def __init__(self, in_channels: int, out_channels: int, index: int): super(SSH, self).__init__() self.in_channels = in_channels self.out_channels = out_channels self.half_out_channels = int(out_channels / 2) self.quater_out_channels = int(self.half_out_channels / 2) self.index = index self.ssh_3x3 = nn.Sequential( nn.Conv2d(in_channels=self.in_channels, out_channels=self.half_out_channels, kernel_size=3, stride=1, padding=1) ) self.ssh_dimred = nn.Sequential( nn.Conv2d(in_channels=self.in_channels, out_channels=self.quater_out_channels, kernel_size=3, stride=1, padding=1), nn.ReLU() ) self.ssh_5x5 = nn.Sequential( nn.Conv2d(in_channels=self.quater_out_channels, out_channels=self.quater_out_channels, kernel_size=3, stride=1, padding=1) ) self.ssh_7x7 = nn.Sequential( nn.Conv2d(in_channels=self.quater_out_channels, out_channels=self.quater_out_channels, kernel_size=3, stride=1, padding=1), nn.ReLU(), nn.Conv2d(in_channels=self.quater_out_channels, out_channels=self.quater_out_channels, kernel_size=3, stride=1, padding=1) ) self.out_relu = nn.ReLU()
def build_conv_block(self, in_channels: int, out_channels: int, kernel_size: int = 3, stride: int = 1, padding: int = 1, n_conv: int = 2, with_pool: bool = False): layers = [] if with_pool: layers.append(nn.MaxPool2d(kernel_size=2, stride=2)) # convx_1 layers += [ nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size, stride=stride, padding=padding), nn.ReLU() ] # convx_2 -> convx_(n_conv) for i in range(1, n_conv): add_layers = [ nn.Conv2d(in_channels=out_channels, out_channels=out_channels, kernel_size=kernel_size, stride=stride, padding=padding), nn.ReLU() ] layers += add_layers # return as sequential return nn.Sequential(*layers)
def __init__(self): super(LFFDv1, self).__init__() self.backbone = nn.Sequential( nn.Conv2d(in_channels=3, out_channels=64, kernel_size=3, stride=2, padding=0), # downsample by 2 nn.ReLU(), nn.Conv2d(in_channels=64, out_channels=64, kernel_size=3, stride=2, padding=0), # downsample by 2 ResBlock(64), ResBlock(64), ResBlock(64)) self.rb1 = ResBlock(64, det_out=True) self.det1 = DetBlock(64) self.relu_conv10 = nn.ReLU() self.conv11 = nn.Conv2d(in_channels=64, out_channels=64, kernel_size=3, stride=2, padding=0) self.rb2 = ResBlock(64) self.det2 = DetBlock(64) self.rb3 = ResBlock(64, det_out=True) self.det3 = DetBlock(64) self.relu_conv15 = nn.ReLU() self.conv16 = nn.Conv2d(in_channels=64, out_channels=128, kernel_size=3, stride=2, padding=0) self.rb4 = ResBlock(128) self.det4 = DetBlock(64) self.relu_conv18 = nn.ReLU() self.conv19 = nn.Conv2d(in_channels=128, out_channels=128, kernel_size=3, stride=2, padding=0) self.rb5 = ResBlock(128) self.det5 = DetBlock(128) self.rb6 = ResBlock(128, det_out=True) self.det6 = DetBlock(128) self.rb7 = ResBlock(128, det_out=True) self.det7 = DetBlock(128) self.relu_conv25 = nn.ReLU() self.det8 = DetBlock(128)
