Cadene / Tensorflow Model Zoo.torch
Licence: other
InceptionV3, InceptionV4, Inception-Resnet pretrained models for Torch7 and PyTorch
Stars: ✭ 280
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Tensorflow Model Zoo.torch
pigallery
PiGallery: AI-powered Self-hosted Secure Multi-user Image Gallery and Detailed Image analysis using Machine Learning, EXIF Parsing and Geo Tagging
Stars: ✭ 35 (-87.5%)
Mutual labels: inception, pretrained-models
Skip Thoughts.torch
Porting of Skip-Thoughts pretrained models from Theano to PyTorch & Torch7
Stars: ✭ 146 (-47.86%)
Mutual labels: torch, pretrained-models
HugsVision
HugsVision is a easy to use huggingface wrapper for state-of-the-art computer vision
Stars: ✭ 154 (-45%)
Mutual labels: pretrained-models
Bert Squad
SQuAD Question Answering Using BERT, PyTorch
Stars: ✭ 256 (-8.57%)
Mutual labels: pretrained-models
a-minimalist-guide
Walkthroughs for DSL, AirSim, the Vector Institute, and more
Stars: ✭ 37 (-86.79%)
Mutual labels: torch
object-flaw-detector-python
Detect various irregularities of a product as it moves along a conveyor belt.
Stars: ✭ 17 (-93.93%)
Mutual labels: pretrained-models
tensorflow-retrain-sample
A sample for tensorflow retraining
Stars: ✭ 25 (-91.07%)
Mutual labels: inception
gans-collection.torch
Torch implementation of various types of GAN (e.g. DCGAN, ALI, Context-encoder, DiscoGAN, CycleGAN, EBGAN, LSGAN)
Stars: ✭ 53 (-81.07%)
Mutual labels: torch
CogView
Text-to-Image generation. The repo for NeurIPS 2021 paper "CogView: Mastering Text-to-Image Generation via Transformers".
Stars: ✭ 708 (+152.86%)
Mutual labels: pretrained-models
i3d-tensorflow
Inflated 3D ConvNets for video understanding
Stars: ✭ 46 (-83.57%)
Mutual labels: inception
vak
a neural network toolbox for animal vocalizations and bioacoustics
Stars: ✭ 21 (-92.5%)
Mutual labels: torch
TOM-Net
TOM-Net: Learning Transparent Object Matting from a Single Image (CVPR 2018)
Stars: ✭ 74 (-73.57%)
Mutual labels: torch
Gluon Face
An unofficial Gluon FR Toolkit for face recognition. https://gluon-face.readthedocs.io
Stars: ✭ 264 (-5.71%)
Mutual labels: pretrained-models
syntaxdot
Neural syntax annotator, supporting sequence labeling, lemmatization, and dependency parsing.
Stars: ✭ 32 (-88.57%)
Mutual labels: pretrained-models
chemicalx
A PyTorch and TorchDrug based deep learning library for drug pair scoring.
Stars: ✭ 176 (-37.14%)
Mutual labels: torch
regnet.pytorch
PyTorch-style and human-readable RegNet with a spectrum of pre-trained models
Stars: ✭ 50 (-82.14%)
Mutual labels: pretrained-models
Deep Learning Model Convertor
The convertor/conversion of deep learning models for different deep learning frameworks/softwares.
Stars: ✭ 3,044 (+987.14%)
Mutual labels: torch
Tensorflow Model Zoo for Torch7 and PyTorch (OBSOLETE)
13/07/2017: Please use the new repo pretrained-models.pytorch which includes inceptionv4 and inceptionresnetv2 with a nicer API.
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.
Using pretrained models
Torch7
Requirements
Please install torchnet-vision.
luarocks install --server=http://luarocks.org/dev torchnet-vision
Models available:
- inceptionv3
- inceptionv4
- inceptionresnetv2
- resnet{18, 34, 50, 101, 152, 200}
- overfeat
- vggm
- vgg16
Simple example
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()))
PyTorch
Currently available in this repo only On pytorch/vision maybe!
Models available:
- inceptionv4
- inceptionresnetv2
Simple example
import torch
from inceptionv4.pytorch_load import inceptionv4
net = inceptionv4()
input = torch.autograd.Variable(torch.ones(1,3,299,299))
output = net.forward(input)
Reproducing the porting
Requirements
- Tensorflow
- Torch7
- PyTorch
- hdf5 for python3
- hdf5 for lua
Example of commands
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
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].