mitmul / Chainer Cifar10
Various CNN models for CIFAR10 with Chainer
Stars: ✭ 134
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Chainer Cifar10
Imagenet
Pytorch Imagenet Models Example + Transfer Learning (and fine-tuning)
Stars: ✭ 134 (+0%)
Mutual labels: convolutional-neural-networks, resnet, densenet, vgg
Pytorch Image Classification
Tutorials on how to implement a few key architectures for image classification using PyTorch and TorchVision.
Stars: ✭ 272 (+102.99%)
Mutual labels: convolutional-neural-networks, resnet, vgg
Keras-CIFAR10
practice on CIFAR10 with Keras
Stars: ✭ 25 (-81.34%)
Mutual labels: vgg, resnet, cifar10
Cifar 10 Cnn
Play deep learning with CIFAR datasets
Stars: ✭ 756 (+464.18%)
Mutual labels: convolutional-neural-networks, densenet, cifar10
Deep Learning With Python
Deep learning codes and projects using Python
Stars: ✭ 195 (+45.52%)
Mutual labels: convolutional-neural-networks, neural-networks, resnet
Pytorch Classification
Classification with PyTorch.
Stars: ✭ 1,268 (+846.27%)
Mutual labels: resnet, densenet, cifar10
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 (+437.31%)
Mutual labels: resnet, densenet, vgg
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 (-45.52%)
Mutual labels: vgg, densenet, resnet
Tensornets
High level network definitions with pre-trained weights in TensorFlow
Stars: ✭ 982 (+632.84%)
Mutual labels: resnet, densenet, vgg
Hyperdensenet
This repository contains the code of HyperDenseNet, a hyper-densely connected CNN to segment medical images in multi-modal image scenarios.
Stars: ✭ 124 (-7.46%)
Mutual labels: convolutional-neural-networks, neural-networks, densenet
Imagenet
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)
Stars: ✭ 126 (-5.97%)
Mutual labels: resnet, densenet, vgg
Iresnet
Improved Residual Networks (https://arxiv.org/pdf/2004.04989.pdf)
Stars: ✭ 163 (+21.64%)
Mutual labels: convolutional-neural-networks, neural-networks, 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 (+134.33%)
Mutual labels: resnet, densenet, vgg
Classification models
Classification models trained on ImageNet. Keras.
Stars: ✭ 938 (+600%)
Mutual labels: resnet, densenet, vgg
Cyclegan Qp
Official PyTorch implementation of "Artist Style Transfer Via Quadratic Potential"
Stars: ✭ 59 (-55.97%)
Mutual labels: convolutional-neural-networks, neural-networks, resnet
Pytorch Speech Commands
Speech commands recognition with PyTorch
Stars: ✭ 128 (-4.48%)
Mutual labels: resnet, densenet, cifar10
Seranet
Super Resolution of picture images using deep learning
Stars: ✭ 79 (-41.04%)
Mutual labels: convolutional-neural-networks, chainer
Wav2letter
Speech Recognition model based off of FAIR research paper built using Pytorch.
Stars: ✭ 78 (-41.79%)
Mutual labels: convolutional-neural-networks, neural-networks
Bsconv
Reference implementation for Blueprint Separable Convolutions (CVPR 2020)
Stars: ✭ 84 (-37.31%)
Mutual labels: resnet, cifar10
Chainer Pspnet
PSPNet in Chainer
Stars: ✭ 76 (-43.28%)
Mutual labels: convolutional-neural-networks, chainer
Train various models on CIFAR10 with Chainer
Requirements
- Python 3.5.1+ (not tested with Python2)
- pip packages:
- chainer>=3.1.0
- chainercv>=0.8.0
- numpy>=1.10.1
- matplotlib>=2.0.0
- scikit-image>=0.13.1
- opencv-python>=3.3.0
- tabulate>=0.8.2
Quick Start
MPLBACKEND=Agg python train.py
With full arguments:
MPLBACKEND=Agg python train.py \
--model_file models/wide_resnet.py \
--model_name WideResNet \
--batchsize 128 \
--training_epoch 500 \
--initial_lr 0.05 \
--lr_decay_rate 0.5 \
--lr_decay_epoch 70 \
--weight_decay 0.0005 \
--random_angle 15.0 \
--pca_sigma 25.5 \
--expand_ratio 1.2 \
--crop_size 28 28 \
--seed 0 \
--gpus 0
About data augmentation
It performs various data augmentation using ChainerCV. Provided operations are:
- Random rotating (using OpenCV or scikit-image)
- Random lighting
- Random LR-flipping
- Random zomming (a.k.a. expansion)
- Random cropping
See the details at transform
function in train.py
.
Exprimental Results
model_name | val/main/accuracy | epoch | batchsize | crop_size | expand_ratio | pca_sigma | random_angle | weight_decay | initial_lr | lr_decay_rate | lr_decay_epoch |
---|---|---|---|---|---|---|---|---|---|---|---|
LeNet5 | 0.860166 | 500 | 128 | [28, 28] | 1.2 | 25.5 | 15 | 0.0005 | 0.01 | 0.5 | 50 |
NIN | 0.879351 | 500 | 128 | [28, 28] | 1.2 | 25.5 | 15 | 0.0005 | 0.01 | 0.5 | 100 |
VGG | 0.934237 | 500 | 128 | [28, 28] | 1.2 | 25.5 | 15 | 0.0005 | 0.05 | 0.5 | 50 |
ResNet50 | 0.950455 | 500 | 128 | [28, 28] | 1.2 | 25.5 | 15 | 0.0005 | 0.05 | 0.5 | 50 |
DenseNet | 0.944818 | 500 | 128 | [28, 28] | 1.2 | 25.5 | 15 | 0.0005 | 0.05 | 0.5 | 50 |
WideResNet | 0.962322 | 500 | 128 | [28, 28] | 1.2 | 25.5 | 15 | 0.0005 | 0.05 | 0.5 | 70 |
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].