All/Python/local/detr/infer.py

import argparse
import random
import numpy as np
import torch
from models import build_model
import torchvision
from torchvision.ops.boxes import batched_nms
import cv2


def get_args_parser():
    parser = argparse.ArgumentParser('Set transformer detector', add_help=False)
    parser.add_argument('--lr', default=1e-4, type=float)
    parser.add_argument('--lr_backbone', default=1e-5, type=float)
    parser.add_argument('--batch_size', default=2, type=int)
    parser.add_argument('--weight_decay', default=1e-4, type=float)
    parser.add_argument('--epochs', default=300, type=int)
    parser.add_argument('--lr_drop', default=200, type=int)
    parser.add_argument('--clip_max_norm', default=0.1, type=float,
                        help='gradient clipping max norm')

    # Model parameters
    parser.add_argument('--frozen_weights', type=str, default=None,
                        help="Path to the pretrained model. If set, only the mask head will be trained")
    # * Backbone
    # 如果设置为resnet101，后面的权重文件路径也需要修改一下
    parser.add_argument('--backbone', default='resnet50', type=str,
                        help="Name of the convolutional backbone to use")
    parser.add_argument('--dilation', action='store_true',
                        help="If true, we replace stride with dilation in the last convolutional block (DC5)")
    parser.add_argument('--position_embedding', default='sine', type=str, choices=('sine', 'learned'),
                        help="Type of positional embedding to use on top of the image features")

    # * Transformer
    parser.add_argument('--enc_layers', default=6, type=int,
                        help="Number of encoding layers in the transformer")
    parser.add_argument('--dec_layers', default=6, type=int,
                        help="Number of decoding layers in the transformer")
    parser.add_argument('--dim_feedforward', default=2048, type=int,
                        help="Intermediate size of the feedforward layers in the transformer blocks")
    parser.add_argument('--hidden_dim', default=256, type=int,
                        help="Size of the embeddings (dimension of the transformer)")
    parser.add_argument('--dropout', default=0.1, type=float,
                        help="Dropout applied in the transformer")
    parser.add_argument('--nheads', default=8, type=int,
                        help="Number of attention heads inside the transformer's attentions")
    parser.add_argument('--num_queries', default=100, type=int,
                        help="Number of query slots")
    parser.add_argument('--pre_norm', action='store_true')

    # * Segmentation
    parser.add_argument('--masks', action='store_true',
                        help="Train segmentation head if the flag is provided")

    # Loss
    parser.add_argument('--no_aux_loss', dest='aux_loss', default='False',
                        help="Disables auxiliary decoding losses (loss at each layer)")
    # * Matcher
    parser.add_argument('--set_cost_class', default=1, type=float,
                        help="Class coefficient in the matching cost")
    parser.add_argument('--set_cost_bbox', default=5, type=float,
                        help="L1 box coefficient in the matching cost")
    parser.add_argument('--set_cost_giou', default=2, type=float,
                        help="giou box coefficient in the matching cost")
    # * Loss coefficients
    parser.add_argument('--mask_loss_coef', default=1, type=float)
    parser.add_argument('--dice_loss_coef', default=1, type=float)
    parser.add_argument('--bbox_loss_coef', default=5, type=float)
    parser.add_argument('--giou_loss_coef', default=2, type=float)
    parser.add_argument('--eos_coef', default=0.1, type=float,
                        help="Relative classification weight of the no-object class")

    # dataset parameters
    parser.add_argument('--dataset_file', default='coco')
    parser.add_argument('--coco_path', type=str, default="coco")
    parser.add_argument('--coco_panoptic_path', type=str)
    parser.add_argument('--remove_difficult', action='store_true')

    # 检测的图像路径
    parser.add_argument('--source_dir', default='demo/images',
                        help='path where to save, empty for no saving')
    # 检测结果保存路径
    parser.add_argument('--output_dir', default='demo/outputs',
                        help='path where to save, empty for no saving')

    parser.add_argument('--device', default='cpu',
                        help='device to use for training / testing')
    parser.add_argument('--seed', default=42, type=int)
    # resnet50对应的权重文件
    parser.add_argument('--resume', default='demo/weights/detr-r50-e632da11.pth',
                        help='resume from checkpoint')
    parser.add_argument('--start_epoch', default=0, type=int, metavar='N',
                        help='start epoch')
    parser.add_argument('--eval', default="True")
    parser.add_argument('--num_workers', default=2, type=int)

