5. 模型分为Large和Small,在ImageNet 分类任务中和V2相比,Large正确率上升了 3.2%,计算
延时还降低了 20%。
MobileNetV3代码实现(pytorch):
https://wanghao.blog.csdn.net/article/details/121607296
数据增强Cutout和Mixup
为了提高成绩我在代码中加入Cutout和Mixup这两种增强方式。实现这两种增强需要安装
torchtoolbox。安装命令:
Cutout实现,在transforms中。
Mixup实现,在train方法中。需要导入包:from torchtoolbox.tools import mixup_data,
mixup_criterion
项目结构
from torchtoolbox.transform import Cutout
# 数据预处理
transform = transforms.Compose([
transforms.Resize((224, 224)),
Cutout(),
transforms.ToTensor(),
transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])
])
for batch_idx, (data, target) in enumerate(train_loader):
data, target = data.to(device, non_blocking=True), target.to(device,
non_blocking=True)
data, labels_a, labels_b, lam = mixup_data(data, target, alpha)
optimizer.zero_grad()
output = model(data)
loss = mixup_criterion(criterion, output, labels_a, labels_b, lam)
loss.backward()
optimizer.step()
print_loss = loss.data.item()
MobileNetV3_demo
├─data
│ ├─test
│ └─train
│ ├─Black-grass
│ ├─Charlock
│ ├─Cleavers
│ ├─Common Chickweed
│ ├─Common wheat
│ ├─Fat Hen
- 1
- 2
- 3
- 4
- 5
- 6
前往页