I try to solve a ML problem using a NN with RELU activation function. my data points look like this :
X[i] : list of 240 values in [0,1]
I use a batch_size > 1 s I use stack to convert my Xs to tensor and I get the following error when using the RELU function.
It is the first NN I design, I don't really know how to handle this one and would like some help =), thanks in advance.
The problem seems to be that variables input and weight.t() have incompatible dimensions for the matrix multiplication. Perhaps, you should just get rid of the transpose for weight, and it will work just fine.
Pytorch tensor for RELU
Hello,
I try to solve a ML problem using a NN with RELU activation function. my data points look like this :
X[i] : list of 240 values in [0,1]
I use a batch_size > 1 s I use stack to convert my Xs to tensor and I get the following error when using the RELU function.
It is the first NN I design, I don't really know how to handle this one and would like some help =), thanks in advance.
The problem seems to be that variables
inputandweight.t()have incompatible dimensions for the matrix multiplication. Perhaps, you should just get rid of the transpose forweight, and it will work just fine.1
Add comment