zfbox/model/base_model/ascnedcl/det_utils.py

"""
Copyright 2022 Huawei Technologies Co., Ltd

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 time

import cv2
import numpy as np
import torch
import torchvision


def letterbox(img, new_shape=(640, 640), color=(114, 114, 114), auto=False, scaleFill=False, scaleup=True):
    # Resize image to a 32-pixel-multiple rectangle https://github.com/ultralytics/yolov3/issues/232
    shape = img.shape[:2]  # current shape [height, width]
    if isinstance(new_shape, int):
        new_shape = (new_shape, new_shape)

    # Scale ratio (new / old)
    r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
    if not scaleup:  # only scale down, do not scale up (for better test mAP)
        r = min(r, 1.0)

    # Compute padding
    ratio = r, r  # width, height ratios
    new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
    dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1]  # wh padding
    if auto:  # minimum rectangle
        dw, dh = np.mod(dw, 64), np.mod(dh, 64)  # wh padding
    elif scaleFill:  # stretch
        dw, dh = 0.0, 0.0
        new_unpad = (new_shape[1], new_shape[0])
        ratio = new_shape[1] / shape[1], new_shape[0] / shape[0]  # width, height ratios

    dw /= 2  # divide padding into 2 sides
    dh /= 2

    if shape[::-1] != new_unpad:  # resize
        img = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR)
    top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
    left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
    img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color)  # add border
    return img, ratio, (dw, dh)



def non_max_suppression(
        prediction,
        conf_thres=0.25,
        iou_thres=0.45,
        classes=None,
        agnostic=False,
        multi_label=False,
        labels=(),
        max_det=100,    #每张图片最低暴力的检测框数量，原本是300，
        nm=0,  # number of masks
):
    """Non-Maximum Suppression (NMS) on inference results to reject overlapping detections

    Returns:
         list of detections, on (n,6) tensor per image [xyxy, conf, cls]
    """
    #判断并获取预测结果：如果 prediction 是列表或元组，选择其中的第一个元素作为模型预测输出
    if isinstance(prediction, (list, tuple)):  # YOLOv5 model in validation model, output = (inference_out, loss_out)
        prediction = prediction[0]  # select only inference output
    #设备检测：检测当前运行设备是否为 Apple MPS，如果是则将预测结果转换为 CPU 进行处理，因为 MPS 尚不完全支持 NMS。
    device = prediction.device
    # mps = 'mps' in device.type  # Apple MPS
    # if mps:  # MPS not fully supported yet, convert tensors to CPU before NMS
    #     prediction = prediction.cpu()

    #获取批量大小和类数量：bs 表示批量大小，nc 表示类的数量，xc 表示通过置信度阈值的候选框。
    bs = prediction.shape[0]  # batch size
    nc = prediction.shape[2] - nm - 5  # number of classes
    xc = prediction[..., 4] > conf_thres  # candidates

    # Checks 参数检查：确保 conf_thres 和 iou_thres 在有效范围内。
    assert 0 <= conf_thres <= 1, f'Invalid Confidence threshold {conf_thres}, valid values are between 0.0 and 1.0'
    assert 0 <= iou_thres <= 1, f'Invalid IoU {iou_thres}, valid values are between 0.0 and 1.0'

    # Settings
    # min_wh = 2  # (pixels) minimum box width and height
    max_wh = 7680  # (pixels) maximum box width and height
    max_nms = 30000  # maximum number of boxes into torchvision.ops.nms()
    time_limit = 0.5 + 0.05 * bs  # seconds to quit after
    multi_label &= nc > 1  # multiple labels per box (adds 0.5ms/img)   如果 nc > 1，则允许每个框有多个标签

    #初始化：记录当前时间用于后续的时间限制，mi 表示掩码索引的起始位置，
    t = time.time()
    mi = 5 + nc  # mask start index
    # output 初始化为一个批次大小的空列表，每个元素是形状为 (0, 6 + nm) 的零张量。
    output = [torch.zeros((0, 6 + nm), device=device)] * bs

    #逐图像处理：遍历批量中的每一张图像，只保留通过置信度筛选的框
    for xi, x in enumerate(prediction):  # image index, image inference
        # Apply constraints
        # x[((x[..., 2:4] < min_wh) | (x[..., 2:4] > max_wh)).any(1), 4] = 0  # width-height
        x = x[xc[xi]]  # confidence

        # Cat apriori labels if autolabelling 自动标签：如果存在标签，按照标签信息构建一个新的检测框，并将其与原有的检测框拼接
        if labels and len(labels[xi]):
            lb = labels[xi]
            v = torch.zeros((len(lb), nc + nm + 5), device=x.device)
            v[:, :4] = lb[:, 1:5]  # box
            v[:, 4] = 1.0  # conf
            v[range(len(lb)), lb[:, 0].long() + 5] = 1.0  # cls
            x = torch.cat((x, v), 0)
            del v

        # If none remain process next image 空检测处理：如果没有剩余检测框，则跳过该图像
        if not x.shape[0]:
            continue

        # Compute conf  置信度计算：更新置信度，x[:, 5:] 乘以 x[:, 4:5]，即置信度等于目标置信度乘以类别置信度
        x[:, 5:] *= x[:, 4:5]  # conf = obj_conf * cls_conf

        # Box/Mask 转换框坐标：将框坐标从中心点格式转换为左上角和右下角格式，并获取掩码信息（如果存在）。
        box = xywh2xyxy(x[:, :4])  # center_x, center_y, width, height) to (x1, y1, x2, y2)
        mask = x[:, mi:]  # zero columns if no masks

