Error in densenet

when i tested this code this error is displayed

class _Transition(nn.Sequential):
    def __init__(self, num_input_features, num_output_features):
        super(_Transition, self).__init__()
        self.add_module('norm', nn.BatchNorm2d(num_input_features))
        self.add_module('relu', nn.ReLU(inplace=True))
        self.add_module('conv', nn.Conv2d(num_input_features, num_output_features,
                                          kernel_size=2, stride=1, bias=False))
        self.add_module('pool', nn.AvgPool2d(kernel_size=2, stride=2))
class _DenseLayer(nn.Module):
    def __init__(self, num_input_features, growth_rate, bn_size, drop_rate, memory_efficient=False):
        super(_DenseLayer, self).__init__()
        self.add_module('norm1', nn.BatchNorm2d(num_input_features)),
        self.add_module('relu1', nn.ReLU(inplace=True)),
        self.add_module('conv1', nn.Conv2d(num_input_features, bn_size *
                                           growth_rate, kernel_size=1, stride=1,
        self.add_module('norm2', nn.BatchNorm2d(bn_size * growth_rate)),
        self.add_module('relu2', nn.ReLU(inplace=True)),
        self.add_module('conv2', nn.Conv2d(bn_size * growth_rate, growth_rate,
                                           kernel_size=3, stride=1, padding=1,
        self.drop_rate = float(drop_rate)
        self.memory_efficient = memory_efficient

    def bn_function(self, inputs):
        "Bottleneck function"
        # type: (List[Tensor]) -> Tensor
        concated_features =, 1)
        bottleneck_output = self.conv1(self.relu1(self.norm1(concated_features)))  # noqa: T484
        return bottleneck_output

    def forward(self, input):  # noqa: F811
        if isinstance(input, Tensor):
            prev_features = [input]
            prev_features = input

        bottleneck_output = self.bn_function(prev_features)
        new_features = self.conv2(self.relu2(self.norm2(bottleneck_output)))
        if self.drop_rate > 0:
            new_features = F.dropout(new_features, p=self.drop_rate,
        return new_features
class _DenseBlock(nn.ModuleDict):
    _version = 2

    def __init__(self, num_layers, num_input_features, bn_size, growth_rate, drop_rate, memory_efficient=False):
        super(_DenseBlock, self).__init__()
        for i in range(num_layers):
            layer = _DenseLayer(
                num_input_features + i * growth_rate,
            self.add_module('denselayer%d' % (i + 1), layer)

    def forward(self, init_features):
        features = [init_features]
        for name, layer in self.items():
            new_features = layer(features)
        return, 1)

class DenseNet(nn.Module):
    def __init__(self, growth_rate=32, block_config=(6,12,24,16),
                 num_init_features=64, bn_size=4, drop_rate=0, num_classes=1000, memory_efficient=False):

        super(DenseNet, self).__init__()

        # Convolution and pooling part from table-1
        self.features = nn.Sequential(OrderedDict([
            ('conv0', nn.Conv2d(1, num_init_features, kernel_size=3, stride=2,
                                padding=1, bias=False)),
            ('norm0', nn.BatchNorm2d(num_init_features)),
            ('relu0', nn.ReLU(inplace=True)),
            ('pool0', nn.MaxPool2d(kernel_size=2, stride=2, padding=1)),

        # Add multiple denseblocks based on config 
        # for densenet-121 config: [6,12,24,16]
        num_features = num_init_features
        for i, num_layers in enumerate(block_config):
            block = _DenseBlock(
            self.features.add_module('denseblock%d' % (i + 1), block)
            num_features = num_features + num_layers * growth_rate
            if i != len(block_config) - 1:
                # add transition layer between denseblocks to 
                # downsample
                trans = _Transition(num_input_features=num_features,
                                    num_output_features=num_features // 2)
                self.features.add_module('transition%d' % (i + 1), trans)
                num_features = num_features // 2

        # Final batch norm
        self.features.add_module('norm5', nn.BatchNorm2d(num_features))

        # Linear layer
        self.classifier = nn.Linear(num_features, num_classes)

        # Official init from torch repo.
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
            elif isinstance(m, nn.BatchNorm2d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.Linear):
                nn.init.constant_(m.bias, 0)

    def forward(self, x):
        features = self.features(x)
        out = F.relu(features, inplace=True)
        out = F.adaptive_avg_pool2d(out, (1, 1))
        out = torch.flatten(out, 1)
        out = self.classifier(out)
        return out

RuntimeError: Given input size: (128x1x1). Calculated output size: (128x0x0). Output size is too small

Your input image resolution should be 224x224 or larger.

hi blackberry, what do I change in this code for a data size 128 ? plzz

You should resize your input image.

blackberyy the size of the input image I cannot change it, but what do I change in this code to make it work?

Sorry, I need to correct myself: Input image size is normally 224x224 for standard CNNs, but they can still work on lower resolution images, until the last feature map size 1x1 or larger. With 224x224 input images, DenseNet features maps are 7x7 as far as I remember.

7*7 it did not work :pensive:

7x7 cannot work. Input image should be at least 32x32, not to result in error. However, normally, they should be at least 224x224, especially if you are using an ImageNet pretrained network.

32 * 32 cannot work blackberry :pensive:

RuntimeError: Given input size: (256x1x1). Calculated output size: (256x0x0). Output size is too small