------#
# 在利用第一个EfficientBlock进行通道数的调整或者高和宽的压缩后
# 进行EfficientBlock的堆叠
#---------------------------------------------------------------#
for _ in range(self._blocks_args[i].num_repeat - 1):
self._blocks.append(MBConvBlock(self._blocks_args[i], self._global_params))
#----------------------------------------------------------------#
# 这是efficientnet的尾部部分，在进行effcientdet构建的时候没用到
# 只在利用efficientnet进行分类的时候用到。
#----------------------------------------------------------------#
in_channels = self._blocks_args[len(self._blocks_args)-1].output_filters
out_channels = round_filters(1280, self._global_params)
self._conv_head = Conv2d(in_channels, out_channels, kernel_size=1, bias=False)
self._bn1 = nn.BatchNorm2d(num_features=out_channels, momentum=bn_mom, eps=bn_eps)
self._avg_pooling = nn.AdaptiveAvgPool2d(1)
self._dropout = nn.Dropout(self._global_params.dropout_rate)
self._fc = nn.Linear(out_channels, self._global_params.num_classes)
self._swish = MemoryEfficientSwish()