        # Detections matrix nx6 (xyxy, conf, cls)
        if multi_label: #如果允许多标签，选择所有符合阈值的类标签。
            i, j = (x[:, 5:mi] > conf_thres).nonzero(as_tuple=False).T
            x = torch.cat((box[i], x[i, 5 + j, None], j[:, None].float(), mask[i]), 1)
        else:  # best class only 只选择置信度最高的标签。
            conf, j = x[:, 5:mi].max(1, keepdim=True)
            x = torch.cat((box, conf, j.float(), mask), 1)[conf.view(-1) > conf_thres]

        # Filter by class 按类过滤：如果指定了 classes，则只保留属于这些类的检测框
        if classes is not None:
            x = x[(x[:, 5:6] == torch.tensor(classes, device=x.device)).any(1)]

        # Check shape 如果检测框超过 max_nms，则按置信度排序后只保留前 max_nms 个框
        n = x.shape[0]  # number of boxes
        if not n:  # no boxes
            continue
        elif n > max_nms:  # excess boxes
            x = x[x[:, 4].argsort(descending=True)[:max_nms]]  # sort by confidence
        else:
            x = x[x[:, 4].argsort(descending=True)]  # sort by confidence

        # Batched NMS 根据类偏移框坐标，对每个类进行非极大值抑制，保留 max_det 个检测框。
        c = x[:, 5:6] * (0 if agnostic else max_wh)  # classes
        boxes, scores = x[:, :4] + c, x[:, 4]  # boxes (offset by class), scores
        i = torchvision.ops.nms(boxes, scores, iou_thres)  # NMS
        if i.shape[0] > max_det:  # limit detections
            i = i[:max_det]

        #输出结果：将NMS后的结果保存到 output 中，如果超时则打印警告并终止处理
        output[xi] = x[i]
        # if mps:
        #     output[xi] = output[xi].to(device)
        if (time.time() - t) > time_limit:
            print(f'WARNING ⚠️ NMS time limit {time_limit:.3f}s exceeded')
            del c,x,box,mask
            break  # time limit exceeded
        del c, x, box, mask
    del device,bs,nc,xc
    del prediction
    return output


def xywh2xyxy(x):
    # Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
    y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
    y[:, 0] = x[:, 0] - x[:, 2] / 2  # top left x
    y[:, 1] = x[:, 1] - x[:, 3] / 2  # top left y
    y[:, 2] = x[:, 0] + x[:, 2] / 2  # bottom right x
    y[:, 3] = x[:, 1] + x[:, 3] / 2  # bottom right y
    return y


def get_labels_from_txt(path):
    labels_dict = dict()
    with open(path) as f:
        for cat_id, label in enumerate(f.readlines()):
            labels_dict[cat_id] = label.strip()
    return labels_dict


def scale_coords(img1_shape, coords, img0_shape, ratio_pad=None):
    # Rescale coords (xyxy) from img1_shape to img0_shape
    if ratio_pad is None:  # calculate from img0_shape
        gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1])  # gain  = old / new
        pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2  # wh padding
    else:
        gain = ratio_pad[0][0]
        pad = ratio_pad[1]

    coords[:, [0, 2]] -= pad[0]  # x padding
    coords[:, [1, 3]] -= pad[1]  # y padding
    coords[:, :4] /= gain
    clip_coords(coords, img0_shape)
    return coords


def clip_coords(boxes, shape):
    # Clip bounding xyxy bounding boxes to image shape (height, width)
    if isinstance(boxes, torch.Tensor):  # faster individually
        boxes[:, 0].clamp_(0, shape[1])  # x1
        boxes[:, 1].clamp_(0, shape[0])  # y1
        boxes[:, 2].clamp_(0, shape[1])  # x2
        boxes[:, 3].clamp_(0, shape[0])  # y2
    else:  # np.array (faster grouped)
        boxes[:, [0, 2]] = boxes[:, [0, 2]].clip(0, shape[1])  # x1, x2
        boxes[:, [1, 3]] = boxes[:, [1, 3]].clip(0, shape[0])  # y1, y2


def nms(box_out, conf_thres=0.4, iou_thres=0.5):
    try:
        boxout = non_max_suppression(box_out, conf_thres=conf_thres, iou_thres=iou_thres, multi_label=True)
    except:
        boxout = non_max_suppression(box_out, conf_thres=conf_thres, iou_thres=iou_thres)
    return boxout


def draw_bbox(bbox, img0, color, wt, names):
    det_result_str = ''
    for idx, class_id in enumerate(bbox[:, 5]):
        if float(bbox[idx][4] < float(0.05)):
            continue
        img0 = cv2.rectangle(img0, (int(bbox[idx][0]), int(bbox[idx][1])), (int(bbox[idx][2]), int(bbox[idx][3])), color, wt)
        img0 = cv2.putText(img0, str(idx) + ' ' + names[int(class_id)], (int(bbox[idx][0]), int(bbox[idx][1] + 16)), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255), 1)
        img0 = cv2.putText(img0, '{:.4f}'.format(bbox[idx][4]), (int(bbox[idx][0]), int(bbox[idx][1] + 32)), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255), 1)
        det_result_str += '{} {} {} {} {} {}\n'.format(names[bbox[idx][5]], str(bbox[idx][4]), bbox[idx][0], bbox[idx][1], bbox[idx][2], bbox[idx][3])
    return img0