Aymeric Damien

Are you using GPU? Usually, this error raises when GPU memory is full.

Please make sure you are running TensorFlow 2.0: ```pip install tensorflow==2.0.0-beta1```

It doesn't really run the 'whole' graph 3 times for 1 loop, it only runs the computation subgraph necessary for every operation you run (So calling `cost` will not compute...

I think this should works... Can you try to just run sess.run([cost])?

Results are correct, because you haven't started to train (by running the optimizer op) your network has random weights, so it give you such results. You can see accuracy is...

Yes, currently only python 2 is supported. I will work on making it compatible with python 3 as well, it should just require some minor changes

This code is working perfectly fine for me. Can you try to re-install tflearn?

You can load/save model at every loop to keep weights. Also note that DNN has its own session, so you do not need to run ``` sess.run(tf.initialize_all_variables()) ``` Also this...

Can you try: ``` python model.load(model_file, weights_only=True) ``` It should load only weights and not unecessary other variables.

Can you try to add 'restore=False' to regression layer?