AttributeError: 'module' object has no attribute 'interpolate'

[zhengyuezhi]

Evaluation only
Traceback (most recent call last):
File "example/mpii.py", line 352, in
main(parser.parse_args())
File "example/mpii.py", line 94, in main
loss, acc, predictions = validate(val_loader, model, criterion, args.num_classes, args.debug, args.flip)
File "example/mpii.py", line 232, in validate
output = model(input)
File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/torch/nn/parallel/data_parallel.py", line 112, in forward
return self.module(*inputs[0], **kwargs[0])
File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "/media/zhengyuezhi/ren/RMPE_Experience/pytorch-pose/pose/models/hourglass.py", line 168, in forward
y = self.hgi
File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "/media/zhengyuezhi/ren/RMPE_Experience/pytorch-pose/pose/models/hourglass.py", line 93, in forward
return self._hour_glass_forward(self.depth, x)
File "/media/zhengyuezhi/ren/RMPE_Experience/pytorch-pose/pose/models/hourglass.py", line 84, in _hour_glass_forward
low2 = self._hour_glass_forward(n-1, low1)
File "/media/zhengyuezhi/ren/RMPE_Experience/pytorch-pose/pose/models/hourglass.py", line 84, in _hour_glass_forward
low2 = self._hour_glass_forward(n-1, low1)
File "/media/zhengyuezhi/ren/RMPE_Experience/pytorch-pose/pose/models/hourglass.py", line 84, in _hour_glass_forward
low2 = self._hour_glass_forward(n-1, low1)
File "/media/zhengyuezhi/ren/RMPE_Experience/pytorch-pose/pose/models/hourglass.py", line 88, in _hour_glass_forward
up2 = F.interpolate(low3, scale_factor=2)
AttributeError: 'module' object has no attribute 'interpolate'

hello,Why am I getting this error, my configuration is python2.7, torch==0.4.0

[bearpaw]

Hi, we use interpolate instead of upsampling in the latest version of code because upsampling seems would be deprecated in the future version of PyTorch.

To avoid this problem, just update your pytorch to version 1.0. I'll update the Readme later.

[bearpaw]

interpolate was introduced in Pytorch 0.4.1. I am closing this issue for no further discussion.