Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
baixb 7630504d50 | 2 years ago | |
---|---|---|
.. | ||
ECOLite | 2 years ago | |
bninception | 2 years ago | |
inceptionresnetv2 | 2 years ago | |
inceptionv4 | 2 years ago | |
.gitignore | 2 years ago | |
LICENSE | 2 years ago | |
README.md | 2 years ago | |
__init__.py | 2 years ago |
This is a porting of tensorflow pretrained models made by Remi Cadene and Micael Carvalho. Special thanks to Moustapha Cissé. All models have been tested on Imagenet.
This work was inspired by inception-v3.torch.
Please install torchnet-vision.
luarocks install --server=http://luarocks.org/dev torchnet-vision
Models available:
require 'image'
tnt = require 'torchnet'
vision = require 'torchnet-vision'
model = vision.models.inceptionresnetv2
net = model.load()
augmentation = tnt.transform.compose{
vision.image.transformimage.randomScale{
minSize = 299, maxSize = 350
},
vision.image.transformimage.randomCrop(299),
vision.image.transformimage.colorNormalize{
mean = model.mean, std = model.std
},
function(img) return img:float() end
}
net:evaluate()
output = net:forward(augmentation(image.lena()))
Currently available in this repo only On pytorch/vision maybe!
Models available:
import torch
from inceptionv4.pytorch_load import inceptionv4
net = inceptionv4()
input = torch.autograd.Variable(torch.ones(1,3,299,299))
output = net.forward(input)
In Tensorflow: Download tensorflow parameters and extract them in ./dump
directory.
python3 inceptionv4/tensorflow_dump.py
In Torch7 or PyTorch: Create the network, load the parameters, launch few tests and save the network in ./save
directory.
th inceptionv4/torch_load.lua
python3 inceptionv4/pytorch_load.py
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》