Open Kishwar opened 6 years ago
Did you find any solution? I've the same problem....
Yes. Change tf version to 1.2 and python 2.7.
Thanks.
Yes. Change tf version to 1.2 and python 2.7.
Aren't these old version of python and TensorFlow? I have the same issue running tf 1.5.0 and python 3.6
You can try to delete this part:
col = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES) for x in col: tf.add_to_collection(tf.GraphKeys.VARIABLES, x )
It works fine for me
I faced a similar problem, one solution which seemed really cool and easy is to restarting the Kernel.
I am trying to run tflearn.DNN(net) on net below. I am getting error "At least two variables have the same name: FullyConnected/W".
Network building
net = tflearn.input_data([None, width, height]) net = tflearn.lstm(net, 128, dropout=0.8) net = tflearn.fully_connected(net, classes, activation='softmax') net = tflearn.regression(net, optimizer='adam', learning_rate=learning_rate, loss='categorical_crossentropy')