def generate_detections(
self, proposal_bboxes: Tensor, proposal_classes: Tensor,
proposal_transformers: Tensor, image_width: int,
image_height: int) -> Tuple[Tensor, Tensor, Tensor]:
proposal_transformers = proposal_transformers.view(
-1, self.num_classes, 4)
mean = self._transformer_normalize_mean.repeat(
1, self.num_classes, 1)
std = self._transformer_normalize_std.repeat(
1, self.num_classes, 1)
proposal_transformers = proposal_transformers * std - mean
proposal_bboxes = proposal_bboxes.view(-1, 1, 4).repeat(
1, self.num_classes, 1)
detection_bboxes = BBox.apply_transformer(
proposal_bboxes.view(-1, 4), proposal_transformers.view(-1, 4))
detection_bboxes = detection_bboxes.view(-1, self.num_classes, 4)
detection_bboxes[:, :,
[0, 2]] = detection_bboxes[:, :, [0, 2]].clamp(
min=0, max=image_width)
detection_bboxes[:, :,
[1, 3]] = detection_bboxes[:, :, [1, 3]].clamp(
min=0, max=image_height)
proposal_probs = F.softmax(proposal_classes, dim=1)
detection_bboxes = detection_bboxes.cpu()
proposal_probs = proposal_probs.cpu()
generated_bboxes = []
generated_classes = []
generated_probs = []
for c in range(1, self.num_classes):
detection_class_bboxes = detection_bboxes[:, c, :]
proposal_class_probs = proposal_probs[:, c]
_, sorted_indices = proposal_class_probs.sort(descending=True)
detection_class_bboxes = detection_class_bboxes[sorted_indices]
proposal_class_probs = proposal_class_probs[sorted_indices]
kept_indices = NMS.suppress(detection_class_bboxes.cuda(),
threshold=0.3)
detection_class_bboxes = detection_class_bboxes[kept_indices]
proposal_class_probs = proposal_class_probs[kept_indices]
generated_bboxes.append(detection_class_bboxes)
generated_classes.append(
torch.ones(len(kept_indices), dtype=torch.int) * c)
generated_probs.append(proposal_class_probs)
generated_bboxes = torch.cat(generated_bboxes, dim=0)
generated_classes = torch.cat(generated_classes, dim=0)
generated_probs = torch.cat(generated_probs, dim=0)
return generated_bboxes, generated_classes, generated_probs
def generate_proposals(self, anchor_bboxes: Tensor, objectnesses: Tensor, transformers: Tensor, image_width: int, image_height: int) -> Tensor:
proposal_score = objectnesses[:, 1]
_, sorted_indices = torch.sort(proposal_score, dim=0, descending=True)
sorted_transformers = transformers[sorted_indices]
sorted_anchor_bboxes = anchor_bboxes[sorted_indices]
proposal_bboxes = BBox.apply_transformer(sorted_anchor_bboxes, sorted_transformers.detach())
proposal_bboxes = BBox.clip(proposal_bboxes, 0, 0, image_width, image_height)
proposal_bboxes = proposal_bboxes[:self._pre_nms_top_n]
kept_indices = NMS.suppress(proposal_bboxes, threshold=0.7)
proposal_bboxes = proposal_bboxes[kept_indices]
proposal_bboxes = proposal_bboxes[:self._post_nms_top_n]
return proposal_bboxes
def forward(self, features: Tensor, image_width: int, image_height: int) -> Tuple[Tensor, Tensor, Tensor, Tensor]:
anchor_bboxes = RegionProposalNetwork._generate_anchors(image_width, image_height, num_x_anchors=features.shape[3], num_y_anchors=features.shape[2]).cuda()
features = self._features(features)
objectnesses = self._objectness(features)
transformers = self._transformer(features)
objectnesses = objectnesses.permute(0, 2, 3, 1).contiguous().view(-1, 2)
transformers = transformers.permute(0, 2, 3, 1).contiguous().view(-1, 4)
proposal_bboxes = RegionProposalNetwork._generate_proposals(anchor_bboxes, objectnesses, transformers, image_width, image_height)
proposal_bboxes = proposal_bboxes[:12000 if self.training else 6000]
keep_indices = NMS.suppress(proposal_bboxes, threshold=0.7)
proposal_bboxes = proposal_bboxes[keep_indices]
proposal_bboxes = proposal_bboxes[:2000 if self.training else 300]
return anchor_bboxes, objectnesses, transformers, proposal_bboxes
def _run_nms(self, bboxes):
start = time.time()
keep_indices = NMS.suppress(bboxes.contiguous(), threshold=0.7)
print('%s in %.3fs, %d -> %d' % (self.id(), time.time() - start, len(bboxes), len(keep_indices)))
return keep_indices