def __init__(self): super(SSH, self).__init__() # backbone self.vgg16 = nn.ModuleList(make_layers(vgg_cfgs['D'])) # SSH - M3 self.M3 = M_Module(512, 256, 128) self.M3_bbox_pred = nn.Conv2d(512, 8, 1, 1, 0) self.M3_cls_score = nn.Conv2d(512, 4, 1, 1, 0) self.M3_cls_score_softmax = nn.Softmax(dim=1) # SSH - M2 self.M2 = M_Module(512, 256, 128) self.M2_bbox_pred = nn.Conv2d(512, 8, 1, 1, 0) self.M2_cls_score = nn.Conv2d(512, 4, 1, 1, 0) self.M2_cls_score_softmax = nn.Softmax(dim=1) # SSH - M1 self.conv4_128 = nn.Conv2d(512, 128, 1, 1, 0) self.conv4_128_relu = nn.ReLU(inplace=True) self.conv5_128 = nn.Conv2d(512, 128, 1, 1, 0) self.conv5_128_relu = nn.ReLU(inplace=True) self.conv5_128_up = nn.ConvTranspose2d(128, 128, 4, 2, 1, groups=128, bias=False) self.eltadd = nn.EltAdd() self.conv4_fuse_final = nn.Conv2d(128, 128, 3, 1, 1) self.conv4_fuse_final_relu = nn.ReLU(inplace=True) self.M1 = M_Module(128, 128, 64) self.M1_bbox_pred = nn.Conv2d(256, 8, 1, 1, 0) self.M1_cls_score = nn.Conv2d(256, 4, 1, 1, 0) self.M1_cls_score_softmax = nn.Softmax(dim=1)
def _conv_dw(in_channels, out_channels, stride): return nn.Sequential( nn.Conv2d(in_channels=in_channels, out_channels=in_channels, kernel_size=3, stride=stride, padding=1, groups=in_channels, bias=False), nn.BatchNorm2d(in_channels), nn.ReLU(inplace=True), nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=1, stride=1, padding=0, bias=False), nn.BatchNorm2d(out_channels), nn.ReLU(inplace=True) )
def __init__(self, in_planes, out_planes, kernel_size, stride=1, padding=0, dilation=1, groups=1, relu=True, bn=True): super(BasicConv, self).__init__() self.out_channels = out_planes if bn: self.conv = nn.Conv2d(in_planes, out_planes, kernel_size=kernel_size, stride=stride, padding=padding, dilation=dilation, groups=groups, bias=False) self.bn = nn.BatchNorm2d(out_planes, eps=1e-5, momentum=0.01, affine=True) self.relu = nn.ReLU(inplace=True) if relu else None else: self.conv = nn.Conv2d(in_planes, out_planes, kernel_size=kernel_size, stride=stride, padding=padding, dilation=dilation, groups=groups, bias=True) self.bn = None self.relu = nn.ReLU(inplace=True) if relu else None
def make_layers(cfg, batch_norm=False): layers = [] in_channels = 3 for v in cfg: if v == 'M': layers += [nn.MaxPool2d(kernel_size=2, stride=2)] else: conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1) if batch_norm: layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)] else: layers += [conv2d, nn.ReLU(inplace=True)] in_channels = v return layers
def __init__(self, input_channels, output_channels): super(DeepHeadModule, self).__init__() self._input_channels = input_channels self._output_channels = output_channels self._mid_channels = min(self._input_channels, 256) #print(self._mid_channels) self.conv1 = nn.Conv2d(self._input_channels, self._mid_channels, kernel_size=3, dilation=1, stride=1, padding=1) self.conv2 = nn.Conv2d(self._mid_channels, self._mid_channels, kernel_size=3, dilation=1, stride=1, padding=1) self.conv3 = nn.Conv2d(self._mid_channels, self._mid_channels, kernel_size=3, dilation=1, stride=1, padding=1) self.conv4 = nn.Conv2d(self._mid_channels, self._output_channels, kernel_size=1, dilation=1, stride=1, padding=0) self.relu = nn.ReLU(inplace=True)
def __init__(self, in_channels, out_channels, kernel_sizes, strides=None, paddings=None, with_pool=True): super(Conv_Block, self).__init__() assert len(in_channels) == len(out_channels) assert len(out_channels) == len(kernel_sizes) if strides is not None: assert len(kernel_sizes) == len(strides) self.pool = None if with_pool: self.pool = nn.MaxPool2d(kernel_size=2, stride=2) groups = len(in_channels) convs = [] for i in range(groups): convs.append( nn.Conv2d(in_channels=in_channels[i], out_channels=out_channels[i], kernel_size=kernel_sizes[i], stride=strides[i], padding=paddings[i])) convs.append(nn.ReLU(inplace=True)) self.feature = nn.Sequential(*convs)
