I didn't change test.py but the config file.
At the line 272(The third line here):
print(all_vars)net1ax_vars = [x for x in all_vars if x.name[0:len(net_name1ax) + 1]==net_name1ax + '/']saver1ax = tf.train.Saver(net1ax_vars)saver1ax.restore(sess, config_net1ax['model_file'])
I got an error:
ValueError: No variables to save
I checked all_vars and I found it seems that no variable named begin with net_name1ax
I tried to make my network inherit from 'TrainableLayer' and add a line below in function initsuper(MSNet, self).__init__(name=name)
But it didn't work
Do I have to rewrite the network by using NiftyNet?
Or rewrite test.py?
Hi, what is the config file you used? Did you change the value of 'net_name'? If you have changed that, I think you need to re-train the model with your new network names.
I didn't change test.py but the config file. At the line 272(The third line here):
print(all_vars)
net1ax_vars = [x for x in all_vars if x.name[0:len(net_name1ax) + 1]==net_name1ax + '/']
saver1ax = tf.train.Saver(net1ax_vars)
saver1ax.restore(sess, config_net1ax['model_file'])
I got an error: ValueError: No variables to save
I checked
all_vars
and I found it seems that no variable named begin withnet_name1ax
I tried to make my network inherit from 'TrainableLayer' and add a line below in function init
super(MSNet, self).__init__(name=name)
But it didn't workDo I have to rewrite the network by using NiftyNet? Or rewrite test.py?