search

davidsandberg / facenet

Face recognition using Tensorflow
MIT License
13.83k stars 4.81k forks source link

train models.inception_resnet_v2 #44

Closed VictoryDong closed 8 years ago

VictoryDong commented 8 years ago

hi, when run facenet_train.py to train inception_resnet_v2 ,I met this problem : Traceback (most recent call last): File "facenet_train.py", line 339, in main(parse_arguments(sys.argv[1:])) File "facenet_train.py", line 70, in main phase_train=phase_train_placeholder, weight_decay=args.weight_decay) File "/home/mqq/victorydong/source/face2/facenet/facenet/src/models/inception_resnet_v1.py", line 135, in inference dropout_keep_prob=keep_probability) File "/home/mqq/victorydong/source/face2/facenet/facenet/src/models/inception_resnet_v1.py", line 157, in inception_resnet_v1 with tf.variable_scope(scope, 'InceptionResnetV1', [inputs], reuse=reuse): File "/home/mqq/anaconda2/lib/python2.7/contextlib.py", line 84, in helper return GeneratorContextManager(func(_args, *_kwds)) TypeError: variable_scope() got multiple values for keyword argument 'reuse'

davidsandberg commented 8 years ago

Hi, Sorry for the delayed response. I have done some updates to the repo and also fixed the problem with the inception_resnet_v2. For most of the training I have done lately I have used inception_resnet_v1 model and training it as a classifier. It seems to work very well and I get a LFW accuracy of 0.94 when trained on the Casia/Facescrub dataset.