titu1994 / DenseNet

DenseNet implementation in Keras
MIT License
707 stars 294 forks source link

I am confused, Is this right? #41

Closed pengzhipz closed 6 years ago

pengzhipz commented 6 years ago
def __dense_block(x, nb_layers, nb_filter, growth_rate, bottleneck=False, dropout_rate=None, weight_decay=1e-4, grow_nb_filters=True, return_concat_list=False):
    concat_axis = -1
    x_list = [x]
    for i in range(nb_layers):
        cb = __conv_block(x, growth_rate, bottleneck, dropout_rate, weight_decay)
        x_list.append(cb)
        x = concatenate([x, cb], axis=concat_axis)
        if grow_nb_filters:
            nb_filter += growth_rate

I want to know if this is a error to pass the grouth_rate to __conv_block, Why not nb_filters?

titu1994 commented 6 years ago

Weights load and predict properly for images, so it is correct.