跟李沐学AI—pytorch版本锚框代码解析
网上大佬的解释 https://fkjkkll.github.io/2021/11/23/%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8BSSD/?highlight=%E9%94%9A%E6%A1%86
w = torch.cat((size_tensor * torch.sqrt(ratio_tensor[0]),sizes[0] * torch.sqrt(ratio_tensor[1:])))\* in_height / in_widthh = torch.cat((size_tensor / torch.sqrt(ratio_tensor[0]),sizes[0] / torch.sqrt(ratio_tensor[1:])))
