Getting "Killed" ouput when trying to run training example about image-segmentation-keras

[SharathHuddar]

That's because you are using tensorflow backend. Use theano backend instead.
Install theano and use the following command

KERAS_BACKEND=theano THEANO_FLAGS=device=gpu,floatX=float32  python  train.py \
 --save_weights_path=weights/ex1 \
 --train_images="data/dataset1/images_prepped_train/" \
 --train_annotations="data/dataset1/annotations_prepped_train/" \
 --val_images="data/dataset1/images_prepped_test/" \
 --val_annotations="data/dataset1/annotations_prepped_test/" \
 --n_classes=10 \
 --input_height=320 \
 --input_width=640 \
 --model_name="vgg_segnet" 

[DawnMe]

@SharathHuddar Thanks, it worked!
Might be useful to add some more informative message rather than "Killed".

[divamgupta]

You see the message 'Killed' because the kernel kills your process. The is probably due to lack of resources.

Look at:
https://stackoverflow.com/questions/726690/who-killed-my-process-and-why

And it is not recommended to train deep learning models without a GPU. It would be extremely slow.

[horo2016]

it maybe memory overrun ,smaller the picture size