search

PJunhyuk / people-counting-pose

Odin: Pose estimation-based tracking and counting of people in videos
Apache License 2.0
173 stars 46 forks source link

ValueError: scale cannot be an integer: False #6

Closed sabaali93 closed 6 years ago

sabaali93 commented 6 years ago

I am getting this error when I try to run the code. Below is the full error: Traceback (most recent call last): File "video_tracking.py", line 41, in import video_pose File "/home/saba/Downloads/people-counting-pose-master/video_pose.py", line 50, in sess, inputs, outputs = predict.setup_pose_prediction(cfg) File "/home/saba/Downloads/people-counting-pose-master/nnet/predict.py", line 11, in setup_pose_prediction outputs = pose_net(cfg).test(inputs) File "/home/saba/Downloads/people-counting-pose-master/nnet/pose_net.py", line 90, in test heads = self.get_net(inputs) File "/home/saba/Downloads/people-counting-pose-master/nnet/pose_net.py", line 86, in get_net net, end_points = self.extract_features(inputs) File "/home/saba/Downloads/people-counting-pose-master/nnet/pose_net.py", line 54, in extract_features with slim.arg_scope(resnet_v1.resnet_arg_scope(False)): File "/home/saba/anaconda2/envs/py36/lib/python3.6/site-packages/tensorflow/contrib/slim/python/slim/nets/resnet_utils.py", line 257, in resnet_arg_scope weights_regularizer=regularizers.l2_regularizer(weight_decay), File "/home/saba/anaconda2/envs/py36/lib/python3.6/site-packages/tensorflow/contrib/layers/python/layers/regularizers.py", line 92, in l2_regularizer raise ValueError('scale cannot be an integer: %s' % (scale,)) ValueError: scale cannot be an integer: False

Dishcreate commented 6 years ago

@sabaali93 , I got the same issue because I was using python 3.5 version. Then I move to python 3.6 it was fix.

PJunhyuk commented 6 years ago

Thanks for feedbacks and solutions!