Hi,
I have a question: how can we train the model, so that it initializes the weights using the values from the checkpoint? In other words how do I fine-tune the model for a new dataset.
In the train.py file
"_with train_model.graph.as_default():
Loaded_train_model, global_step = model_helper.create_or_load_model(
Train_model.model, model_dir, trainsess, "train")"
The above content is modified to the following:
"_with tf.Session() as sess:
New_saver=tf.train.import_meta_graph('checkpoint_dir/MyModel-1000.meta')
New_saver.restore(sess,tf.train.latest_checkpoint('checkpointdir')"
I am newbie of nmt.I do not know where there is a problem with the above method. In the end, I failed.
I hope you can provide some suggestions.
Looking forward to your advice or answers.
Best regards,
Thank you very much!
Hi, I have a question: how can we train the model, so that it initializes the weights using the values from the checkpoint? In other words how do I fine-tune the model for a new dataset. In the train.py file "_with train_model.graph.as_default(): Loaded_train_model, global_step = model_helper.create_or_load_model( Train_model.model, model_dir, trainsess, "train")" The above content is modified to the following: "_with tf.Session() as sess: New_saver=tf.train.import_meta_graph('checkpoint_dir/MyModel-1000.meta') New_saver.restore(sess,tf.train.latest_checkpoint('checkpointdir')" I am newbie of nmt.I do not know where there is a problem with the above method. In the end, I failed. I hope you can provide some suggestions. Looking forward to your advice or answers. Best regards, Thank you very much!