def __init__(self, in_channels, out_channels, kernel_size, stride, padding, **kwargs): super(ConvBNReLU, self).__init__() self.in_channels = in_channels self.out_channels = out_channels self.conv = nn.Conv2d(in_channels, out_channels, kernel_size, stride, padding, bias=True, **kwargs) self.bn = nn.BatchNorm2d(out_channels) self.relu = nn.ReLU(inplace=True)
def __init__(self, in_planes, out_planes, stride=1, scale=0.1, map_reduce=8, vision=1, groups=1): super(BasicRFB, self).__init__() self.scale = scale self.out_channels = out_planes inter_planes = in_planes // map_reduce self.branch0 = nn.Sequential( BasicConv(in_planes, inter_planes, kernel_size=1, stride=1, groups=groups, relu=False), BasicConv(inter_planes, 2 * inter_planes, kernel_size=(3, 3), stride=stride, padding=(1, 1), groups=groups), BasicConv(2 * inter_planes, 2 * inter_planes, kernel_size=3, stride=1, padding=vision + 1, dilation=vision + 1, relu=False, groups=groups) ) self.branch1 = nn.Sequential( BasicConv(in_planes, inter_planes, kernel_size=1, stride=1, groups=groups, relu=False), BasicConv(inter_planes, 2 * inter_planes, kernel_size=(3, 3), stride=stride, padding=(1, 1), groups=groups), BasicConv(2 * inter_planes, 2 * inter_planes, kernel_size=3, stride=1, padding=vision + 2, dilation=vision + 2, relu=False, groups=groups) ) self.branch2 = nn.Sequential( BasicConv(in_planes, inter_planes, kernel_size=1, stride=1, groups=groups, relu=False), BasicConv(inter_planes, (inter_planes // 2) * 3, kernel_size=3, stride=1, padding=1, groups=groups), BasicConv((inter_planes // 2) * 3, 2 * inter_planes, kernel_size=3, stride=stride, padding=1, groups=groups), BasicConv(2 * inter_planes, 2 * inter_planes, kernel_size=3, stride=1, padding=vision + 4, dilation=vision + 4, relu=False, groups=groups) ) self.ConvLinear = BasicConv(6 * inter_planes, out_planes, kernel_size=1, stride=1, relu=False) self.shortcut = BasicConv(in_planes, out_planes, kernel_size=1, stride=stride, relu=False) self.relu = nn.ReLU(inplace=False) self.eltadd = nn.EltAdd()
def __init__(self, up_from_channels, up_to_channels): super(LFPN, self).__init__() self.conv1 = nn.Conv2d(up_from_channels, up_to_channels, kernel_size=1) self.conv1_relu = nn.ReLU(inplace=True) self.upsampling = nn.ConvTranspose2d(up_to_channels, up_to_channels, kernel_size=4, stride=2, padding=1, groups=up_to_channels, bias=False) self.conv2 = nn.Conv2d(up_to_channels, up_to_channels, kernel_size=1) self.conv2_relu = nn.ReLU(inplace=True) self.eltmul = nn.EltMul()
def __init__(self, in_channels, out_channels_left, out_channels_right): super(M_Module, self).__init__() inc = in_channels ocl, ocr = out_channels_left, out_channels_right # left branch self.ssh_3x3 = nn.Conv2d(inc, ocl, 3, 1, 1) # right branch self.ssh_dimred = nn.Conv2d(inc, ocr, 3, 1, 1) self.ssh_dimred_relu = nn.ReLU(inplace=True) self.ssh_5x5 = nn.Conv2d(ocr, ocr, 3, 1, 1) self.ssh_7x7_1 = nn.Conv2d(ocr, ocr, 3, 1, 1) self.ssh_7x7_1_relu = nn.ReLU(inplace=True) self.ssh_7x7 = nn.Conv2d(ocr, ocr, 3, 1, 1) self.ssh_output_relu = nn.ReLU(inplace=True)
