HasnainRaz/FC-DenseNet-TensorFlow

seems error of logits reshape when num_classes != 2

LilianYe opened this issue · 0 comments

In function xentropy_loss() of model.py
logits = tf.reshape(logits, [tf.shape(logits)[0], -1, 2])
should be
logits = tf.reshape(logits, [tf.shape(logits)[0], -1, self.num_classes])