Caxton

icon company @google icon location Taiwan

Results 2 comments of Caxton

Results very poor

I got a better result by removing this line: `saver = tf.train.import_meta_graph('./fcn_16s_checkpoint/model_fcn16s_final.ckpt.meta') # placed locally`

tf 1.0 changes tf.pack -> tf.stack

@vijtad I refer your code and got an error below, any idea? I also found that you use `prediction_mask = (pred_np.squeeze() == 8)` instead of `prediction_mask = (pred_np.squeeze() == 15)`,...