prasunroy / cnn-on-degraded-images Goto Github PK

Hello,

When I try to run train_deepcnn.py script I get this error:

Traceback (most recent call last):
File "train_deepcnn.py", line 349, in
train()
File "train_deepcnn.py", line 339, in train
initial_epoch=0)
File "/home/raov/.virtualenvs/deep_learning/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training.py", line 819, in fit
use_multiprocessing=use_multiprocessing)
File "/home/raov/.virtualenvs/deep_learning/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training_v2.py", line 397, in fit
prefix='val_')
File "/usr/lib/python3.6/contextlib.py", line 99, in exit
self.gen.throw(type, value, traceback)
File "/home/raov/.virtualenvs/deep_learning/lib/python3.6/site-packages/tensorflow_core/python/keras/engine/training_v2.py", line 771, in on_epoch
self.callbacks.on_epoch_end(epoch, epoch_logs)
File "/home/raov/.virtualenvs/deep_learning/lib/python3.6/site-packages/tensorflow_core/python/keras/callbacks.py", line 302, in on_epoch_end
callback.on_epoch_end(epoch, logs)
File "/home/raov/.virtualenvs/deep_learning/lib/python3.6/site-packages/mlutils-0.1.0-py3.6.egg/mlutils/callbacks.py", line 70, in on_epoch_end
File "/home/raov/.virtualenvs/deep_learning/lib/python3.6/site-packages/mlutils-0.1.0-py3.6.egg/mlutils/callbacks.py", line 93, in _checkpoint
TypeError: unsupported format string passed to NoneType.format
2020-04-14 01:39:24.486882: W tensorflow/core/kernels/data/generator_dataset_op.cc:103] Error occurred when finalizing GeneratorDataset iterator: Cancelled: Operation was cancelled

I have NVIDIA GeForce GTX 1060 6 GB graphic card and I am using TensorFlow 2.1.0. CUDA and CUDNN are installed as given in the link:

https://www.tensorflow.org/install/gpu

I tried to search on Google, but couldn't find the solution for this. I found a similar error on StackOverflow (https://stackoverflow.com/questions/60000573/error-occurred-when-finalizing-generatordataset-iterator-cancelled-operation-w), but the accepted solution doesn't work for me. I believe that I have compatible CUDA and TensorFlow versions.

Please help!