What's wrong with me ?

[XiaoZzai]

Initializing the variables of the model Initialization finished [-] init_model : 1.16156 sec, which is 0.01936 mins, which is 0.00032 hours Traceback (most recent call last): File "main.py", line 19, in main() File "main.py", line 15, in main agent.run() File "/media/arch760/My Passport/TFSegmentation/utils/misc.py", line 18, in timed result = f(*args, **kwargs) File "/media/arch760/My Passport/TFSegmentation/agent.py", line 88, in run self.operator = self.operator(self.args, self.sess, self.model, self.model) File "/media/arch760/My Passport/TFSegmentation/train/train.py", line 50, in init super().init(args, sess, train_model, test_model) File "/media/arch760/My Passport/TFSegmentation/train/basic_train.py", line 39, in init save_relative_paths=True) File "/home/arch760/.local/lib/python3.5/site-packages/tensorflow/python/training/saver.py", line 1338, in init self.build() File "/home/arch760/.local/lib/python3.5/site-packages/tensorflow/python/training/saver.py", line 1347, in build self._build(self._filename, build_save=True, build_restore=True) File "/home/arch760/.local/lib/python3.5/site-packages/tensorflow/python/training/saver.py", line 1384, in _build build_save=build_save, build_restore=build_restore) File "/home/arch760/.local/lib/python3.5/site-packages/tensorflow/python/training/saver.py", line 813, in _build_internal saveables = self._ValidateAndSliceInputs(names_to_saveables) File "/home/arch760/.local/lib/python3.5/site-packages/tensorflow/python/training/saver.py", line 661, in _ValidateAndSliceInputs names_to_saveables = BaseSaverBuilder.OpListToDict(names_to_saveables) File "/home/arch760/.local/lib/python3.5/site-packages/tensorflow/python/training/saver.py", line 638, in OpListToDict name) ValueError: At least two variables have the same name: network/conv1_x/bn1/mu

[erolrecep]

Which version of tensorflow do you use? I've faced the same issue when I was trying to run with v1.7.1 .

[XiaoZzai]

@erolrecep
1.8.0 ...

[erolrecep]

@18605973470 On requirements files they say 1.3.0 for tensorflow-gpu, 1.4.0 for tensorflow.