Spaces:
Sleeping
Sleeping
File size: 7,410 Bytes
251e479 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 |
# Copyright (c) OpenMMLab. All rights reserved.
from torch import nn
from torch.autograd import Function
from torch.autograd.function import once_differentiable
from torch.nn.modules.utils import _pair
from ..utils import ext_loader
ext_module = ext_loader.load_ext(
'_ext', ['deform_roi_pool_forward', 'deform_roi_pool_backward'])
class DeformRoIPoolFunction(Function):
@staticmethod
def symbolic(g, input, rois, offset, output_size, spatial_scale,
sampling_ratio, gamma):
return g.op(
'mmcv::MMCVDeformRoIPool',
input,
rois,
offset,
pooled_height_i=output_size[0],
pooled_width_i=output_size[1],
spatial_scale_f=spatial_scale,
sampling_ratio_f=sampling_ratio,
gamma_f=gamma)
@staticmethod
def forward(ctx,
input,
rois,
offset,
output_size,
spatial_scale=1.0,
sampling_ratio=0,
gamma=0.1):
if offset is None:
offset = input.new_zeros(0)
ctx.output_size = _pair(output_size)
ctx.spatial_scale = float(spatial_scale)
ctx.sampling_ratio = int(sampling_ratio)
ctx.gamma = float(gamma)
assert rois.size(1) == 5, 'RoI must be (idx, x1, y1, x2, y2)!'
output_shape = (rois.size(0), input.size(1), ctx.output_size[0],
ctx.output_size[1])
output = input.new_zeros(output_shape)
ext_module.deform_roi_pool_forward(
input,
rois,
offset,
output,
pooled_height=ctx.output_size[0],
pooled_width=ctx.output_size[1],
spatial_scale=ctx.spatial_scale,
sampling_ratio=ctx.sampling_ratio,
gamma=ctx.gamma)
ctx.save_for_backward(input, rois, offset)
return output
@staticmethod
@once_differentiable
def backward(ctx, grad_output):
input, rois, offset = ctx.saved_tensors
grad_input = grad_output.new_zeros(input.shape)
grad_offset = grad_output.new_zeros(offset.shape)
ext_module.deform_roi_pool_backward(
grad_output,
input,
rois,
offset,
grad_input,
grad_offset,
pooled_height=ctx.output_size[0],
pooled_width=ctx.output_size[1],
spatial_scale=ctx.spatial_scale,
sampling_ratio=ctx.sampling_ratio,
gamma=ctx.gamma)
if grad_offset.numel() == 0:
grad_offset = None
return grad_input, None, grad_offset, None, None, None, None
deform_roi_pool = DeformRoIPoolFunction.apply
class DeformRoIPool(nn.Module):
def __init__(self,
output_size,
spatial_scale=1.0,
sampling_ratio=0,
gamma=0.1):
super(DeformRoIPool, self).__init__()
self.output_size = _pair(output_size)
self.spatial_scale = float(spatial_scale)
self.sampling_ratio = int(sampling_ratio)
self.gamma = float(gamma)
def forward(self, input, rois, offset=None):
return deform_roi_pool(input, rois, offset, self.output_size,
self.spatial_scale, self.sampling_ratio,
self.gamma)
class DeformRoIPoolPack(DeformRoIPool):
def __init__(self,
output_size,
output_channels,
deform_fc_channels=1024,
spatial_scale=1.0,
sampling_ratio=0,
gamma=0.1):
super(DeformRoIPoolPack, self).__init__(output_size, spatial_scale,
sampling_ratio, gamma)
self.output_channels = output_channels
self.deform_fc_channels = deform_fc_channels
self.offset_fc = nn.Sequential(
nn.Linear(
self.output_size[0] * self.output_size[1] *
self.output_channels, self.deform_fc_channels),
nn.ReLU(inplace=True),
nn.Linear(self.deform_fc_channels, self.deform_fc_channels),
nn.ReLU(inplace=True),
nn.Linear(self.deform_fc_channels,
self.output_size[0] * self.output_size[1] * 2))
self.offset_fc[-1].weight.data.zero_()
self.offset_fc[-1].bias.data.zero_()
def forward(self, input, rois):
assert input.size(1) == self.output_channels
x = deform_roi_pool(input, rois, None, self.output_size,
self.spatial_scale, self.sampling_ratio,
self.gamma)
rois_num = rois.size(0)
offset = self.offset_fc(x.view(rois_num, -1))
offset = offset.view(rois_num, 2, self.output_size[0],
self.output_size[1])
return deform_roi_pool(input, rois, offset, self.output_size,
self.spatial_scale, self.sampling_ratio,
self.gamma)
class ModulatedDeformRoIPoolPack(DeformRoIPool):
def __init__(self,
output_size,
output_channels,
deform_fc_channels=1024,
spatial_scale=1.0,
sampling_ratio=0,
gamma=0.1):
super(ModulatedDeformRoIPoolPack,
self).__init__(output_size, spatial_scale, sampling_ratio, gamma)
self.output_channels = output_channels
self.deform_fc_channels = deform_fc_channels
self.offset_fc = nn.Sequential(
nn.Linear(
self.output_size[0] * self.output_size[1] *
self.output_channels, self.deform_fc_channels),
nn.ReLU(inplace=True),
nn.Linear(self.deform_fc_channels, self.deform_fc_channels),
nn.ReLU(inplace=True),
nn.Linear(self.deform_fc_channels,
self.output_size[0] * self.output_size[1] * 2))
self.offset_fc[-1].weight.data.zero_()
self.offset_fc[-1].bias.data.zero_()
self.mask_fc = nn.Sequential(
nn.Linear(
self.output_size[0] * self.output_size[1] *
self.output_channels, self.deform_fc_channels),
nn.ReLU(inplace=True),
nn.Linear(self.deform_fc_channels,
self.output_size[0] * self.output_size[1] * 1),
nn.Sigmoid())
self.mask_fc[2].weight.data.zero_()
self.mask_fc[2].bias.data.zero_()
def forward(self, input, rois):
assert input.size(1) == self.output_channels
x = deform_roi_pool(input, rois, None, self.output_size,
self.spatial_scale, self.sampling_ratio,
self.gamma)
rois_num = rois.size(0)
offset = self.offset_fc(x.view(rois_num, -1))
offset = offset.view(rois_num, 2, self.output_size[0],
self.output_size[1])
mask = self.mask_fc(x.view(rois_num, -1))
mask = mask.view(rois_num, 1, self.output_size[0], self.output_size[1])
d = deform_roi_pool(input, rois, offset, self.output_size,
self.spatial_scale, self.sampling_ratio,
self.gamma)
return d * mask
|