def __init__(self, in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1): super(IdentityBlock, self).__init__() out_channels_1, out_channels_2, out_channels_3 = out_channels//4, out_channels//4, out_channels self.conv1 = nn.Conv2d(in_channels, out_channels_1, kernel_size=(1, 1)) self.bn1 = nn.BatchNorm2d(out_channels_1) self.relu1 = nn.ReLU(inplace=True) self.conv2 = nn.Conv2d(out_channels_1, out_channels_2, kernel_size=(kernel_size, kernel_size), padding=(padding, padding), dilation=(dilation, dilation)) self.bn2 = nn.BatchNorm2d(out_channels_2) self.relu2 = nn.ReLU(inplace=True) self.conv3 = nn.Conv2d(out_channels_2, out_channels_3, kernel_size=(1, 1)) self.bn3 = nn.BatchNorm2d(out_channels_3) self.eltadd = nn.EltAdd() self.relu_f = nn.ReLU(inplace=True)
def __init__(self, mode='slim'): super(ULFG, self).__init__() self.mode = mode self.base_channel = 8 * 2 self.backbone = nn.Sequential( _conv_bn(3, self.base_channel, 2), # 160*120 _conv_dw(self.base_channel, self.base_channel * 2, 1), _conv_dw(self.base_channel * 2, self.base_channel * 2, 2), # 80*60 _conv_dw(self.base_channel * 2, self.base_channel * 2, 1), _conv_dw(self.base_channel * 2, self.base_channel * 4, 2), # 40*30 _conv_dw(self.base_channel * 4, self.base_channel * 4, 1), _conv_dw(self.base_channel * 4, self.base_channel * 4, 1), _conv_dw(self.base_channel * 4, self.base_channel * 4, 1), _conv_dw(self.base_channel * 4, self.base_channel * 8, 2), # 20*15 _conv_dw(self.base_channel * 8, self.base_channel * 8, 1), _conv_dw(self.base_channel * 8, self.base_channel * 8, 1), _conv_dw(self.base_channel * 8, self.base_channel * 16, 2), # 10*8 _conv_dw(self.base_channel * 16, self.base_channel * 16, 1) ) if self.mode == 'rfb': self.backbone[7] = BasicRFB(self.base_channel * 4, self.base_channel * 4, stride=1, scale=1.0) self.source_layer_indexes = [8, 11, 13] self.extras = nn.Sequential( nn.Conv2d(in_channels=self.base_channel * 16, out_channels=self.base_channel * 4, kernel_size=1), nn.ReLU(), _seperable_conv2d(in_channels=self.base_channel * 4, out_channels=self.base_channel * 16, kernel_size=3, stride=2, padding=1), nn.ReLU() ) self.regression_headers = nn.ModuleList([ _seperable_conv2d(in_channels=self.base_channel * 4, out_channels=3 * 4, kernel_size=3, padding=1), _seperable_conv2d(in_channels=self.base_channel * 8, out_channels=2 * 4, kernel_size=3, padding=1), _seperable_conv2d(in_channels=self.base_channel * 16, out_channels=2 * 4, kernel_size=3, padding=1), nn.Conv2d(in_channels=self.base_channel * 16, out_channels=3 * 4, kernel_size=3, padding=1) ]) self.classification_headers = nn.ModuleList([ _seperable_conv2d(in_channels=self.base_channel * 4, out_channels=3 * 2, kernel_size=3, padding=1), _seperable_conv2d(in_channels=self.base_channel * 8, out_channels=2 * 2, kernel_size=3, padding=1), _seperable_conv2d(in_channels=self.base_channel * 16, out_channels=2 * 2, kernel_size=3, padding=1), nn.Conv2d(in_channels=self.base_channel * 16, out_channels=3 * 2, kernel_size=3, padding=1) ]) self.softmax = nn.Softmax(dim=2)
def __init__(self, in_channel, out_channel, kernel_size, stride=1, padding=0, bias=False, add_relu=True, add_bn=True, eps=1e-5): super(ConvBlock, self).__init__() self.conv = nn.Conv2d(in_channel, out_channel, kernel_size, stride, padding, bias=bias) self.relu = None self.bn = None if add_relu: self.relu = nn.ReLU() if add_bn: self.bn = nn.BatchNorm2d(out_channel, eps=eps)
def __init__(self, channels, det_out=False): super(ResBlock, self).__init__() self.channels = channels self.det_out = det_out self.relu = nn.ReLU() self.block = nn.Sequential( nn.Conv2d(in_channels=self.channels, out_channels=self.channels, kernel_size=3, stride=1, padding=1), nn.ReLU(), nn.Conv2d(in_channels=self.channels, out_channels=self.channels, kernel_size=3, stride=1, padding=1)) self.eltadd = nn.EltAdd()