    # distributed training parameters
    parser.add_argument('--world_size', default=1, type=int,
                        help='number of distributed processes')
    parser.add_argument('--dist_url', default='env://', help='url used to set up distributed training')
    return parser


def init():
    args, _ = get_args_parser().parse_known_args()
    device = torch.device(args.device)
    model, _, _ = build_model(args)
    Checkpoint = torch.load(args.resume, map_location="cpu")
    model.load_state_dict(Checkpoint["model"], False)
    model.to(device)

    return model, device


# COCO classes
Classes = [
    'N/A', 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus',
    'train', 'truck', 'boat', 'traffic light', 'fire hydrant', 'N/A',
    'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse',
    'sheep', 'cow', 'elephant', 'bear', 'zebra', 'giraffe', 'N/A', 'backpack',
    'umbrella', 'N/A', 'N/A', 'handbag', 'tie', 'suitcase', 'frisbee', 'skis',
    'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove',
    'skateboard', 'surfboard', 'tennis racket', 'bottle', 'N/A', 'wine glass',
    'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple', 'sandwich',
    'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake',
    'chair', 'couch', 'potted plant', 'bed', 'N/A', 'dining table', 'N/A',
    'N/A', 'toilet', 'N/A', 'tv', 'laptop', 'mouse', 'remote', 'keyboard',
    'cell phone', 'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'N/A',
    'book', 'clock', 'vase', 'scissors', 'teddy bear', 'hair drier',
    'toothbrush'
]
Model, Device = init()
ToTensor = torchvision.transforms.ToTensor()


def box_cxcywh_to_xyxy(x):
    x_c, y_c, w, h = x.unbind(1)
    b = [(x_c - 0.5 * w), (y_c - 0.5 * h),
         (x_c + 0.5 * w), (y_c + 0.5 * h)]
    return torch.stack(b, dim=1)


def rescale_bboxes(out_bbox, size):
    img_w, img_h = size
    b = box_cxcywh_to_xyxy(out_bbox)
    b = b * torch.tensor([img_w, img_h, img_w, img_h], dtype=torch.float32)
    return b


def filter_boxes(scores, boxes, confidence=0.7, apply_nms=True, iou=0.5):
    keep = scores.max(-1).values > confidence
    scores, boxes = scores[keep], boxes[keep]

    if apply_nms:
        top_scores, labels = scores.max(-1)
        keep = batched_nms(boxes, top_scores, labels, iou)
        scores, boxes = scores[keep], boxes[keep]

    return scores, boxes


def plot_one_box(x, img, color=None, label=None, line_thickness=1):
    tl = line_thickness or round(0.002 * (img.shape[0] + img.shape[1]) / 2) + 1  # line/font thickness
    color = color or [random.randint(0, 255) for _ in range(3)]
    c1, c2 = (int(x[0]), int(x[1])), (int(x[2]), int(x[3]))
    cv2.rectangle(img, c1, c2, color, thickness=tl, lineType=cv2.LINE_AA)
    if label:
        tf = max(tl - 1, 1)  # font thickness
        t_size = cv2.getTextSize(label, 0, fontScale=tl / 3, thickness=tf)[0]
        c2 = c1[0] + t_size[0], c1[1] - t_size[1] - 3
        cv2.rectangle(img, c1, c2, color, -1, cv2.LINE_AA)  # filled
        cv2.putText(img, label, (c1[0], c1[1] - 2), 0, tl / 3, [225, 255, 255], thickness=tf, lineType=cv2.LINE_AA)


def inference(img: "np.ndarray") -> "np.ndarray":
    # 加载图片数据到cpu、gpu中
    imgTensor = ToTensor(img)
    imgTensor = torch.reshape(imgTensor, [-1, imgTensor.shape[0], imgTensor.shape[1], imgTensor.shape[2]])
    imgTensor.to(Device)

    # Model(image)即可检测图片里的对象数据
    inferenceResult = Model(imgTensor)
    # 检测对象的得分
    scores = inferenceResult["pred_logits"].softmax(-1)[0, :, :-1].cpu()
    # 检测对象的位置数据
    boxes = rescale_bboxes(inferenceResult["pred_boxes"][0,].cpu(), (imgTensor.shape[3], imgTensor.shape[2]))
    scores, boxes = filter_boxes(scores, boxes)
    scores, boxes = scores.data.numpy(), boxes.data.numpy()

    # 在图片中标记对象
    for i in range(boxes.shape[0]):
        class_id = scores[i].argmax()
        label = Classes[class_id]
        confidence = scores[i].max()
        text = f"{label} {confidence:.3f}"
        plot_one_box(boxes[i], img, label=text)

    # 返回标记后的图像数据
    return img


def main():
    img = cv2.imread("./123.png")
    out = inference(img)
    cv2.imwrite("./out.jpg", out)


if __name__ == "__main__":
    main()