I’m implementing an RBF network by using some beginner examples from Pytorch Website. I have a problem when implementing the kernel bandwidth differentiation for the network. Also, I would like to know whether my attempt to implement the idea is fine. This is a code sample to reproduce the issue. Thanks
# -*- coding: utf-8 -*-
import torch
from torch.autograd import Variable
def kernel_product(x,y, mode = "gaussian", s = 1.):
x_i = x.unsqueeze(1)
y_j = y.unsqueeze(0)
xmy = ((x_i-y_j)**2).sum(2)
if mode == "gaussian" : K = torch.exp( - xmy/s**2) )
elif mode == "laplace" : K = torch.exp( - torch.sqrt(xmy + (s**2)))
elif mode == "energy" : K = torch.pow( xmy + (s**2), -.25 )
return torch.t(K)
class MyReLU(torch.autograd.Function):
"""
We can implement our own custom autograd Functions by subclassing
torch.autograd.Function and implementing the forward and backward passes
which operate on Tensors.
"""
@staticmethod
def forward(ctx, input):
"""
In the forward pass we receive a Tensor containing the input and return
a Tensor containing the output. ctx is a context object that can be used
to stash information for backward computation. You can cache arbitrary
objects for use in the backward pass using the ctx.save_for_backward method.
"""
ctx.save_for_backward(input)
return input.clamp(min=0)
@staticmethod
def backward(ctx, grad_output):
"""
In the backward pass we receive a Tensor containing the gradient of the loss
with respect to the output, and we need to compute the gradient of the loss
with respect to the input.
"""
input, = ctx.saved_tensors
grad_input = grad_output.clone()
grad_input[input < 0] = 0
return grad_input
dtype = torch.cuda.FloatTensor
N, D_in, H, D_out = 64, 1000, 100, 10
# Create random Tensors to hold input and outputs, and wrap them in Variables.
x = Variable(torch.randn(N, D_in).type(dtype), requires_grad=False)
y = Variable(torch.randn(N, D_out).type(dtype), requires_grad=False)
# Create random Tensors for weights, and wrap them in Variables.
w1 = Variable(torch.randn(H, D_in).type(dtype), requires_grad=True)
w2 = Variable(torch.randn(H, D_out).type(dtype), requires_grad=True)
# I've created this scalar variable (the kernel bandwidth)
s = Variable(torch.randn(1).type(dtype), requires_grad=True)
learning_rate = 1e-6
for t in range(500):
# To apply our Function, we use Function.apply method. We alias this as 'relu'.
relu = MyReLU.apply
# Forward pass: compute predicted y using operations on Variables; we compute
# ReLU using our custom autograd operation.
# y_pred = relu(x.mm(w1)).mm(w2)
y_pred = relu(kernel_product(w1, x, s)).mm(w2)
# Compute and print loss
loss = (y_pred - y).pow(2).sum()
print(t, loss.data[0])
# Use autograd to compute the backward pass.
loss.backward()
# Update weights using gradient descent
w1.data -= learning_rate * w1.grad.data
w2.data -= learning_rate * w2.grad.data
# Manually zero the gradients after updating weights
w1.grad.data.zero_()
w2.grad.data.zero_()
However I get this error, which disappears when I simply use a fixed scalar in the default input parameter of kernel_product():
RuntimeError: eq() received an invalid combination of arguments - got (str), but expected one of:
* (float other)
didn't match because some of the arguments have invalid types: (str)
* (Variable other)
didn't match because some of the arguments have invalid types: (str)
Thank you for your help