Extremely bad results and recurring exception
tombenj opened this issue · comments
Results on the pre-trained data are turning really awful:
And the recurring exception that everyone seems to get over and over again is:
InvalidArgumentError (see above for traceback): Number of ways to split should evenly divide the split dimension, but got split_dim 3 (size = 4) and num_split 3
@MarvinTeichmann is anyone able to help?
Hey all.
The above exception is being caused due to the presence of alpha channel in the input image, which can be removed by specifying this:
# Existing line in demo.py
image = scp.misc.imread(input_image)
# Add this line next to it
image = image[:,:,:3]
I even tried increasing the brightness as discussed in #129 , but that doesn't seem to work. Is there any way the input image needs to be pre-processed/transformed that can improve the results for road detection?
Ping @MarvinTeichmann