shekkizh / FCN.tensorflow

Tensorflow implementation of Fully Convolutional Networks for Semantic Segmentation (http://fcn.berkeleyvision.org)
MIT License
1.25k stars 527 forks source link

MemoryError #78

Closed MandyMo closed 6 years ago

MandyMo commented 6 years ago

Step: 5050, Train_loss:1.6929 ** Epochs completed: 1** Traceback (most recent call last): File "FCN.py", line 223, in tf.app.run() File "C:\Users\medusa\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\platform\app.py", line 48, in run _sys.exit(main(_sys.argv[:1] + flags_passthrough)) File "FCN.py", line 191, in main train_images, train_annotations = train_dataset_reader.next_batch(FLAGS.batch_size)tch(FLAGS.batch_size) File "D:\ML\FCN\FCN.tensorflow\BatchDatsetReader.py", line 72, in next_batch self.images = self.images[perm] MemoryError

i got this runtime error, anybody have meet the same runtime error?

shekkizh commented 6 years ago

Closing due to inactivity. Exhausted ram/ cache?!