def __init__(self, in_channels): super(CPM, self).__init__() # residual self.branch1 = Conv_BN(in_channels, 1024, 1, 1, 0, act=None) self.branch2a = Conv_BN(in_channels, 256, 1, 1, 0, act='relu') self.branch2b = Conv_BN(256, 256, 3, 1, 1, act='relu') self.branch2c = Conv_BN(256, 1024, 1, 1, 0, act=None) self.eltadd = nn.EltAdd() self.rescomb_relu = nn.ReLU(inplace=True) # ssh self.ssh_1_conv = nn.Conv2d(1024, 256, 3, 1, 1) self.ssh_dimred_conv = nn.Conv2d(1024, 128, 3, 1, 1) self.ssh_dimred_relu = nn.ReLU(inplace=True) self.ssh_2_conv = nn.Conv2d(128, 128, 3, 1, 1) self.ssh_3a_conv = nn.Conv2d(128, 128, 3, 1, 1) self.ssh_3a_relu = nn.ReLU(inplace=True) self.ssh_3b_conv = nn.Conv2d(128, 128, 3, 1, 1) self.concat_relu = nn.ReLU(inplace=True)
def __init__(self, channel_size): super(FEM, self).__init__() self.cs = channel_size self.cpm1 = nn.Conv2d(self.cs, 256, kernel_size=3, dilation=1, stride=1, padding=1) self.cpm2 = nn.Conv2d(self.cs, 256, kernel_size=3, dilation=2, stride=1, padding=2) self.cpm3 = nn.Conv2d(256, 128, kernel_size=3, dilation=1, stride=1, padding=1) self.cpm4 = nn.Conv2d(256, 128, kernel_size=3, dilation=2, stride=1, padding=2) self.cpm5 = nn.Conv2d(128, 128, kernel_size=3, dilation=1, stride=1, padding=1) self.relu1 = nn.ReLU(inplace=True) self.relu2 = nn.ReLU(inplace=True) self.relu3 = nn.ReLU(inplace=True) self.relu4 = nn.ReLU(inplace=True) self.relu5 = nn.ReLU(inplace=True)
def build_conv_block(self, in_channels: int, out_channels: int, kernel_size: int = 3, stride: int = 1, padding: int = 1, dilation: int = 1, n_conv: int = 2, with_pool: bool = False): layers = [ nn.Conv2d(in_channels, out_channels, kernel_size, stride, padding, dilation), nn.ReLU() ] for i in range(1, n_conv): layers += [ nn.Conv2d(out_channels, out_channels, kernel_size, stride, padding), nn.ReLU() ] if with_pool: layers += [nn.MaxPool2d(2, 2)] return nn.Sequential(*layers)
def __init__(self): super(LFFDv2, self).__init__() self.backbone = nn.Sequential( nn.Conv2d(in_channels=3, out_channels=64, kernel_size=3, stride=2, padding=0), # downsample by 2 nn.ReLU(), nn.Conv2d(in_channels=64, out_channels=64, kernel_size=3, stride=2, padding=0), # downsample by 2 ResBlock(64), ResBlock(64), ResBlock(64)) self.relu_conv8 = nn.ReLU() self.conv9 = nn.Conv2d(in_channels=64, out_channels=64, kernel_size=3, stride=2, padding=0) # downsample by 2 self.rb1 = ResBlock(64) self.det1 = DetBlock(64) self.relu_conv11 = nn.ReLU() self.conv12 = nn.Conv2d(in_channels=64, out_channels=64, kernel_size=3, stride=2, padding=0) # downsample by 2 self.rb2 = ResBlock(64) self.det2 = DetBlock(64) self.relu_conv14 = nn.ReLU() self.conv15 = nn.Conv2d(in_channels=64, out_channels=128, kernel_size=3, stride=2, padding=0) # downsample by 2 self.rb3 = ResBlock(128) self.det3 = DetBlock(64) self.relu_conv17 = nn.ReLU() self.conv18 = nn.Conv2d(in_channels=128, out_channels=128, kernel_size=3, stride=2, padding=0) # downsample by 2 self.rb4 = ResBlock(128) self.det4 = DetBlock(128) self.relu_conv20 = nn.ReLU() self.det5 = DetBlock(128)
