hsintao/dpns

Dual Path Networks

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).

• 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	11.7	20.15	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

• Caffe Implementation with trained models by soeaver
• Chainer Implementation by oyam
• Keras Implementation by titu1994
• MXNet Implementation by miraclewkf
• PyTorch Implementation by oyam
• PyTorch Implementation with trained models by rwightman

Other Resources

ImageNet-1k Trainig/Validation List:

• Download link: GoogleDrive

ImageNet-1k category name mapping table:

• Download link: GoogleDrive

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

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

• Download link: GoogleDrive

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}
}