Spaces:
No application file
No application file
| # Copyright (c) Facebook, Inc. and its affiliates. | |
| import torch | |
| from torch.nn import functional as F | |
| from detectron2.layers import paste_masks_in_image | |
| from detectron2.structures import Instances | |
| from detectron2.utils.memory import retry_if_cuda_oom | |
| # perhaps should rename to "resize_instance" | |
| def detector_postprocess( | |
| results: Instances, output_height: int, output_width: int, mask_threshold: float = 0.5 | |
| ): | |
| """ | |
| Resize the output instances. | |
| The input images are often resized when entering an object detector. | |
| As a result, we often need the outputs of the detector in a different | |
| resolution from its inputs. | |
| This function will resize the raw outputs of an R-CNN detector | |
| to produce outputs according to the desired output resolution. | |
| Args: | |
| results (Instances): the raw outputs from the detector. | |
| `results.image_size` contains the input image resolution the detector sees. | |
| This object might be modified in-place. | |
| output_height, output_width: the desired output resolution. | |
| Returns: | |
| Instances: the resized output from the model, based on the output resolution | |
| """ | |
| # Change to 'if is_tracing' after PT1.7 | |
| if isinstance(output_height, torch.Tensor): | |
| # Converts integer tensors to float temporaries to ensure true | |
| # division is performed when computing scale_x and scale_y. | |
| output_width_tmp = output_width.float() | |
| output_height_tmp = output_height.float() | |
| new_size = torch.stack([output_height, output_width]) | |
| else: | |
| new_size = (output_height, output_width) | |
| output_width_tmp = output_width | |
| output_height_tmp = output_height | |
| scale_x, scale_y = ( | |
| output_width_tmp / results.image_size[1], | |
| output_height_tmp / results.image_size[0], | |
| ) | |
| results = Instances(new_size, **results.get_fields()) | |
| if results.has("pred_boxes"): | |
| output_boxes = results.pred_boxes | |
| elif results.has("proposal_boxes"): | |
| output_boxes = results.proposal_boxes | |
| else: | |
| output_boxes = None | |
| assert output_boxes is not None, "Predictions must contain boxes!" | |
| output_boxes.scale(scale_x, scale_y) | |
| output_boxes.clip(results.image_size) | |
| results = results[output_boxes.nonempty()] | |
| if results.has("pred_masks"): | |
| results.pred_masks = retry_if_cuda_oom(paste_masks_in_image)( | |
| results.pred_masks[:, 0, :, :], # N, 1, M, M | |
| results.pred_boxes, | |
| results.image_size, | |
| threshold=mask_threshold, | |
| ) | |
| if results.has("pred_keypoints"): | |
| results.pred_keypoints[:, :, 0] *= scale_x | |
| results.pred_keypoints[:, :, 1] *= scale_y | |
| return results | |
| def sem_seg_postprocess(result, img_size, output_height, output_width): | |
| """ | |
| Return semantic segmentation predictions in the original resolution. | |
| The input images are often resized when entering semantic segmentor. Moreover, in same | |
| cases, they also padded inside segmentor to be divisible by maximum network stride. | |
| As a result, we often need the predictions of the segmentor in a different | |
| resolution from its inputs. | |
| Args: | |
| result (Tensor): semantic segmentation prediction logits. A tensor of shape (C, H, W), | |
| where C is the number of classes, and H, W are the height and width of the prediction. | |
| img_size (tuple): image size that segmentor is taking as input. | |
| output_height, output_width: the desired output resolution. | |
| Returns: | |
| semantic segmentation prediction (Tensor): A tensor of the shape | |
| (C, output_height, output_width) that contains per-pixel soft predictions. | |
| """ | |
| result = result[:, : img_size[0], : img_size[1]].expand(1, -1, -1, -1) | |
| result = F.interpolate( | |
| result, size=(output_height, output_width), mode="bilinear", align_corners=False | |
| )[0] | |
| return result | |