Benchmark and model zoo¶
常规设置¶
所有的模型我们都是在
CUB_200_2011_train
上进行训练并且在CUB_200_2011_test
上进行测试的为了与其他代码库进行公平的比较,我们将GPU内存报告为所有8个GPU的’ torch.cuda.max_memory_allocate() ‘的最大值。注意,这个值通常小于’ nvidia-smi ‘显示的值。
所有的预训练的backbone都是来自于PyTorch model zoo。
Backbone 模型¶
下面列出了FGVCLib中常用的骨干模型的详细表:
model | source | link | description |
---|---|---|---|
ResNet18 | TorchVision | torchvision's ResNet-18 | From torchvision's ResNet-18. |
ResNet34 | TorchVision | torchvision's ResNet-34 | From torchvision's ResNet-34. |
ResNet50 | TorchVision | torchvision's ResNet-50 | From torchvision's ResNet-50. |
ResNet101 | TorchVision | torchvision's ResNet-101 | From torchvision's ResNet-101. |
ResNet152 | TorchVision | torchvision's ResNet-152 | From torchvision's ResNet-152. |
Vgg11 | TorchVision | torchvision's Vgg-11 | From torchvision's Vgg-11. |
Vgg13 | TorchVision | torchvision's Vgg-13 | From torchvision's Vgg-13. |
Vgg16 | TorchVision | torchvision's Vgg-16 | From torchvision's Vgg-16. |
Vgg19 | TorchVision | torchvision's Vgg-19 | From torchvision's Vgg-19. |