def obj_feature_map(self, features, rois):
"""
Gets the ROI features
:param features: [batch_size, dim, IM_SIZE/4, IM_SIZE/4] (features at level p2)
:param rois: [num_rois, 5] array of [img_num, x0, y0, x1, y1].
:return: [num_rois, #dim] array
"""
feature_pool = RoIAlignFunction(self.pooling_size, self.pooling_size, spatial_scale=1 / 16)(
self.compress(features) if self.use_resnet else features, rois)
return self.roi_fmap(feature_pool.view(rois.size(0), -1))
def new_obj_feature_map(self, features, rois):
"""
Gets the ROI features
:param features: [batch_size, dim, IM_SIZE/4, IM_SIZE/4] (features at level p2)
:param rois: [num_rois, 5] array of [img_num, x0, y0, x1, y1].
:return: [num_rois, #dim] array
"""
feature_pool = RoIAlignFunction(self.pooling_size, self.pooling_size, spatial_scale=1 / 16)(
features, rois)
return self.new_roi_fmap_obj(feature_pool.view(rois.size(0), -1)) # vgg.classifier
def obj_feature_map(self, features, rois):
"""
Gets the ROI features
:param features: [batch_size, dim, IM_SIZE/4, IM_SIZE/4] (features at level p2)
:param rois: [num_rois, 5] array of [img_num, x0, y0, x1, y1].
:return: [num_rois, #dim] array
"""
if not self.use_resnet:
feature_pool = RoIAlignFunction(
self.pooling_size, self.pooling_size, spatial_scale=1 / 16)(
self.compress(features) if self.use_resnet else features,
rois)
return self.roi_fmap(feature_pool.view(rois.size(0), -1))
else:
# feature_pool: [batch, 1024, 8, 8]; x: [batch, 1024, 7, 7]; fc7: [2048, 4, 4] --> [2048]
feature_pool = RoIAlignFunction(self.pooling_size + 1,
self.pooling_size + 1,
spatial_scale=1 / 16)(features,
rois)
x = F.avg_pool2d(feature_pool, kernel_size=2, stride=1)
fc7 = self.features.layer4(x)
fc7 = fc7.mean(3).mean(2)
return fc7
def obj_feature_map(self, features, rois):
feature_pool = RoIAlignFunction(self.pooling_size,
self.pooling_size,
spatial_scale=1 / 16)(features, rois)
return self.roi_fmap_obj(feature_pool.view(rois.size(0), -1))
