We manually converted the original torch models into caffe format from https://github.com/liuzhuang13/DenseNet.

For details of these networks, please read the original paper:

• Densely Connected Convolutional Networks

The top-1/5 accuracy rates by using single center crop (crop size: 224x224, image size: 256xN)

Update (July 27, 2017): for your convenience, we also provide a link to these models on Baidu Disk.

Due to compatibility reasons, several modifications have been made:

• BGR mean values [103.94,116.78,123.68] are subtracted
• scale: 0.017 is used, instead of the original std values for image preprocessing
• ceil_mode: false is used in the first pooling layers ('pool1')