search

HasnainRaz / FC-DenseNet-TensorFlow

Fully Convolutional DenseNet (A.K.A 100 layer tiramisu) for semantic segmentation of images implemented in TensorFlow.
MIT License
123 stars 41 forks source link

two bugs? #10

Closed zem007 closed 6 years ago

zem007 commented 6 years ago

I found two issues in the process of running the codes.

  1. Model.py (line#: 66), it should be 'def batch_norm(self, x, training, name)'?

  2. Model.py (line#: 229), it should be 'x = self.dense_block(x, training, block_nb - 1, 'up_denseblock' + str(block_nb))' ?

HasnainRaz commented 6 years ago

  1. batch_norm is a static method (you can see the @staticmethod decorator on top of it), which means it doesn't require the self argument.

  2. The for loop already starts with block_nb - 1, so there is no need to that in the method call.

zem007 commented 6 years ago

thank you!