I manually defined a DenseNet as follows, the core code is from
torchvision.models.densenet121, the others are kept same. My denseNet definition:
class DenseNet(nn.Module): r"""Densenet-BC model class, based on `"Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf>`_ Args: growth_rate (int) - how many filters to add each layer (`k` in paper) block_config (list of 4 ints) - how many layers in each pooling block num_init_features (int) - the number of filters to learn in the first convolution layer bn_size (int) - multiplicative factor for number of bottle neck layers (i.e. bn_size * k features in the bottleneck layer) drop_rate (float) - dropout rate after each dense layer num_classes (int) - number of classification classes """ def __init__(self, growth_rate=32, block_config=(6, 12, 24, 16), num_init_features=64, bn_size=4, drop_rate=0, num_classes=198): super(DenseNet, self).__init__() # First convolution self.features = nn.Sequential(OrderedDict([ ('conv0', nn.Conv2d(3, num_init_features, kernel_size=7, stride=2, padding=3, bias=False)), ('norm0', nn.BatchNorm2d(num_init_features)), ('relu0', nn.ReLU(inplace=True)), ('pool0', nn.MaxPool2d(kernel_size=3, stride=2, padding=1)), ])) # Each denseblock num_features = num_init_features for i, num_layers in enumerate(block_config): block = _DenseBlock(num_layers=num_layers, num_input_features=num_features, bn_size=bn_size, growth_rate=growth_rate, drop_rate=drop_rate) self.features.add_module('denseblock%d' % (i + 1), block) num_features = num_features + num_layers * growth_rate if i != len(block_config) - 1: 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): nn.init.kaiming_normal_(m.weight) 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) feat = F.adaptive_avg_pool2d(out, (1, 1)).view(features.size(0), -1) out = self.classifier(feat) return feat.view(-1, 1024), out
By referring to PyTorch tutorial transfer learning chapter. I also try this without ImageNet weights:
densenet121 = models.densenet121(pretrained=False) num_ftrs = densenet121.classifier.in_features densenet121.classifier = nn.Linear(num_ftrs, 198)
After training, I got two quite different results. The latter one has 60%+ Acc, while the former one only has 20%+ Acc. I don’t know how to figure this out, since they are the same model. Is there anything wrong in my implementation?