Assign torch.cuda.FloatTensor - numpy

Question

I'd like to know how can I do the following code, but now using pytorch,
where dtype = torch.cuda.FloatTensor. There's the code straight python (using numpy):
import numpy as np
import random as rand
xmax, xmin = 5, -5
pop = 30
x = (xmax-xmin)*rand.random(pop,1)
y = x**2
[minz, indexmin] = np.amin(y), np.argmin(y)
best = x[indexmin]
This is my attempt to do it:
import torch
dtype = torch.cuda.FloatTensor
def fit (position):
return position**2
def main():
pop = 30
xmax, xmin = 5, -5
x= (xmax-xmin)*torch.rand(pop, 1).type(dtype)+xmin
y = fit(x)
[miny, indexmin] = torch.min(y,0)
best = x[indexmin]
print(best)
The last part where I define the variable best as the value of x with index equal to indexmin it doesn't work. What am I doing wrong here.
The following messenge appears:
RuntimeError: expecting vector of indices at /opt/conda/conda-bld/pytorch_1501971235237/work/pytorch-0.1.12/torch/lib/THC/generic/THCTensorIndex.cu:405

Answer 1

The above code works fine in pytorch 0.2. Let me analyze your code so that you can identify the problem.
x= (xmax-xmin)*torch.rand(pop, 1).type(dtype)+xmin
y = fit(x)
Here, x and y is a 2d tensor of shape 30x1. In the next line:
[miny, indexmin] = torch.min(y,0)
The returned tensor miny is a 2d tensor of shape 30x1 and indexmin is a 1d tensor of size 1. So, when you execute:
best = x[indexmin]
It (probably) gives error (in old pytorch version) because x is a 2d tensor of shape 30x1 and indexmin is a 1d tensor of size 1. To resolve this error, you can simply do:
best = x.squeeze()[indexmin] # x.squeeze() returns a 1d tensor of size `30`
Please note, a 2d tensor of shape 30x1 is same as a 1d tensor of size 30. So, you can modify your program as follows.
import torch
dtype = torch.cuda.FloatTensor
def main():
pop, xmax, xmin = 30, 5, -5
x= (xmax-xmin)*torch.rand(pop).type(dtype)+xmin
y = torch.pow(x, 2)
minz, indexmin = y.min(0)
best = x[indexmin]
print(best)
main()