network.py 文件源码

def _crop_pool_layer(self, bottom, rois, max_pool=True):
    # implement it using stn
    # box to affine
    # input (x1,y1,x2,y2)
    """
    [  x2-x1             x1 + x2 - W + 1  ]
    [  -----      0      ---------------  ]
    [  W - 1                  W - 1       ]
    [                                     ]
    [           y2-y1    y1 + y2 - H + 1  ]
    [    0      -----    ---------------  ]
    [           H - 1         H - 1      ]
    """
    rois = rois.detach()

    x1 = rois[:, 1::4] / 16.0
    y1 = rois[:, 2::4] / 16.0
    x2 = rois[:, 3::4] / 16.0
    y2 = rois[:, 4::4] / 16.0

    height = bottom.size(2)
    width = bottom.size(3)

    # affine theta
    theta = Variable(rois.data.new(rois.size(0), 2, 3).zero_())
    theta[:, 0, 0] = (x2 - x1) / (width - 1)
    theta[:, 0 ,2] = (x1 + x2 - width + 1) / (width - 1)
    theta[:, 1, 1] = (y2 - y1) / (height - 1)
    theta[:, 1, 2] = (y1 + y2 - height + 1) / (height - 1)

    if max_pool:
      pre_pool_size = cfg.POOLING_SIZE * 2
      grid = F.affine_grid(theta, torch.Size((rois.size(0), 1, pre_pool_size, pre_pool_size)))
      crops = F.grid_sample(bottom.expand(rois.size(0), bottom.size(1), bottom.size(2), bottom.size(3)), grid)
      crops = F.max_pool2d(crops, 2, 2)
    else:
      grid = F.affine_grid(theta, torch.Size((rois.size(0), 1, cfg.POOLING_SIZE, cfg.POOLING_SIZE)))
      crops = F.grid_sample(bottom.expand(rois.size(0), bottom.size(1), bottom.size(2), bottom.size(3)), grid)

    return crops