search

arnab39 / FewShot_GAN-Unet3D

Tensorflow implementation of our paper: Few-shot 3D Multi-modal Medical Image Segmentation using Generative Adversarial Learning
MIT License
377 stars 82 forks source link

when I 'run main.py --testing' have some errors FailedPreconditionError (see above for traceback): Attempting to use uninitialized value D/d_up3_deconv/g [[node D/d_up3_deconv/g/read (defined at ../lib/operations.py:87) = Identity[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:0"](D/d_up3_deconv/g)]] [[{{node ArgMax/_3}} = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_491_ArgMax", tensor_type=DT_INT64, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]] #4

Open tongxuezhou opened 5 years ago

arnab39 commented 5 years ago

Hi, Firstly, I would request you not to open a new issue everytime you face a problem. You can continue posting on the same issue with new comments. Also please put specific title and under it post your entire error message which helps to keep the issues section clean. I will soon get back to you with your problem.

tongxuezhou commented 5 years ago

@arnab39 thanks for your reminding, I'm new to use github, I'll follow that.

tongxuezhou commented 5 years ago

@arnab39 hi, did you check the problem? looking forward to your reply~

hassaanmahmood commented 5 years ago

I am also getting same error in python main_unet.py --testing . Resolved it with sess.run(tf.global_variables_initializer()) now getting out of memory error. trying to fix it using GPU allocation. or any guidance how to solve it?

hassaanmahmood commented 5 years ago

I am also getting same error in python main_unet.py --testing . Resolved it with sess.run(tf.global_variables_initializer()) now getting out of memory error. trying to fix it using GPU allocation. or any guidance how to solve it?

I solved this issue by `

 with tf.device('/device:GPU:2'):

     with tf.variable_scope('U') as scope:`

in def trained_network_dis(patch, reuse=False):

hrmello commented 5 years ago

I solved this issue by changing the following in test.py: In, def test, write

    # To load the saved checkpoint
    saver = tf.train.Saver()
    with tf.Session() as sess:
      sess.run(tf.global_variables_initializer()) #added line to make testing work
      try:
        load_model(F.best_checkpoint_dir, sess, saver)
        print(" Checkpoint loaded succesfully!....\n")
      except:
        print(" [!] Checkpoint loading failed!....\n")
        return