Skip to content

developer0hye/PyTorch-Darknet53

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

46 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Darknet53

This is implementation of Darknet53 network discussed in [1] used for feature extractor of YOLOv3.

This new network is more efficient than ResNet-101 or ResNet-152.

Here are some ImageNet results:

  • Framework: Darknet [2]
  • GPU: Titan X
  • Input Shape(CWH): 3 x 256 x 256

darknet_table

Darknet-53 is better than ResNet-101 and 1.5× faster.

Darknet-53 has similar performance to ResNet-152 and is 2× faster [1] .

But when I trained and tested this model with 224x224 input image, I could not get the good results like the above table.

I got 75.xx% accracy on Imagenet validation dataset.

Pretrained model_weight_download

Network Structure

webp net-resizeimage

Training

python train.py --data [imagenet-folder with train and val folders] --gpu 0 -b 64

Benchmark

  • Framework: PyTorch
  • GPU: GTX 1080 Ti 11GB
  • CPU: i7 6550 3.4 GHZ
  • RAM: 16 GB
  • Batch Size: 1
  • Input Shape(CWH): 3 x 224 x 224

On GPU

resnet101 : 0.034906 sec
resnet152 : 0.055852 sec
densenet121 : 0.041888 sec
darknet53 : 0.017952 sec

On CPU

resnet101 : 0.675194 sec
resnet152 : 0.949459 sec
densenet121 : 0.649266 sec
darknet53 : 0.405916 sec

Reference

[1] YOLOv3: An Incremental Improvement

[2] darknet framework

[3] ImageNet training in PyTorch

Releases

No releases published

Packages

No packages published

Languages