-
Netscope homepage
http://ethereon.github.io/netscope/quickstart.html -
CaffeNet
http://ethereon.github.io/netscope/#/preset/caffenet -
FCN: fully convolutional network
http://ethereon.github.io/netscope/#/preset/fcn-8s-pascal -
GoogLenet
http://ethereon.github.io/netscope/#/preset/googlenet -
NIN (Network in Network)
http://ethereon.github.io/netscope/#/preset/nin -
[ResNet-50] (http://ethereon.github.io/netscope/#/gist/db945b393d40bfa26006)
-
[ResNet-101] (http://ethereon.github.io/netscope/#/gist/b21e2aae116dc1ac7b50)
-
[ResNet-152] (http://ethereon.github.io/netscope/#/gist/d38f3e6091952b45198b)
-
SEnet (author's version)
http://ethereon.github.io/netscope/#/gist/9b7742a9f0c5ee8c6a55f7ba6911152d -
SE RESNET 50 V1
http://ethereon.github.io/netscope/#/gist/36a20d27cba38695b4a44632d7af608c -
MobileNet
http://ethereon.github.io/netscope/#/gist/2883d142ae486d4237e50f392f32994e -
DenseNet
The top-1/5 accuracy rates by using single center crop (crop size: 224x224, image size: 256xN)
Network | Top-1 | Top-5 | Download | Architecture |
---|---|---|---|---|
DenseNet 121 (k=32) | 74.91 | 92.19 | caffemodel (30.8 MB) | netscope |
DenseNet 169 (k=32) | 76.09 | 93.14 | caffemodel (54.6 MB) | netscope |
DenseNet 201 (k=32) | 77.31 | 93.64 | caffemodel (77.3 MB) | netscope |
DenseNet 161 (k=48) | 77.64 | 93.79 | caffemodel (110 MB) | netscope |