Torchvision.models of pytorch

1

I wonder which dataset is the pretrained model in pytorch? ILSVRC-2012? ILSVRC-2014? or others?

2

The pre-trained models were trained on ImageNet-12:
discussion in other thread

3

I wonder why the top-5 and top-1 error is significantly higher than the same model in caffe?

4

I wonder why the top-5 and top-1 error is significantly higher than the same model in caffe?

5

Which model do you have in mind?

6

For example, in https://github.com/BVLC/caffe/wiki/Model-Zoo#resnets-deep-residual-networks-from-msra-at-imagenet-and-coco-2015, the top-5 of vgg-16 is 7.4%, but 9.62% and 8.5%(with bn) in pytorch.

7

I’m not sure, but I assume the site reports the multi-scale evaluation instead of the single-scale one.
You can see the different error rates in Table 3 and 4 in their paper.
Table 3 comes pretty close to the pre-trained models.

8

Thank you for your reply!