How to generate the train dataset? about east HOT 12 CLOSED

see in training samples

from east.

@argman @zxytim Why the code always stuck at time.sleep(0.01) in the def get_batch(num_workers=10, **kwargs): after read through the the images?

from east.

if you dont have enough cpu-cores, you should reduce the num_readers to a suitable number.

from east.

@argman Even I change the readers number to 4(I am sure I have at least 28 free cores), the stuck problem still there, below is the part of running log:
image_list.shape:(1000,)
1000 training images in ICDAR2015
enqueuer.queue isnot empty, sleep 0.01
enqueuer.queue isnot empty, sleep 0.01
enqueuer.queue isnot empty, sleep 0.01
.
.
.
.
enqueuer.queue isnot empty, sleep 0.01

from east.

I dont encounter your problem, maybe it's the version of keras, I use keras to provide mulithread
what's your keras version ?

from east.

@argman My keras version is 2.0.0, and which version of keras you used?

from east.

I've updated the code, no need to install keras now.

from east.

@argman Now I faced new problem while training, the tips is warning, the warning info:
icdar.py:210: RuntimeWarning: divide by zero encountered in float_scalars
theta = np.arctan((poly[3][0] - poly[0][0]) / (poly[3][1] - poly[0][1]))
icdar.py:216: RuntimeWarning: divide by zero encountered in float_scalars
theta = np.arctan((poly[2][0] - poly[1][0]) / (poly[2][1] - poly[1][1]))

from east.

its caused by some small polygons, you can ignore it.

from east.

@LearnerInGithub The newest version is using np.arctan2, the problem should be fixed.

from east.

@LearnerInGithub how did you solve the problem of being stucked in sleep(0.01) ??

from east.

@LearnerInGithub @rmmal how did you solve the problem of being stucked in sleep(0.01) ??

from east.