about model-tiramisu-67.py

0bserver07 / One-Hundred-Layers-Tiramisu

Keras Implementation of The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation by (Simon Jégou, Michal Drozdzal, David Vazquez, Adriana Romero, Yoshua Bengio)

https://arxiv.org/abs/1611.09326

MIT License

197 stars 54 forks source link

about model-tiramisu-67.py #10

Open alexliyang opened 6 years ago

alexliyang commented 6 years ago

layer_bottleneck = self.DenseBlock(15,408, layer_5a_down, enc_model_layers, 'layer_bottleneck') # m = 348 + 5*12 = 408

here DenseBlock(15,408... is 15 or 5 ?

when we count m = 348 + 5*12 = 408 use 5 , but , the parameter 15 should be used ?