Repository navigation
torch.nn.functional.avg_pool1d is not working correctly #1249
Description
Hello! I've found that torch.nn.functional.avg_pool1d is not working as expected.
Here is my test code:
using TorchSharp;
var x = torch.zeros(5, 7, 128);
Console.WriteLine(x.metastr());
// [5x7x128], type = Float32, device = cpu
var y1 = torch.nn.functional.avg_pool1d(x, 2);
Console.WriteLine(y1.metastr());
// [5x7x127], type = Float32, device = cpu
var y2 = torch.nn.AvgPool1d(2).call(x);
Console.WriteLine(y2.metastr());
// [5x7x64], type = Float32, device = cpuAnd in PyTorch:
import torch
x = torch.zeros(5, 7, 128)
print(x.size())
# torch.Size([5, 7, 128])
y1 = torch.nn.functional.avg_pool1d(x, 2)
print(y1.size())
# torch.Size([5, 7, 64])
y2 = torch.nn.AvgPool1d(2)(x)
print(y2.size())
# torch.Size([5, 7, 64])There seems to be something going wrong with torch.nn.functional.avg_pool1d, while torch.nn.AvgPool1d still works well.
Activity
shaltielshmid commentedon Mar 2, 2024
Thank you for reporting! The discrepancy between PyTorch and TorchSharp is the default value assigned to the
strideparameter. I submitted a fix for the next version, but until then you can just specify thestrideparameter to be the same as thekernelSizeparameter to get the desired results.E.g.,
NiklasGustafsson commentedon Mar 5, 2024
Fixed in v0.102.1.