From: Deep convolutional neural networks for mammography: advances, challenges and applications
 | AlexNet [16] | ZF-Net [77] | GoogLeNet [78] | VGG-Net [79] | ResNet [80] |
---|---|---|---|---|---|
Year | 2012 | 2013 | 2014 | 2014 | 2015 |
Image Resolution | 227 ×227 | 227 ×227 | 224 ×224 | 224 ×224 | 2244 ×224 |
Number of layers | 8 | 8 | 22 | 19 | 152 |
Number of Conv-Pool layers | 5 | 5 | 21 | 16 | 151 |
Number of FC layers | 3 | 3 | 1 | 3 | 1 |
Full connected layer size | 4096,4096,1000 | 4096,4096,1000 | 1000 | 4096,4096,1000 | 1000 |
Filter Sizes | 3, 5, 11 | 3, 5, 11 | 1,3,5,7 | 3 | 1,3,7 |
Number of Filters | 96 - 384 | 96 - 384 | 64 - 384 | 64 - 512 | 64 - 2048 |
Strides | 1, 4 | 1, 4 | 1, 2 | 1 | 1, 2 |
Data Augmentation | + | + | + | + | + |
Dropout | + | + | + | + | + |
Batch Normalization | - | - | - | - | + |
Number of GPU | 2 GTX | 1 GTX | A few high-end | 4 Nvidia | Â |
580 GPUs | 580 GPUs | GPUs | Titan Black GPUs | Titan Black GPUs | 8 GPUs |
Training Time | 5:6 days | 12 days | 1 week | 2:3 weeks | 2:3 weeks |
Top-5 error | 16.40% | 11.2% | 6.70% | 7.30% | 3.57% |