I want to design a binary classifier,
I have a dataset with size 5000 and 3 columns (
‘text_a’ a vector with 1024 numbers(this is the output of Roberta),
‘text_b’ a vector with 1024 numbers,
in each row, if the text_a and text_b be similar the label would be 1 otherwise it would be 0.
I want to design a classifier that gives 2 inputs, each input with size 1024 but I can’t.
could you help me how should be the first layer? or the whole model?
Not clearly understood the problem statement. Please write something extra or in different language for me to help you out.
thanks for your reply,
I am a beginner in Paytorch. And I only work with networks with one input.
Here we have two inputs for a classifier and I do not know what the network architecture and input layer should be like?
Okay. So lets do one thing. Since I am not able to grasp your task, so you can share your dataset with me via email. I will give it time and update you sometime tomorrow.
And lets chat on private msg regarding this.