2021/2/18
(1)解决AttributeError: module ‘tensorflow’ has no attribute ‘ConfigProto’
AttributeError: module ‘tensorflow’ has no attribute 'ConfigProto’这个问题,这个是由于现在新版本中一些1.0版本的函数被和2.0版本函数区分开的缘故
tf.ConfigProto
修改为
tf.compat.v1.ConfigProto
(2)tensorflow使用Session模块时报错:AttributeError: module ‘tensorflow’ has no attribute ‘Session’
错误的意思是tensortflow模块没有Session属性,后来查阅资料发现,tensorflow2.0版本中的确没有Session这个属性,如果安装的是tensorflow2.0版本又想利用Session属性,可以将tf.Session()更改为:
tf.compat.v1.Session()
(3)Tried to step & times. The specified number of total steps is *
changing my steps_per_epoch in the OneCycleLR to 2*(len(train_loader)).
(4)Input and hidden tensors are not at the same device, found input tensor at cuda:0 and hidden tensor
Input and hidden tensors are not at the same device, found input tensor at cuda:0 and hidden tensor
解决:
change
def init_hidden(self, batch_size = 1):
return (torch.zeros(1, batch_size, self.hidden_size), torch.zeros(1, batch_size, self.hidden_size))
to
def init_hidden(self, batch_size = 1):
return (torch.zeros(1, batch_size, self.hidden_size).cuda(), torch.zeros(1, batch_size, self.hidden_size).cuda())