image = tf.placeholder(tf.float32, shape=[None, IMAGE_SIZE, IMAGE_SIZE, 6]).

shekkizh / FCN.tensorflow

Tensorflow implementation of Fully Convolutional Networks for Semantic Segmentation (http://fcn.berkeleyvision.org)

MIT License

1.25k stars 527 forks source link

image = tf.placeholder(tf.float32, shape=[None, IMAGE_SIZE, IMAGE_SIZE, 6]). #71

Closed MLjian closed 6 years ago

MLjian commented 7 years ago

image = tf.placeholder(tf.float32, shape=[None, IMAGE_SIZE, IMAGE_SIZE, 6], name="input_image"). If I have a 6 channel image data, parameter:3-->6, does it work?

shekkizh commented 6 years ago

Closing due to inactivity. It should.

summer17s commented 6 years ago

@MLjian hey bro, I have same issue about 6 channels data training , have you solve this problem?