Where is the pretrained model of vgg-16 from?

wasidennis / AdaptSegNet

Learning to Adapt Structured Output Space for Semantic Segmentation, CVPR 2018 (spotlight)

850 stars 203 forks source link

Where is the pretrained model of vgg-16 from? #23

Closed mathfinder closed 6 years ago

mathfinder commented 6 years ago

I want to know how to get the pretrained model you use for training. Is it trained on ImageNet by pytorch official? Or is downloaded from here: http://www.robots.ox.ac.uk/~vgg/software/very_deep/caffe/VGG_ILSVRC_16_layers.caffemodel?

wasidennis commented 6 years ago

The pre-trained model in this repo is downloaded from deeplab v2 (ImageNet + COCO ).

hfslyc commented 6 years ago

what @wasidennis mentioned is actually for resnet-101. The VGG16 pretrained model is the original imagenet pretrained weight transferred to pytorch format.

you can download it here: https://github.com/jcjohnson/pytorch-vgg