chenharel1 comments

Repositories
Issues
Comments

Results 3 comments of


                                            chenharel1

Where is the given pre-trained model, i.e. the checkpoint?

The code link brings me to a page in chinese (which I can't read). I press on the download icon (I think it is...) ![download_icon](https://user-images.githubusercontent.com/49487954/58965237-e9567380-87b8-11e9-840d-e51077f89d71.png) and I downloaded an .exe...

Variable rnn/lstm_cell/weights/Adam/ does not exist, or was not created with tf.get_variable(). Did you mean to set reuse=None in VarScope?

Thanks @123liluky , your solution worked for me.

output/trainging-20-log.txt

@wei-1234567 You have to set restore_weights=False. Then in the following "if" phrase: (line ~167) if (self.restore_weights == True): sess.run(init) self.saver.restore(sess, self.rolo_weights_file) print "Loading complete!" + '\n' else: sess.run(init) The code...