cifar-10-cnn

This repository is about some CNN Architecture's implementations for cifar10.

I just use Keras and Tensorflow to implementate all of these CNN models.

Requirements

• Python (3.5.2)
• Keras (2.0.6)
• tensorflow-gpu (1.2.1)

Architectures and papers

• The first CNN model: LeNet
  • LeNet-5 - Yann LeCun
• Network in Network
  • Network In Network
• Vgg19 Network
  • Very Deep Convolutional Networks for Large-Scale Image Recognition
• Residual Network
  • Deep Residual Learning for Image Recognition
  • Identity Mappings in Deep Residual Networks
• Wide Residual Network
  • Wide Residual Networks
• ResNeXt
  • Aggregated Residual Transformations for Deep Neural Networks
• DenseNet
  • Densely Connected Convolutional Networks

Accuracy of all my implementations

network	dropout	preprocess	GPU	params	training time	accuracy(%)
Lecun-Network	-	meanstd	GTX980TI	62k	30 min	76.27
Network-in-Network	0.5	meanstd	GTX1060	0.96M	1 h 30 min	91.25
Network-in-Network_bn	0.5	meanstd	GTX980TI	0.97M	2 h 20 min	91.75
Vgg19-Network	0.5	meanstd	GTX980TI	45M	4 hours	93.53
Residual-Network50	-	meanstd	GTX980TI	1.7M	8 h 58 min	94.10
Wide-resnet 16x8	-	meanstd	GTX1060	11.3M	11 h 32 min	95.14
ResNeXt-4x64d	-	meanstd	GTX1080TI	20M	22 h 50 min	95.51
DenseNet-100x12	-	meanstd	GTX980TI	0.85M	30 h 40 min	95.15

About ResNeXt & DenseNet

Because I don't have enough machines to train the larger networks.
So I only trained the smallest network described in the paper.
You can see the results in liuzhuang13/DenseNet and prlz77/ResNeXt.pytorch