/DPNs

Dual Path Networks

Primary LanguagePython

Dual Path Networks

This repository contains the code and trained models of:

Yunpeng Chen, Jianan Li, Huaxin Xiao, Xiaojie Jin, Shuicheng Yan, Jiashi Feng. "Dual Path Networks" (NIPS17).

example

  • DPNs helped us won the 1st place in Object Localization Task in ILSVRC 2017, with all competition tasks within Top 3. (Team: NUS-Qihoo_DPNs)

Implementation

DPNs are implemented by MXNet @92053bd.

Augmentation

Method Settings
Random Mirror True
Random Crop 8% - 100%
Aspect Ratio 3/4 - 4/3
Random HSL [20,40,50]

Note: We did not use PCA Lighting and any other advanced augmentation methods. Input images are resized by bicubic interpolation.

Normalization

The augmented input images are substrated by mean RGB = [ 124, 117, 104 ], and then multiplied by 0.0167.

Mean-Max Pooling

Here, we introduce a new testing technique by using Mean-Max Pooling which can further improve the performance of a well trained CNN in the testing phase without the need of any training/fine-tuining process. This testing technique is designed for the case when the testing images is larger than training crops. The idea is to first convert a trained CNN model into a convolutional network and then insert the following Mean-Max Pooling layer (a.k.a. Max-Avg Pooling), i.e. 0.5 * (global average pooling + global max pooling), just before the final softmax layer.

Based on our observations, Mean-Max Pooling consistently boost the testing accuracy. We adopted this testing strategy in both LSVRC16 and LSVRC17.

Results

ImageNet-1k

Single Model, Single Crop Validation Error:

   
Model Size GFLOPs 224x224 320x320 320x320
( with mean-max pooling )
Top 1 Top 5 Top 1 Top 5 Top 1 Top 5
DPN-68 49 MB 2.5 23.57 6.93 22.15 5.90 21.51 5.52
DPN-92 145 MB 6.5 20.73 5.37 19.34 4.66 19.04 4.53
DPN-98 236 MB 11.720.15 5.15 18.94 4.44 18.72 4.40
DPN-131 304 MB 16.0 19.93 5.12 18.62 4.23 18.55 4.16

ImageNet-1k (Pretrained on ImageNet-5k)

Single Model, Single Crop Validation Error:

Model Size GFLOPs 224x224 320x320 320x320
( with mean-max pooling )
Top 1 Top 5 Top 1 Top 5 Top 1 Top 5
DPN-68 49 MB 2.5 22.45 6.09 20.92 5.26 20.62 5.07
DPN-92 145 MB 6.5 19.98 5.06 19.00 4.37 18.79 4.19
DPN-107 333 MB 18.3 19.75 4.94 18.34 4.19 18.15 4.03

Note: DPN-107 is not well trained.

ImageNet-5k

Single Model, Single Crop Validation Accuracy:

Model Size GFLOPs 224x224 320x320 320x320
( with mean-max pooling )
Top 1 Top 5 Top 1 Top 5 Top 1 Top 5
DPN-68 61 MB 2.5 61.27 85.46 61.54 85.99 62.35 86.20
DPN-92 184 MB 6.5 67.31 89.49 66.84 89.38 67.42 89.76

Note: The higher model complexity comes from the final classifier. Models trained on ImageNet-5k learn much richer feature representation than models trained on ImageNet-1k.

Efficiency (Training)

The training speed is tested based on MXNet @92053bd.

Multiple Nodes (Without specific code optimization):

Model CUDA
/cuDNN
#Node GPU Card
(per node)
Batch Size
(per GPU)
kvstore GPU Mem
(per GPU)
Training Speed*
(per node)
DPN-68 8.0 / 5.1 10 4 x K80 (Tesla) 64 dist_sync 9337 MiB 284 img/sec
DPN-92 8.0 / 5.1 10 4 x K80 (Tesla) 32 dist_sync 8017 MiB 133 img/sec
DPN-98 8.0 / 5.1 10 4 x K80 (Tesla) 32 dist_sync 11128 MiB 85 img/sec
DPN-131 8.0 / 5.1 10 4 x K80 (Tesla) 24 dist_sync 11448 MiB 60 img/sec
DPN-107 8.0 / 5.1 10 4 x K80 (Tesla) 24 dist_sync 12086 MiB 55 img/sec

*This is the actual training speed, which includes data augmentation, forward, backward, parameter update, network communication, etc. MXNet is awesome, we observed a linear speedup as has been shown in link

Trained Models

Model Size Dataset MXNet Model
DPN-68 49 MB ImageNet-1k GoogleDrive
DPN-68* 49 MB ImageNet-1k GoogleDrive
DPN-68 61 MB ImageNet-5k GoogleDrive
DPN-92 145 MB ImageNet-1k GoogleDrive
DPN-92 138 MB Places365-Standard GoogleDrive
DPN-92* 145 MB ImageNet-1k GoogleDrive
DPN-92 184 MB ImageNet-5k GoogleDrive
DPN-98 236 MB ImageNet-1k GoogleDrive
DPN-131 304 MB ImageNet-1k GoogleDrive
DPN-107* 333 MB ImageNet-1k GoogleDrive

*Pretrained on ImageNet-5k and then fine-tuned on ImageNet-1k.

Third-party Implementations

Other Resources

ImageNet-1k Trainig/Validation List:

ImageNet-1k category name mapping table:

ImageNet-5k Raw Images:

  • The ImageNet-5k is a subset of ImageNet10K provided by this paper.
  • Please download the ImageNet10K and then extract the ImageNet-5k by the list below.

ImageNet-5k Trainig/Validation List:

  • It contains about 5k leaf categories from ImageNet10K. There is no category overlapping between our provided ImageNet-5k and the official ImageNet-1k.
  • Download link: [GoogleDrive: https://goo.gl/kNZC4j]
  • Download link: GoogleDrive
  • Mapping Table: GoogleDrive

Places365-Standard Validation List & Matlab code for 10 crops testing:

Citation

If you use DPN in your research, please cite the paper:

@article{Chen2017,
  title={Dual Path Networks},
  author={Yunpeng Chen, Jianan Li, Huaxin Xiao, Xiaojie Jin, Shuicheng Yan, Jiashi Feng},
  journal={arXiv preprint arXiv:1707.01629},
  year={2017}
}