You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
您好,我在使用您arcface tf2.0版本完成了tfrecord的转换,在使用train_mutigpus训练的时候出现了报错,错误如下:
train_multigpu.py:92 train_step
step_fn, args=(_images, _labels, _regCoef,))
train_multigpu.py:87 step_fn
zip(gradients, model.trainable_variables))
ValueError: colocate_vars_with must only be passed a variable created in this tf.distribute.Strategy.scope(), not: <tf.Variable 'train_model/arcfacelayer/kernel:0' shape=(512, 85742) dtype=float32, numpy=array......................................................................., dtype=float32)>
请问您知道这是什么问题吗?我目前查下来不知道怎样去解决,感谢您的分享!