zz198808 / cifar-10-cnn

Using cifar-10 datasets to learn deep learning.

Convolutional Neural Networks (CNN) for CIFAR-10 Dataset

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

I just use Keras and Tensorflow to implementate all of these CNN models.
(maybe pytorch version if I have time)

Requirements

• Python (3.5.2)
• Keras (2.0.8)
• tensorflow-gpu (1.3.0)

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
• SENet
  • Squeeze-and-Excitation Networks

Documents & tutorials

There are also some documents and tutorials in doc & issues/3.
See that if you need.

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	39M	4 hours	93.53
Residual-Network110	-	meanstd	GTX980TI	1.7M	8 h 58 min	94.10
Wide-resnet 16x8	-	meanstd	GTX1060	11.3M	11 h 32 min	95.14
DenseNet-100x12	-	meanstd	GTX980TI	0.85M	30 h 40 min	95.15
ResNeXt-4x64d	-	meanstd	GTX1080TI	20M	22 h 50 min	95.51
SENet(ResNeXt-4x64d)	-	meanstd	GTX1080	20M	-	-

Now, I fixed some bugs and used 1080TI to retrain all of the following models.

In particular：
Change the batch size according to your GPU's memory.
Modify the learning rate schedule may imporve the results of accuracy!

network	GPU	params	batch size	epoch	training time	accuracy(%)
Lecun-Network	GTX1080TI	62k	128	200	30 min	76.25
Network-in-Network	GTX1080TI	0.97M	128	200	1 h 40 min	91.63
Vgg19-Network	GTX1080TI	39M	128	200	1 h 53 min	93.53
Residual-Network20	GTX1080TI	0.27M	128	200	47 min	92.16
Residual-Network32	GTX1080TI	0.47M	128	200	1 h 13 min	92.86
Residual-Network110	GTX1080TI	1.7M	128	200	4 h 30 min	94.44
Wide-resnet 16x8	GTX1080TI	11.3M	128	200	5 h 1 min	95.13
DenseNet-100x12	GTX1080TI	0.85M	64	250	17 h 20 min	94.91
DenseNet-100x24	GTX1080TI	3.3M	64	250	22 h 27 min	95.30
DenseNet-160x24	1080 x 2	7.5M	64	250	50 h 20 min	95.90
ResNeXt-4x64d	GTX1080TI	20M	120	250	21 h 3 min	95.19
SENet(ResNeXt-4x64d)	GTX1080TI	20M	120	250	21 h 57 min	95.60

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

Please feel free to contact me if you have any questions!