indices error while training

[moeinsamadi]

Hi. I encountered with the following error while training:
`Prepare Data...

Traceback (most recent call last):
File "main.py", line 53, in
tf.app.run()
File "/home/hermes/.local/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 124, in run
sys.exit(main(argv))
File "main.py", line 45, in main
rdn.train(FLAGS)
File "/home/hermes/RDN-TensorFlow-master/model.py", line 272, in train
input_setup(config)
File "/home/hermes/RDN-TensorFlow-master/utils.py", line 194, in input_setup
make_sub_data(data, config)
File "/home/hermes/RDN-TensorFlow-master/utils.py", line 126, in make_sub_data
input, label_, = preprocess(data[i], config.scale, eng, mdouble)
File "/home/hermes/RDN-TensorFlow-master/utils.py", line 55, in preprocess
label_ = modcrop(img, scale)
File "/home/hermes/RDN-TensorFlow-master/utils.py", line 45, in modcrop
img = img[0:h, 0:w, :]
TypeError: slice indices must be integers or None or have an index method`

I used python3 branch. Also I should mention that I put all images to RDN-TensorFlow/Train/DIV2K_train_HR.
What should I do now?
Thanks

[LiUzHiAn]

@moeinsamadi
hi, this error is caused by python3 version. In python3 branch, the / is float number division , while // is division for integer. So, you have to complete this modification of line （43、44、48、49、155、156） in utils.py.
BTW, could you please share your hyperprameters configuration?

[moeinsamadi]

@LiUzHiAn
Thank you very much. It is working now!
These are the hyperparameters:
flags.DEFINE_integer("image_size", 32, "the size of image input")
flags.DEFINE_integer("c_dim", 3, "the size of channel")
flags.DEFINE_integer("scale", 3, "the size of scale factor for preprocessing input image")
flags.DEFINE_integer("stride", 16, "the size of stride")
flags.DEFINE_integer("epoch", 2, "number of epoch")
flags.DEFINE_integer("batch_size", 128, "the size of batch")
flags.DEFINE_float("learning_rate", 1e-4 , "the learning rate")
flags.DEFINE_integer("D", 5, "D")
flags.DEFINE_integer("C", 3, "C")
flags.DEFINE_integer("G", 64, "G")
flags.DEFINE_integer("G0", 64, "G0")
flags.DEFINE_integer("kernel_size", 3, "the size of kernel")

Training seems to be so time consuming! I ran the training on a laptop with Intel R Core i5 CPU M 480 2.67GHz × 4 and 3.7 GiB Memory. Training time for each epoch was approximately 3 hour!
I only changed "batch_size" from 64 (default) to 128.