coco_eval.py

# Copyright (c) 2021-2022, NVIDIA CORPORATION. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#           http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

import numpy as np
import torch
import torch._six

import pycocotools.mask as mask_util


class CocoEvaluator(object):
    def prepare(self, predictions, iou_type):
        if iou_type == "bbox":
            return self.prepare_for_coco_detection(predictions)
        elif iou_type == "segm":
            return self.prepare_for_coco_segmentation(predictions)
        elif iou_type == "keypoints":
            return self.prepare_for_coco_keypoint(predictions)
        else:
            raise ValueError("Unknown iou type {}".format(iou_type))

    def prepare_for_coco_detection(self, predictions):
        coco_results = []
        for original_id, prediction in predictions.items():
            if len(prediction) == 0:
                continue

            boxes = prediction["boxes"]
            boxes = convert_to_xywh(boxes).tolist()
            scores = prediction["scores"].tolist()
            labels = prediction["labels"].tolist()

            coco_results.extend(
                [
                    {
                        "image_id": original_id,
                        "category_id": label,
                        "bbox": bbox,
                        "score": score,
                    }
                    for (bbox, label, score) in zip(boxes, labels, scores)
                ]
            )
        return coco_results

    def prepare_for_coco_segmentation(self, predictions):
        coco_results = []
        for original_id, prediction in predictions.items():
            if len(prediction) == 0:
                continue

            scores = prediction["scores"]
            labels = prediction["labels"]
            masks = prediction["masks"]
            masks = masks > 0.5
            scores = prediction["scores"].tolist()
            labels = prediction["labels"].tolist()

            rles = [
                mask_util.encode(np.array(mask[0, :, :, np.newaxis], dtype=np.uint8, order="F"))[0]
                for mask in masks
            ]
            for rle in rles:
                rle["counts"] = rle["counts"].decode("utf-8")

            coco_results.extend(
                [
                    {
                        "image_id": original_id,
                        "category_id": labels[k],
                        "segmentation": rle,
                        "score": scores[k],
                    }
                    for k, rle in enumerate(rles)
                ]
            )
        return coco_results

    def prepare_for_coco_keypoint(self, predictions):
        coco_results = []
        for original_id, prediction in predictions.items():
            if len(prediction) == 0:
                continue

            boxes = prediction["boxes"]
            boxes = convert_to_xywh(boxes).tolist()
            scores = prediction["scores"].tolist()
            labels = prediction["labels"].tolist()
            keypoints = prediction["keypoints"]
            keypoints = keypoints.flatten(start_dim=1).tolist()

            coco_results.extend(
                [
                    {
                        "image_id": original_id,
                        "category_id": labels[k],
                        'keypoints': keypoint,
                        "score": scores[k],
                    }
                    for k, keypoint in enumerate(keypoints)
                ]
            )
        return coco_results


def convert_to_xywh(boxes):
    xmin, ymin, xmax, ymax = boxes.unbind(1)
    return torch.stack((xmin, ymin, xmax - xmin, ymax - ymin), dim=1)