def __init__(self, in_channels): super(DetBlock, self).__init__() self.in_channels = in_channels self.det_channels = 128 self.det_conv = nn.Conv2d(in_channels=self.in_channels, out_channels=self.det_channels, kernel_size=1, stride=1, padding=0) self.det_relu = nn.ReLU() self.bbox_conv = nn.Conv2d(in_channels=self.det_channels, out_channels=self.det_channels, kernel_size=1, stride=1, padding=0) self.bbox_relu = nn.ReLU() self.bbox_out_conv = nn.Conv2d(in_channels=self.det_channels, out_channels=4, kernel_size=1, stride=1, padding=0) self.score_conv = nn.Conv2d(in_channels=self.det_channels, out_channels=self.det_channels, kernel_size=1, stride=1, padding=0) self.score_relu = nn.ReLU() self.score_out_conv = nn.Conv2d(in_channels=self.det_channels, out_channels=2, kernel_size=1, stride=1, padding=0) self.softmax = nn.Softmax(dim=1)
def upsample(in_channels, out_channels): # should use F.inpterpolate return nn.Sequential( nn.Conv2d(in_channels=in_channels, out_channels=in_channels, kernel_size=(3, 3), stride=1, padding=1, groups=in_channels, bias=False), nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=1, stride=1, padding=0, bias=False), nn.BatchNorm2d(out_channels), nn.ReLU())
def __init__(self, inplanes, planes, stride=1, downsample=None): super(Bottleneck, self).__init__() self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False) self.bn1 = nn.BatchNorm2d(planes) self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False) self.bn2 = nn.BatchNorm2d(planes) self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False) self.bn3 = nn.BatchNorm2d(planes * 4) self.relu = nn.ReLU(inplace=True) self.downsample = downsample self.stride = stride self.eltadd = nn.EltAdd()
def __init__(self, in_channels, out_channels, kernel_sizes, strides=1, paddings=0, act='relu', bias=False): super(Conv_BN, self).__init__() self.conv = nn.Conv2d(in_channels, out_channels, kernel_sizes, strides, paddings, bias=bias) self.bn = nn.BatchNorm2d(out_channels, eps=0.001, momentum=0.999) self.act = None if act == 'relu': self.act = nn.ReLU(inplace=True)
def __init__(self, in_channel, out_channel): super(SSH, self).__init__() assert out_channel % 4 == 0 leaky = 0 if (out_channel <= 64): leaky = 0.1 self.conv3X3 = conv_bn_no_relu(in_channel, out_channel // 2, stride=1) self.conv5X5_1 = conv_bn(in_channel, out_channel // 4, stride=1, leaky=leaky) self.conv5X5_2 = conv_bn_no_relu(out_channel // 4, out_channel // 4, stride=1) self.conv7X7_2 = conv_bn(out_channel // 4, out_channel // 4, stride=1, leaky=leaky) self.conv7x7_3 = conv_bn_no_relu(out_channel // 4, out_channel // 4, stride=1) self.relu = nn.ReLU()
def __init__(self): super(S3FD, self).__init__() # backbone self.vgg16 = nn.ModuleList(make_layers(vgg_cfgs['D'])) # s3fd specific self.conv_fc6 = nn.Conv2d(512, 1024, 3, 1, 1) self.relu_fc6 = nn.ReLU() self.conv_fc7 = nn.Conv2d(1024, 1024, 1, 1, 0) self.relu_fc7 = nn.ReLU() self.conv6_1 = nn.Conv2d(1024, 256, 1, 1, 0) self.relu_conv6_1 = nn.ReLU() self.conv6_2 = nn.Conv2d(256, 512, 3, 2, 1) self.relu_conv6_2 = nn.ReLU() self.conv7_1 = nn.Conv2d(512, 128, 1, 1, 0) self.relu_conv7_1 = nn.ReLU() self.conv7_2 = nn.Conv2d(128, 256, 3, 2, 1) self.relu_conv7_2 = nn.ReLU() self.l2norm_conv3_3 = nn.L2Norm2d(256, 10) self.l2norm_conv4_3 = nn.L2Norm2d(512, 8) self.l2norm_conv5_3 = nn.L2Norm2d(512, 5) # Detection Head - mbox_loc self.mbox_loc_conv3_3_norm = nn.Conv2d(256, 4, 3, 1, 1) self.mbox_loc_conv4_3_norm = nn.Conv2d(512, 4, 3, 1, 1) self.mbox_loc_conv5_3_norm = nn.Conv2d(512, 4, 3, 