(2014)
|Network|Models Evaluated|Crops Evaluated|Top-1 Error|Top-5 Error|
|---|---|---|---|---|
|
VGGNet \[18]|2|\-|23.7%|6.8%|
|GoogLeNet \[20]|7|144|\-|6.67%|
|PReLU \[6]|\-|\-|\-|4.94%|
|BN-Inception
AlexNet | 2012 | Deeper | 84.70% | 62M | 1.5B | | VGGNet | 2014 | Fixed-size kernels | 92.30% | 138M | 19.6B |
< 0 码力 |
58 页 |
23.92 MB
| 2 年前 3
number of parameters and increased complexity. In Computer Vision, several model architectures such as VGGNet, Inception, ResNet etc. (refer to Figure 1-2). have successively beat previous records at the annual
0 码力 |
21 页 |
3.17 MB
| 2 年前 3
深度学习与PyTorch入门实战 - 41. 经典卷积网络0 码力 | 13 页 | 1.20 MB | 2 年前3