VGG

Very Deep Convolutional Networks for Large-Scale Image Recognition

摘要

In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

使用方式

Predict imageUse the modelTrain/Test Command

from mmpretrain import inference_model

predict = inference_model('vgg11_8xb32_in1k', 'demo/bird.JPEG')
print(predict['pred_class'])
print(predict['pred_score'])

Models and results

Image Classification on ImageNet-1k

模型	预训练	Params (M)	Flops (G)	Top-1 (%)	Top-5 (%)	配置文件	下载
vgg11_8xb32_in1k	从头训练	132.86	7.63	68.75	88.87	config	model | log
vgg13_8xb32_in1k	从头训练	133.05	11.34	70.02	89.46	config	model | log
vgg16_8xb32_in1k	从头训练	138.36	15.50	71.62	90.49	config	model | log
vgg19_8xb32_in1k	从头训练	143.67	19.67	72.41	90.80	config	model | log
vgg11bn_8xb32_in1k	从头训练	132.87	7.64	70.67	90.16	config	model | log
vgg13bn_8xb32_in1k	从头训练	133.05	11.36	72.12	90.66	config	model | log
vgg16bn_8xb32_in1k	从头训练	138.37	15.53	73.74	91.66	config	model | log
vgg19bn_8xb32_in1k	从头训练	143.68	19.70	74.68	92.27	config	model | log

引用

@article{simonyan2014very,
  title={Very deep convolutional networks for large-scale image recognition},
  author={Simonyan, Karen and Zisserman, Andrew},
  journal={arXiv preprint arXiv:1409.1556},
  year={2014}
}