have a question about IoU metric: bbox

[MinGiSa]

When I run training with the PyTorch version, I obtain the following IoU metrics. I modified the code to increase the resolution from 640 to 1024 and used images like the one provided below,

However, the -1.000 scores do not change even after further training. What should I fix, and could you provide some advice?

IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.784 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.898 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.891 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.785 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.586 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.914 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.930 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.930 best_stat: {'epoch': 70, 'coco_eval_bbox': 0.7925207858496603} Training time 0:32:39

[lyuwenyu]

I think this involves how coco_metric defines objects of different sizes. In your case, It may thinks they are all large objects. If the detection results is good, you can ignore -1.000 scores

[MinGiSa]

I think this involves how coco_metric defines objects of different sizes. In your case, It may thinks they are all large objects. If the detection results is good, you can ignore -1.000 scores

thank you for giving answer.

there is a new question about results. I changed the model with rtdetr_r101vd_6x_coco.yml and obtained these training results.

=========================================================== IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.921 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 1.000 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.921 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.930 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.930 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.935 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = -1.000 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.935 best_stat: {'epoch': 88, 'coco_eval_bbox': 0.9470352035203521} Training time 1:32:23

===========================================================

However, when I perform inference, the results are poor. Is there any solution?

threshold 0 result

threshold 0.1 result

=============================================================

import torch from torch import nn from torchvision.transforms import transforms from PIL import Image, ImageDraw import sys import os sys.path.insert(0, os.path.join(os.path.dirname(os.path.abspath(file)), '..')) from src.core import YAMLConfig import argparse from pathlib import Path import time

class ImageReader: def init(self, resize=224, mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]): self.transform = transforms.Compose([

transforms.Resize((resize, resize)) if isinstance(resize, int) else transforms.Resize(

        #     (resize[0], resize[1])),
        transforms.ToTensor(),
        # transforms.Normalize(mean=mean, std=std),
    ])
    self.resize = resize
    self.pil_img = None

def __call__(self, image_path, *args, **kwargs):
    """
    读取图片
    """
    self.pil_img = Image.open(image_path).convert('RGB').resize((self.resize, self.resize))
    return self.transform(self.pil_img).unsqueeze(0)

class Model(nn.Module): def init(self, confg=None, ckpt="") -> None: super().init() self.cfg = YAMLConfig(confg, resume=ckpt) if ckpt: checkpoint = torch.load(ckpt, map_location='cpu') if 'ema' in checkpoint: state = checkpoint['ema']['module'] else: state = checkpoint['model'] else: raise AttributeError('only support resume to load model.state_dict by now.')

    # NOTE load train mode state -> convert to deploy mode
    self.cfg.model.load_state_dict(state)

    self.model = self.cfg.model.deploy()
    self.postprocessor = self.cfg.postprocessor.deploy()
    # print(self.postprocessor.deploy_mode)

def forward(self, images, orig_target_sizes):
    outputs = self.model(images)
    return self.postprocessor(outputs, orig_target_sizes)

def get_argparser(): parser = argparse.ArgumentParser() parser.add_argument("--config", default=r".\RT-DETR\rtdetr_pytorch\configs\rtdetr\rtdetr_r101vd_6x_coco.yml", help="配置文件路径") parser.add_argument("--ckpt", default=r".\RT-DETR\rtdetr_pytorch\logs\checkpoint.pth", help="权重文件路径") parser.add_argument("--image", default=r".\RT-DETR\rtdetr_pytorch\dataset\customDataSet\test", help="待推理图片路径") parser.add_argument("--output_dir", default=r".\RT-DETR\rtdetr_pytorch\inference", help="输出文件保存路径") parser.add_argument("--device", default="cuda") return parser

def main(args): device = torch.device(args.device) model = Model(confg=args.config, ckpt=args.ckpt) model.to(device=device) for filename in os.listdir(args.image): img_path = Path(os.path.join(args.image, filename)) device = torch.device(args.device) reader = ImageReader(resize=1024)

    img =reader(img_path).to(device)
    size = torch.tensor([[img.shape[2], img.shape[3]]]).to(device)
    start = time.time()
    output = model(img, size)
    print(f"elapsedTime：{time.time() - start:.4f}s")
    labels, boxes, scores = output
    im = reader.pil_img
    draw = ImageDraw.Draw(im)
    thrh = 0.1

    for i in range(img.shape[0]):

        scr = scores[i]
        lab = labels[i][scr > thrh]
        box = boxes[i][scr > thrh]

        for b in box:
            draw.rectangle(list(b), outline='red', )
            draw.text((b[0], b[1]), text=str(lab[i]), fill='blue', )

    save_path = Path(args.output_dir) / img_path.name
    im.save(save_path)
    print(f"savePath:{save_path}")

if name == "main": main(get_argparser().parse_args())

[amndzr]

@MinGiSa Im having the same issue, how did you fix it?

[MinGiSa]

@MinGiSa Im having the same issue, how did you fix it?

Nope, not yet solved