All Projects → jiweibo → Imagenet

jiweibo / Imagenet

Licence: mit
This implements training of popular model architectures, such as AlexNet, ResNet and VGG on the ImageNet dataset(Now we supported alexnet, vgg, resnet, squeezenet, densenet)

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Imagenet

Classification models
Classification models trained on ImageNet. Keras.
Stars: ✭ 938 (+644.44%)
Mutual labels:  resnet, imagenet, densenet, vgg
Keras Idiomatic Programmer
Books, Presentations, Workshops, Notebook Labs, and Model Zoo for Software Engineers and Data Scientists wanting to learn the TF.Keras Machine Learning framework
Stars: ✭ 720 (+471.43%)
Mutual labels:  resnet, densenet, vgg
Pytorch2keras
PyTorch to Keras model convertor
Stars: ✭ 676 (+436.51%)
Mutual labels:  resnet, imagenet, densenet
Tensornets
High level network definitions with pre-trained weights in TensorFlow
Stars: ✭ 982 (+679.37%)
Mutual labels:  resnet, densenet, vgg
Imagenet
Pytorch Imagenet Models Example + Transfer Learning (and fine-tuning)
Stars: ✭ 134 (+6.35%)
Mutual labels:  resnet, densenet, vgg
Pytorch Classification
Classification with PyTorch.
Stars: ✭ 1,268 (+906.35%)
Mutual labels:  resnet, imagenet, densenet
Chainer Cifar10
Various CNN models for CIFAR10 with Chainer
Stars: ✭ 134 (+6.35%)
Mutual labels:  resnet, densenet, vgg
pytorch2keras
PyTorch to Keras model convertor
Stars: ✭ 788 (+525.4%)
Mutual labels:  imagenet, densenet, resnet
python cv AI ML
用python做计算机视觉,人工智能,机器学习,深度学习等
Stars: ✭ 73 (-42.06%)
Mutual labels:  vgg, densenet, resnet
Tianchi Medical Lungtumordetect
天池医疗AI大赛[第一季]:肺部结节智能诊断 UNet/VGG/Inception/ResNet/DenseNet
Stars: ✭ 314 (+149.21%)
Mutual labels:  resnet, densenet, vgg
Cnn Models
ImageNet pre-trained models with batch normalization for the Caffe framework
Stars: ✭ 355 (+181.75%)
Mutual labels:  resnet, imagenet, vgg
Medicalzoopytorch
A pytorch-based deep learning framework for multi-modal 2D/3D medical image segmentation
Stars: ✭ 546 (+333.33%)
Mutual labels:  resnet, densenet
Ir Net
This project is the PyTorch implementation of our accepted CVPR 2020 paper : forward and backward information retention for accurate binary neural networks.
Stars: ✭ 119 (-5.56%)
Mutual labels:  resnet, imagenet
Resnet Imagenet Caffe
train resnet on imagenet from scratch with caffe
Stars: ✭ 105 (-16.67%)
Mutual labels:  resnet, imagenet
Mmclassification
OpenMMLab Image Classification Toolbox and Benchmark
Stars: ✭ 532 (+322.22%)
Mutual labels:  resnet, imagenet
Cifar Zoo
PyTorch implementation of CNNs for CIFAR benchmark
Stars: ✭ 584 (+363.49%)
Mutual labels:  resnet, densenet
Awesome Very Deep Learning
♾A curated list of papers and code about very deep neural networks
Stars: ✭ 435 (+245.24%)
Mutual labels:  resnet, densenet
Vgg16 Pytorch
VGG16 Net implementation from PyTorch Examples scripts for ImageNet dataset
Stars: ✭ 26 (-79.37%)
Mutual labels:  resnet, vgg
Pyramidnet
Torch implementation of the paper "Deep Pyramidal Residual Networks" (https://arxiv.org/abs/1610.02915).
Stars: ✭ 121 (-3.97%)
Mutual labels:  resnet, imagenet
Pretrained Models.pytorch
Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.
Stars: ✭ 8,318 (+6501.59%)
Mutual labels:  resnet, imagenet

ImageNet

This implements training of popular model architectures, such as AlexNet, SqueezeNet, ResNet, DenseNet and VGG on the ImageNet dataset(Now we supported alexnet, vgg, resnet, squeezenet, densenet).

Requirements

Training

To train a model, run main.py with the desired model architecture and the path to the ImageNet dataset:

python main.py [imagenet-folder with train and val folders] -a alexnet --lr 0.01

The default learning rate schedule starts at 0.01 and decays by a factor of 10 every 30 epochs.

Usage

usage: main.py [-h] [-a ARCH] [--epochs N] [--start-epoch N] [-b N] [--lr LR]
               [--momentum M] [--weight-decay W] [-j N] [-m] [-p]
               [--print-freq N] [--resume PATH] [-e]
               DIR

PyTorch ImageNet Training

positional arguments:
  DIR                   path to dataset

optional arguments:
  -h, --help            show this help message and exit
  -a ARCH, --arch ARCH  model architecture: alexnet | squeezenet1_0 |
                        squeezenet1_1 | densenet121 | densenet169 |
                        densenet201 | densenet201 | densenet161 | vgg11 |
                        vgg11_bn | vgg13 | vgg13_bn | vgg16 | vgg16_bn | vgg19
                        | vgg19_bn | resnet18 | resnet34 | resnet50 |
                        resnet101 | resnet152 (default: alexnet)
  --epochs N            numer of total epochs to run
  --start-epoch N       manual epoch number (useful to restarts)
  -b N, --batch-size N  mini-batch size (default: 256)
  --lr LR, --learning-rate LR
                        initial learning rate
  --momentum M          momentum
  --weight-decay W, --wd W
                        Weight decay (default: 1e-4)
  -j N, --workers N     number of data loading workers (default: 4)
  -m, --pin-memory      use pin memory
  -p, --pretrained      use pre-trained model
  --print-freq N, -f N  print frequency (default: 10)
  --resume PATH         path to latest checkpoitn, (default: None)
  -e, --evaluate        evaluate model on validation set


Result

The results of a single model on ILSVRC-2012 validation set.

Model [email protected] (val) [email protected] (val) Parameters ModelSize(MB)
AlexNet 56.522% 79.066% 244
SqueezeNet1_0 58.092% 80.420% 5
SqueezeNet1_1 58.178% 80.624% 5
DenseNet121 74.434% 91.972% 32
DenseNet169 75.600% 92.806% 57
DenseNet201 76.896% 93.370% 81
DenseNet161 77.138% 93.560% 116
Vgg11 69.020% 88.628% 532
Vgg13 69.928% 89.246% 532
Vgg16 71.592% 90.382% 554
Vgg19 72.376% 90.876% 574
Vgg11_bn 70.370% 89.810% 532
Vgg13_bn 71.586% 90.374% 532
Vgg16_bn 73.360% 91.516% 554
Vgg19_bn 74.218% 91.842% 574
ResNet18 69.758% 89.078% 47
ResNet34 73.314% 91.420% 87
ResNet50 76.130% 92.862% 103
ResNet101 77.374% 93.546% 179
ResNet152 78.312% 94.046% 242

Acknowledgement

PyTorch Examples

AlexNet

VGG

ResNet

SqueezeNet

DenseNet

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].