def __init__(self, in_channels, num_anchors, num_classes, num_layers, onnx_export=False): super(ClassNet, self).__init__() self.num_anchors = num_anchors self.num_classes = num_classes self.num_layers = num_layers self.conv_list = nn.ModuleList([ SeparableConvBlock(in_channels, in_channels, norm=False, activation=False) for i in range(num_layers) ]) # 每一个有效特征层对应的BatchNorm2d不同 self.bn_list = nn.ModuleList([ nn.ModuleList([ nn.BatchNorm2d(in_channels, momentum=0.01, eps=1e-3) for i in range(num_layers) ]) for j in range(5) ]) # num_anchors = 9 # num_anchors num_classes self.header = SeparableConvBlock(in_channels, num_anchors * num_classes, norm=False, activation=False) self.swish = MemoryEfficientSwish() if not onnx_export else Swish()
def __init__(self, in_channels, out_channels=None, norm=True, activation=False, onnx_export=False): super(SeparableConvBlock, self).__init__() if out_channels is None: out_channels = in_channels self.depthwise_conv = Conv2dStaticSamePadding(in_channels, in_channels, kernel_size=3, stride=1, groups=in_channels, bias=False) self.pointwise_conv = Conv2dStaticSamePadding(in_channels, out_channels, kernel_size=1, stride=1) self.norm = norm if self.norm: self.bn = nn.BatchNorm2d(num_features=out_channels, momentum=0.01, eps=1e-3) self.activation = activation if self.activation: self.swish = MemoryEfficientSwish() if not onnx_export else Swish()
def __init__(self, block_args, global_params): super().__init__() self._block_args = block_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 self._bn_mom = 1 - global_params.batch_norm_momentum self._bn_eps = global_params.batch_norm_epsilon #----------------------------# # 计算是否施加注意力机制 #----------------------------# self.has_se = (self._block_args.se_ratio is not None) and (0 < self._block_args.se_ratio <= 1) #----------------------------# # 判断是否添加残差边 #----------------------------# self.id_skip = block_args.id_skip #-------------------------------------------------# # 利用Inverted residuals # part1 利用1x1卷积进行通道数上升 #-------------------------------------------------# inp = self._block_args.input_filters oup = self._block_args.input_filters * self._block_args.expand_ratio if self._block_args.expand_ratio != 1: self._expand_conv = Conv2d(in_channels=inp, out_channels=oup, kernel_size=1, bias=False) self._bn0 = nn.BatchNorm2d(num_features=oup, momentum=self._bn_mom, eps=self._bn_eps) #------------------------------------------------------# # 如果步长为2x2的话,利用深度可分离卷积进行高宽压缩 # part2 利用3x3卷积对每一个channel进行卷积 #------------------------------------------------------# k = self._block_args.kernel_size s = self._block_args.stride self._depthwise_conv = Conv2d(in_channels=oup, out_channels=oup, groups=oup, kernel_size=k, stride=s, bias=False) self._bn1 = nn.BatchNorm2d(num_features=oup, momentum=self._bn_mom, eps=self._bn_eps) #------------------------------------------------------# # 完成深度可分离卷积后 # 对深度可分离卷积的结果施加注意力机制 #------------------------------------------------------# if self.has_se: num_squeezed_channels = max(1, int(self._block_args.input_filters * self._block_args.se_ratio)) #------------------------------------------------------# # 通道先压缩后上升,最后利用sigmoid将值固定到0-1之间 #------------------------------------------------------# self._se_reduce = Conv2d(in_channels=oup, out_channels=num_squeezed_channels, kernel_size=1) self._se_expand = Conv2d(in_channels=num_squeezed_channels, out_channels=oup, kernel_size=1) #------------------------------------------------------# # part3 利用1x1卷积进行通道下降 #------------------------------------------------------# final_oup = self._block_args.output_filters self._project_conv = Conv2d(in_channels=oup, out_channels=final_oup, kernel_size=1, bias=False) self._bn2 = nn.BatchNorm2d(num_features=final_oup, momentum=self._bn_mom, eps=self._bn_eps) self._swish = MemoryEfficientSwish()
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 __init__(self, block_args, global_params): super().__init__() self._block_args = block_args # 获得标准化的参数 self._bn_mom = 1 - global_params.batch_norm_momentum self._bn_eps = global_params.batch_norm_epsilon # 注意力机制的缩放比例 self.has_se = (self._block_args.se_ratio is not None) and ( 0 < self._block_args.se_ratio <= 1) # 是否需要短接边 self.id_skip = block_args.id_skip Conv2d = get_same_padding_conv2d(image_size=global_params.image_size) # 1x1卷积通道扩张 inp = self._block_args.input_filters # number of input channels oup = self._block_args.input_filters * self._block_args.expand_ratio # number of output channels if self._block_args.expand_ratio != 1: self._expand_conv = Conv2d( in_channels=inp, out_channels=oup, kernel_size=1, bias=False) self._bn0 = nn.BatchNorm2d( num_features=oup, momentum=self._bn_mom, eps=self._bn_eps) # 深度可分离卷积 k = self._block_args.kernel_size s = self._block_args.stride self._depthwise_conv = Conv2d( in_channels=oup, out_channels=oup, groups=oup, kernel_size=k, stride=s, bias=False) self._bn1 = nn.BatchNorm2d( num_features=oup, momentum=self._bn_mom, eps=self._bn_eps) # 注意力机制模块组,先进行通道数的收缩再进行通道数的扩张 if self.has_se: num_squeezed_channels = max( 1, int(self._block_args.input_filters * self._block_args.se_ratio)) self._se_reduce = Conv2d( in_channels=oup, out_channels=num_squeezed_channels, kernel_size=1) self._se_expand = Conv2d( in_channels=num_squeezed_channels, out_channels=oup, kernel_size=1) # 输出部分 final_oup = self._block_args.output_filters self._project_conv = Conv2d( in_channels=oup, out_channels=final_oup, kernel_size=1, bias=False) self._bn2 = nn.BatchNorm2d( num_features=final_oup, momentum=self._bn_mom, eps=self._bn_eps) self._swish = MemoryEfficientSwish()
def set_swish(self, memory_efficient=True): """Sets swish function as memory efficient (for training) or standard (for export)""" # swish函数 self._swish = MemoryEfficientSwish() if memory_efficient else Swish() for block in self._blocks: block.set_swish(memory_efficient)
def set_swish(self, memory_efficient=True): """Sets swish function as memory efficient (for training) or standard (for export)""" self._swish = MemoryEfficientSwish() if memory_efficient else Swish()
def __init__(self, num_channels, conv_channels, first_time=False, epsilon=1e-4, onnx_export=False, attention=True): super(BiFPN, self).__init__() self.epsilon = epsilon self.conv6_up = SeparableConvBlock(num_channels, onnx_export=onnx_export) self.conv5_up = SeparableConvBlock(num_channels, onnx_export=onnx_export) self.conv4_up = SeparableConvBlock(num_channels, onnx_export=onnx_export) self.conv3_up = SeparableConvBlock(num_channels, onnx_export=onnx_export) self.conv4_down = SeparableConvBlock(num_channels, onnx_export=onnx_export) self.conv5_down = SeparableConvBlock(num_channels, onnx_export=onnx_export) self.conv6_down = SeparableConvBlock(num_channels, onnx_export=onnx_export) self.conv7_down = SeparableConvBlock(num_channels, onnx_export=onnx_export) self.p6_upsample = nn.Upsample(scale_factor=2, mode='nearest') self.p5_upsample = nn.Upsample(scale_factor=2, mode='nearest') self.p4_upsample = nn.Upsample(scale_factor=2, mode='nearest') self.p3_upsample = nn.Upsample(scale_factor=2, mode='nearest') self.p4_downsample = MaxPool2dStaticSamePadding(3, 2) self.p5_downsample = MaxPool2dStaticSamePadding(3, 2) self.p6_downsample = MaxPool2dStaticSamePadding(3, 2) self.p7_downsample = MaxPool2dStaticSamePadding(3, 2) self.swish = MemoryEfficientSwish() if not onnx_export else Swish() self.first_time = first_time if self.first_time: # 获取到了efficientnet的最后三层,对其进行通道的下压缩 self.p5_down_channel = nn.Sequential( Conv2dStaticSamePadding(conv_channels[2], num_channels, 1), nn.BatchNorm2d(num_channels, momentum=0.01, eps=1e-3), ) self.p4_down_channel = nn.Sequential( Conv2dStaticSamePadding(conv_channels[1], num_channels, 1), nn.BatchNorm2d(num_channels, momentum=0.01, eps=1e-3), ) self.p3_down_channel = nn.Sequential( Conv2dStaticSamePadding(conv_channels[0], num_channels, 1), nn.BatchNorm2d(num_channels, momentum=0.01, eps=1e-3), ) # 对输入进来的p5进行宽高的下采样 self.p5_to_p6 = nn.Sequential( Conv2dStaticSamePadding(conv_channels[2], num_channels, 1), nn.BatchNorm2d(num_channels, momentum=0.01, eps=1e-3), MaxPool2dStaticSamePadding(3, 2) ) self.p6_to_p7 = nn.Sequential( MaxPool2dStaticSamePadding(3, 2) ) # BIFPN第一轮的时候,跳线那里并不是同一个in self.p4_down_channel_2 = nn.Sequential( Conv2dStaticSamePadding(conv_channels[1], num_channels, 1), nn.BatchNorm2d(num_channels, momentum=0.01, eps=1e-3), ) self.p5_down_channel_2 = nn.Sequential( Conv2dStaticSamePadding(conv_channels[2], num_channels, 1), nn.BatchNorm2d(num_channels, momentum=0.01, eps=1e-3), ) # 简易注意力机制的weights self.p6_w1 = nn.Parameter(torch.ones(2, dtype=torch.float32), requires_grad=True) self.p6_w1_relu = nn.ReLU() self.p5_w1 = nn.Parameter(torch.ones(2, dtype=torch.float32), requires_grad=True) self.p5_w1_relu = nn.ReLU() self.p4_w1 = nn.Parameter(torch.ones(2, dtype=torch.float32), requires_grad=True) self.p4_w1_relu = nn.ReLU() self.p3_w1 = nn.Parameter(torch.ones(2, dtype=torch.float32), requires_grad=True) self.p3_w1_relu = nn.ReLU() self.p4_w2 = nn.Parameter(torch.ones(3, dtype=torch.float32), requires_grad=True) self.p4_w2_relu = nn.ReLU() self.p5_w2 = nn.Parameter(torch.ones(3, dtype=torch.float32), requires_grad=True) self.p5_w2_relu = nn.ReLU() self.p6_w2 = nn.Parameter(torch.ones(3, dtype=torch.float32), requires_grad=True) self.p6_w2_relu = nn.ReLU() self.p7_w2 = nn.Parameter(torch.ones(2, dtype=torch.float32), requires_grad=True) self.p7_w2_relu = nn.ReLU() self.attention = attention
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()