search

DLR-RM / AugmentedAutoencoder

Official Code: Implicit 3D Orientation Learning for 6D Object Detection from RGB Images
MIT License
338 stars 97 forks source link

Segmentation fault (core dumped) #49

Closed YinnnnnnnnS closed 4 years ago

YinnnnnnnnS commented 4 years ago

Describe the bug

  1. I can't use "ae_train exp_group/my_autoencoder -d" becauese " command not found" so I use "python ae_train exp_group/my_autoencoder -d" 2.When I use "python ae_train exp_group/my_autoencoder -d", after loading pictures, the program quit in "reconstr_train = sess.run(decoder.x, feed_dict={queue.x:this_x})" (line 140 in ae_train.py) the bug info is "Segmentation fault (core dumped)" 3.And when I check the shape of this_x and queue.x, the output is "('queue.x', TensorShape([Dimension(None), Dimension(128), Dimension(128), Dimension(3)])) ('this_x', (128, 128, 3))" 4.I have also changed the batch size and the number of pictures, it seems not to be the memory problem of GPU

System Info

MartinSmeyer commented 4 years ago

Do you have .local/bin/ in your PATH? Then ae_train ... should work after pip install --user .

Did you try to run this on a machine without a display? Does ae_train without -d work?

DateBro commented 4 years ago

@YinnnnnnnnS 1. Maybe you can try to add 'export PATH=$PATH:/home/xxx/.local/bin/' in your ~/.bashrc file to solve the 'command not found' problem.

MartinSmeyer commented 4 years ago

closed because inactive