sagieppel / Fully-convolutional-neural-network-FCN-for-semantic-segmentation-Tensorflow-implementation

68 stars 40 forks source link

getting error while running train.py file #5

Open neelima1719 opened 6 years ago

neelima1719 commented 6 years ago

I am getting following error

from ._conv import register_converters as _register_converters npy file loaded build model started WARNING:tensorflow:From /home/dtrl/Downloads/FCN/Fully-convolutional-neural-network-FCN-for-semantic-segmentation-Tensorflow-implementation-master/BuildNetVgg16.py:110: calling argmax (from tensorflow.python.ops.math_ops) with dimension is deprecated and will be removed in a future version. Instructions for updating: Use the axis argument instead FCN model built Setting up Saver...

Kernel died, restarting

sagieppel commented 6 years ago

All these messages are standard so I cant deduce much from it. In which line of the code the program crashed?

neelima1719 commented 6 years ago

The code basically giving error here:

Net = BuildNetVgg16.BUILD_NET_VGG16(vgg16_npy_path=model_path) #Create class for the network Net.build(image, NUM_CLASSES,keep_prob)# Create the net and load intial weights

......................................Get loss functions for neural net

work one loss f

Thanks and Regards Neelima Chauhan SRF DTRL, DRDO New Delhi

On Wed, May 9, 2018 at 3:29 PM, sagieppel notifications@github.com wrote:

All these messages are standard so I cant deduce much from it. In which line of the code the program crashed?

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/sagieppel/Fully-convolutional-neural-network-FCN-for-semantic-segmentation-Tensorflow-implementation/issues/5#issuecomment-387849566, or mute the thread https://github.com/notifications/unsubscribe-auth/AUBC14gtlVc9pdvkLsdKjsXu0YSs3GF0ks5tw0OqgaJpZM4T4BLR .

neelima1719 commented 6 years ago

Sorry for the prvs reply but now it is coming in this code: print("Setting up Saver...") saver = tf.train.Saver() sess.run(tf.global_variables_initializer()) #Initialize variables

Thanks and Regards Neelima Chauhan SRF DTRL, DRDO New Delhi

On Thu, May 10, 2018 at 1:28 AM, neelima chauhan < neelima.chauhan17@gmail.com> wrote:

The code basically giving error here:

Net = BuildNetVgg16.BUILD_NET_VGG16(vgg16_npy_path=model_path) #Create class for the network Net.build(image, NUM_CLASSES,keep_prob)# Create the net and load intial weights

......................................Get loss functions for neural net

work one loss f

Thanks and Regards Neelima Chauhan SRF DTRL, DRDO New Delhi

On Wed, May 9, 2018 at 3:29 PM, sagieppel notifications@github.com wrote:

All these messages are standard so I cant deduce much from it. In which line of the code the program crashed?

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/sagieppel/Fully-convolutional-neural-network-FCN-for-semantic-segmentation-Tensorflow-implementation/issues/5#issuecomment-387849566, or mute the thread https://github.com/notifications/unsubscribe-auth/AUBC14gtlVc9pdvkLsdKjsXu0YSs3GF0ks5tw0OqgaJpZM4T4BLR .

sagieppel commented 6 years ago

Not sure I understand. Does the program crush in the line: saver.restore(sess, ckpt.model_checkpoint_path)?