1, 1) self.mbox_loc_conv_fc7 = nn.Conv2d(1024, 4, 3, 1, 1) self.mbox_loc_conv6_2 = nn.Conv2d(512, 4, 3, 1, 1) self.mbox_loc_conv7_2 = nn.Conv2d(256, 4, 3, 1, 1) # Detection Head - mbox_conf self.mbox_conf_conv3_3_norm = nn.Conv2d( 256, 4, 3, 1, 1) # 4->2 through maxout at channels 0~2 self.mbox_conf_conv4_3_norm = nn.Conv2d(512, 2, 3, 1, 1) self.mbox_conf_conv5_3_norm = nn.Conv2d(512, 2, 3, 1, 1) self.mbox_conf_conv_fc7 = nn.Conv2d(1024, 2, 3, 1, 1) self.mbox_conf_conv6_2 = nn.Conv2d(512, 2, 3, 1, 1) self.mbox_conf_conv7_2 = nn.Conv2d(256, 2, 3, 1, 1) # Detection Head - mbox_conf - softmax self.softmax = nn.Softmax(dim=-1)
def __init__(self, in_channels, out_channels, **kwargs): super(BasicConv2d, self).__init__() self.conv = nn.Conv2d(in_channels, out_channels, bias=False, **kwargs) self.bn = nn.BatchNorm2d(out_channels, eps=1e-5) self.relu = nn.ReLU()
def __init__(self): super(DSFD, self).__init__() self.size = 640 self.num_classes = 2 ###### # build backbone ###### resnet152 = vision.models.resnet152() self.layer1 = nn.Sequential(resnet152.conv1, resnet152.bn1, resnet152.relu, resnet152.maxpool, resnet152.layer1) self.layer2 = nn.Sequential(resnet152.layer2) self.layer3 = nn.Sequential(resnet152.layer3) self.layer4 = nn.Sequential(resnet152.layer4) self.layer5 = nn.Sequential(*[ nn.Conv2d(2048, 512, kernel_size=1), nn.BatchNorm2d(512), nn.ReLU(inplace=True), nn.Conv2d(512, 512, kernel_size=3, padding=1, stride=2), nn.BatchNorm2d(512), nn.ReLU(inplace=True) ]) self.layer6 = nn.Sequential(*[ nn.Conv2d( 512, 128, kernel_size=1, ), nn.BatchNorm2d(128), nn.ReLU(inplace=True), nn.Conv2d(128, 256, kernel_size=3, padding=1, stride=2), nn.BatchNorm2d(256), nn.ReLU(inplace=True) ]) ###### # dsfd specific layers ###### output_channels = [256, 512, 1024, 2048, 512, 256] # fpn fpn_in = output_channels self.latlayer3 = nn.Conv2d(fpn_in[3], fpn_in[2], kernel_size=1, stride=1, padding=0) self.latlayer2 = nn.Conv2d(fpn_in[2], fpn_in[1], kernel_size=1, stride=1, padding=0) self.latlayer1 = nn.Conv2d(fpn_in[1], fpn_in[0], kernel_size=1, stride=1, padding=0) self.smooth3 = nn.Conv2d(fpn_in[2], fpn_in[2], kernel_size=1, stride=1, padding=0) self.smooth2 = nn.Conv2d(fpn_in[1], fpn_in[1], kernel_size=1, stride=1, padding=0) self.smooth1 = nn.Conv2d(fpn_in[0], fpn_in[0], kernel_size=1, stride=1, padding=0) self.upsample = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=False) self.eltmul = nn.EltMul() # fem cpm_in = output_channels self.cpm3_3 = FEM(cpm_in[0]) self.cpm4_3 = FEM(cpm_in[1]) self.cpm5_3 = FEM(cpm_in[2]) self.cpm7 = FEM(cpm_in[3]) self.cpm6_2 = FEM(cpm_in[4]) self.cpm7_2 = FEM(cpm_in[5]) # pa cfg_mbox = [1, 1, 1, 1, 1, 1] head = pa_multibox(output_channels, cfg_mbox, self.num_classes) # detection head self.loc = nn.ModuleList(head[0]) self.conf = nn.ModuleList(head[1]) self.softmax = nn.Softmax(dim=-1)
from _utils import test_on import sys sys.path.append('.') from flops_counter import nn from flops_counter.tensorsize import TensorSize ###### # test on ReLU ###### relu = { 'layers': [ nn.ReLU() # same shape ], 'ins': [TensorSize([1, 64, 112, 112])], 'out_shape': [TensorSize([1, 64, 112, 112])], 'out_flops': [1605632] } test_on(relu) ###### # test on Sigmoid ###### sigmoid = { 'layers': [ nn.Sigmoid() # same shape ], 'ins': [TensorSize([1, 1, 56, 56])], 'out_shape': [TensorSize([1, 1, 56, 56])], 'out_flops': [9408]