Torch7 trained models available

pretrained_models.lua

-- Available torch7 pre-trained models for download 

Alexnet (trained by me) 
cudnn: https://ln.sync.com/dl/3d9c28e80#cvjp4mjs-mc2y8jrt-9wq5yebx-yrdchcei
mean = {0.48037518790839, 0.45039056120456, 0.39922636057037}
std =  {0.27660147027775, 0.26883440068399, 0.28014687231841}
img size: 3x224x224

overfeat: https://github.com/jhjin/overfeat-torch
mean = {118.380948, 118.380948, 118.380948}
std = {61.896913, 61.896913, 61.896913}
img size: 3x221x221

VGG: 
-- to be added

google inception v3: https://github.com/Moodstocks/inception-v3.torch
cunn: https://ln.sync.com/dl/cbf63d8e0#24uv7grn-84vk7qdf-qgkba7s7-3pdtt52f (.t7 format)
cudnn: https://ln.sync.com/dl/c7a2fc8d0#2vk8twdk-haifrfwv-du3p3b4w-nnpbm8bu (.t7 format)
image normalization: img:mul(255):add(-128):mul(0.0078125)
img size: 3x229x229

resnet: https://github.com/facebook/fb.resnet.torch
resnet-18: http://torch7.s3-website-us-east-1.amazonaws.com/data/resnet-18.t7
resnet-34: http://torch7.s3-website-us-east-1.amazonaws.com/data/resnet-34.t7
resnet-50: http://torch7.s3-website-us-east-1.amazonaws.com/data/resnet-50.t7
resnet-101: http://torch7.s3-website-us-east-1.amazonaws.com/data/resnet-101.t7
mean = { 0.485, 0.456, 0.406 }
std = { 0.229, 0.224, 0.225 }
img size: 3x224x224