def __init__(self, num_classes=1000, aux_logits=True, transform_input=False, init_weights=True, blocks=None): super(GoogLeNet, self).__init__() if blocks is None: blocks = [BasicConv2d, Inception, InceptionAux] assert len(blocks) == 3 conv_block = blocks[0] inception_block = blocks[1] inception_aux_block = blocks[2] self.aux_logits = aux_logits self.transform_input = transform_input self.conv1 = conv_block(3, 64, kernel_size=7, stride=2, padding=3) self.maxpool1 = my_MaxPool2d(3, stride=2, ceil_mode=True) self.conv2 = conv_block(64, 64, kernel_size=1) self.conv3 = conv_block(64, 192, kernel_size=3, padding=1) self.maxpool2 = my_MaxPool2d(3, stride=2, ceil_mode=True) self.inception3a = inception_block(192, 64, 96, 128, 16, 32, 32) self.inception3b = inception_block(256, 128, 128, 192, 32, 96, 64) self.maxpool3 = my_MaxPool2d(3, stride=2, ceil_mode=True) self.inception4a = inception_block(480, 192, 96, 208, 16, 48, 64) self.inception4b = inception_block(512, 160, 112, 224, 24, 64, 64) self.inception4c = inception_block(512, 128, 128, 256, 24, 64, 64) self.inception4d = inception_block(512, 112, 144, 288, 32, 64, 64) self.inception4e = inception_block(528, 256, 160, 320, 32, 128, 128) self.maxpool4 = my_MaxPool2d(2, stride=2, ceil_mode=True) self.inception5a = inception_block(832, 256, 160, 320, 32, 128, 128) self.inception5b = inception_block(832, 384, 192, 384, 48, 128, 128) ##!! Mandatory variables self._layers = None if aux_logits: self.aux1 = inception_aux_block(512, num_classes) self.aux2 = inception_aux_block(528, num_classes) self.avgpool = my_AdaptiveAvgPool2d((1, 1)) self.dropout = nn.Dropout(0.2) self.fc = my_Linear(1024, num_classes) if init_weights: self._initialize_weights()
def make_layers(cfg, batch_norm=False): layers = [] in_channels = 3 for v in cfg: if v == 'M': layers += [my_MaxPool2d(kernel_size=2, stride=2)] else: conv2d = my_Conv2d(in_channels, v, kernel_size=3, padding=1) if batch_norm: layers += [conv2d, my_BatchNorm2d(v), my_ReLU(inplace=True)] else: layers += [conv2d, my_ReLU(inplace=True)] in_channels = v return nn.Sequential(*layers)
def _make_layers(self, cfg): layers = [] in_channels = 3 for x in cfg: if x == 'M': layers += [my_MaxPool2d(kernel_size=2, stride=2)] else: layers += [ my_Conv2d(in_channels, x, kernel_size=3, padding=1), my_BatchNorm2d(x), my_ReLU(inplace=True) ] in_channels = x layers += [my_AvgPool2d(kernel_size=1, stride=1)] return nn.Sequential(*layers)
def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch5x5red, ch5x5, pool_proj, conv_block=None): super(Inception, self).__init__() if conv_block is None: conv_block = BasicConv2d self.branch1 = conv_block(in_channels, ch1x1, kernel_size=1) self.branch2 = nn.Sequential( conv_block(in_channels, ch3x3red, kernel_size=1), conv_block(ch3x3red, ch3x3, kernel_size=3, padding=1) ) self.branch3 = nn.Sequential( conv_block(in_channels, ch5x5red, kernel_size=1), conv_block(ch5x5red, ch5x5, kernel_size=3, padding=1) ) self.branch4 = nn.Sequential( my_MaxPool2d(kernel_size=3, stride=1, padding=1, ceil_mode=True), conv_block(in_channels, pool_proj, kernel_size=1) ) self._mode = 0
def __init__(self, block, layers, num_classes=1000, zero_init_residual=False, groups=1, width_per_group=64, replace_stride_with_dilation=None, norm_layer=None): super(ResNet, self).__init__() if norm_layer is None: norm_layer = my_BatchNorm2d self._norm_layer = norm_layer self.inplanes = 64 self.dilation = 1 if replace_stride_with_dilation is None: # each element in the tuple indicates if we should replace # the 2x2 stride with a dilated convolution instead replace_stride_with_dilation = [False, False, False] if len(replace_stride_with_dilation) != 3: raise ValueError("replace_stride_with_dilation should be None " "or a 3-element tuple, got {}".format( replace_stride_with_dilation)) self.groups = groups self.base_width = width_per_group self.conv1 = my_Conv2d(3, self.inplanes, kernel_size=7, stride=2, padding=3, bias=False) self.bn1 = norm_layer(self.inplanes) self.relu = my_ReLU(inplace=True) self.maxpool = my_MaxPool2d(kernel_size=3, stride=2, padding=1) self.layer1 = self._make_layer(block, 64, layers[0]) self.layer2 = self._make_layer(block, 128, layers[1], stride=2, dilate=replace_stride_with_dilation[0]) self.layer3 = self._make_layer(block, 256, layers[2], stride=2, dilate=replace_stride_with_dilation[1]) self.layer4 = self._make_layer(block, 512, layers[3], stride=2, dilate=replace_stride_with_dilation[2]) self.avgpool = my_AdaptiveAvgPool2d((1, 1)) #self.avgpool = my_AdaptiveAvgPool2d(1) self.fc = my_Linear(512 * block.expansion, num_classes) ##!! Mandatory variables self._layers = None for m in self.modules(): if isinstance(m, nn.Conv2d): nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu') elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)): nn.init.constant_(m.weight, 1) nn.init.constant_(m.bias, 0) # Zero-initialize the last BN in each residual branch, # so that the residual branch starts with zeros, and each residual block behaves like an identity. # This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677 if zero_init_residual: for m in self.modules(): if isinstance(m, Bottleneck): nn.init.constant_(m.bn3.weight, 0) elif isinstance(m, BasicBlock): nn.init.constant_(m.bn2.weight, 0)