Error in tanh1<-mx.symbol.Convolution(data=conv1, act_type="relu")

1

Please help I am getting an error in R the following code :

conv1<-mx.symbol.Convolution(data=data,kernel=c(5,5),num_filter=20)

tanh1<-mx.symbol.Convolution(data=conv1, act_type="relu")

ERROR: Error in mx.varg.symbol.Convolution(list(...)) : 
  Cannot find argument 'act_type', Possible Arguments:
----------------
kernel : Shape(tuple), required
    Convolution kernel size: (w,), (h, w) or (d, h, w)
stride : Shape(tuple), optional, default=[]
    Convolution stride: (w,), (h, w) or (d, h, w). Defaults to 1 for each dimension.
dilate : Shape(tuple), optional, default=[]
    Convolution dilate: (w,), (h, w) or (d, h, w). Defaults to 1 for each dimension.
pad : Shape(tuple), optional, default=[]
    Zero pad for convolution: (w,), (h, w) or (d, h, w). Defaults to no padding.
num_filter : int (non-negative), required
    Convolution filter(channel) number
num_group : int (non-negative), optional, default=1
    Number of group partitions.
workspace : long (non-negative), optional, default=1024
    Maximum temporary workspace allowed (MB) in convolution.This parameter has two usages. When CUDNN is not used, it determines the effective batch size of the convolution kernel. When CUDNN is used, it controls the maximum tempora
2

Hi @SomyKamble,

You can use the following code:

conv1<-mx.symbol.Convolution(data=data,kernel=c(5,5),num_filter=20)
tanh<-mx.symbol.Activation(data=conv1, act_type="relu")

Note that you called your variable tanh, but here you are using a relu activation. If you actually want a tanh activation you should use:

conv1<-mx.symbol.Convolution(data=data,kernel=c(5,5),num_filter=20)
tanh<-mx.symbol.Activation(data=conv1, act_type="tanh")