使用 KITTI数据集训练YOLOX

1. 现在KITTI集后，首先将数据集转换为COCO数据集格式。

kitti_vis.py

import os
from pathlib import Path
import numpy as np
import cv2


def anno_vis(img, anno_list):
    for anno in anno_list:
        points = np.array(anno[4:8], dtype=np.float32)
        cv2.rectangle(img, (int(points[0]),int(points[1])), (int(points[2]),int(points[3])), (0, 0, 255), 2)
        cv2.putText(img, anno[0], (int(points[0]),int(points[1])), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255), 2)


    cv2.imshow('img', img)
    ret = cv2.waitKey(0)
    if ret == 27:
        exit(0)

if __name__ == '__main__':
    
    img_root = Path(r'D:\BaiduNetdiskDownload\CV\KITTI\KITTI-train_test-Image\training\image_2')
    label_root = Path(r'D:\BaiduNetdiskDownload\CV\KITTI\KITTI-train_test-Label\training\label_2')
    
    img_list = os.listdir(img_root)
    
    for img_name in img_list[:5]:
        img_name = Path(img_name)
        label_name = img_name.with_suffix('.txt')
        img = cv2.imread(str(img_root/img_name))
    
        with open(label_root/label_name) as f:
            l = [x.split() for x in f.read().strip().splitlines()]
        anno_vis(img, l)

 kitti_split.py

'''
用于将KITTI数据集的7000多张训练集分为：前4000张为训练集，4000-6000张为验证集，剩余为测试集
运行命令：
python ./tools/kitti_split.py --source_img_path ./KITTI_origin/training/image_2 --source_label_path ./KITTI_origin/training/label_2/
--dst_img_path ./KITTI_YOLOX/img --dst_label_path ./KITTI_YOLOX/label



    # img_root = Path(r'D:\BaiduNetdiskDownload\CV\KITTI\KITTI-train_test-Image\training\image_2')
    # label_root = Path(r'D:\BaiduNetdiskDownload\CV\KITTI\KITTI-train_test-Label\training\label_2')

'''


import os
import argparse
from pathlib import Path
import shutil
from tqdm import tqdm
from loguru import logger


def make_parser():
    parser = argparse.ArgumentParser("")   
    parser.add_argument('--source_img_path', default=r'D:\BaiduNetdiskDownload\CV\KITTI\KITTI-train_test-Image\training\image_2',  help="Specify original kitti img path")
    parser.add_argument('--source_label_path', default=r'D:\BaiduNetdiskDownload\CV\KITTI\KITTI-train_test-Label\training\label_2',help="Specify original kitti label path")

    parser.add_argument('--dst_img_path', default=r'D:\BaiduNetdiskDownload\CV\KITTI\KITTI_YOLOX\img',help="Specify splited kitti img path")
    parser.add_argument('--dst_label_path', default=r'D:\BaiduNetdiskDownload\CV\KITTI\KITTI_YOLOX\label',help="Specify splited kitti label path")

    return parser

def check_dir(dir):
    if Path(dir).is_dir() == False:
        Path(dir).mkdir(parents=True, exist_ok=True)
        logger.info('Created %s' % dir)

if __name__ == '__main__':
    args = make_parser().parse_args()

    img_root = Path(args.source_img_path)
    label_root = Path(args.source_label_path)

    # img_root = Path(r'D:\BaiduNetdiskDownload\CV\KITTI\KITTI-train_test-Image\training\image_2')
    # label_root = Path(r'D:\BaiduNetdiskDownload\CV\KITTI\KITTI-train_test-Label\training\label_2')


    img_list = os.listdir(img_root)
    dst_train_img_root = Path(args.dst_img_path)/'train'
    dst_val_img_root = Path(args.dst_img_path)/'val'
    dst_test_img_root = Path(args.dst_img_path)/'test'

    dst_train_label_root = Path(args.dst_label_path)/'train'
    dst_val_label_root = Path(args.dst_label_path)/'val'
    dst_test_label_root = Path(args.dst_label_path)/'test'

    check_dir(dst_train_img_root)
    check_dir(dst_val_img_root)
    check_dir(dst_test_img_root)
    check_dir(dst_train_label_root)
    check_dir(dst_val_label_root)
    check_dir(dst_test_label_root)

    for img_name in tqdm(img_list):
        if int(Path(img_name).stem) < 4000:
            shutil.copyfile(img_root/img_name, dst_train_img_root/img_name)
            shutil.copyfile(label_root/(Path(img_name).with_suffix('.txt')), dst_train_label_root/(Path(img_name).with_suffix('.txt')))
            
        elif int(Path(img_name).stem) < 6000:
            shutil.copyfile(img_root/img_name, dst_val_img_root/img_name)
            shutil.copyfile(label_root/(Path(img_name).with_suffix('.txt')), dst_val_label_root/(Path(img_name).with_suffix('.txt')))
            
        else:
            shutil.copyfile(img_root/img_name, dst_test_img_root/img_name)
            shutil.copyfile(label_root/(Path(img_name).with_suffix('.txt')), dst_test_label_root/(Path(img_name).with_suffix('.txt')))
            
            

kitti2coco.py

'''
KITTI标注转COCO标注

运行命令：

（1）训练集：python tools/kitti2coco.py --img_path ./KITTI_YOLOX/img/train --label_path ./KITTI_YOLOX/label/train --dst_json ./train.json
（2）验证集：python tools/kitti2coco.py --img_path ./KITTI_YOLOX/img/val --label_path ./KITTI_YOLOX/label/val --dst_json ./val.json
（3）测试集：python tools/kitti2coco.py --img_path ./KITTI_YOLOX/img/test --label_path ./KITTI_YOLOX/label/test --dst_json ./test.json
'''
import os
import json
import argparse
from pathlib import Path
import cv2
from tqdm import tqdm

# parser.add_argument('--dst_img_path', default=r'D:\BaiduNetdiskDownload\CV\KITTI\KITTI_YOLOX\img',
#                     help="Specify splited kitti img path")
# parser.add_argument('--dst_label_path', default=r'D:\BaiduNetdiskDownload\CV\KITTI\KITTI_YOLOX\label',
#                     help="Specify splited kitti label path")



def make_parser():
    # parser = argparse.ArgumentParser("Kitti to COCO format")
    # parser.add_argument('--img_path', type=str, default=r'D:\BaiduNetdiskDownload\CV\KITTI\KITTI_YOLOX\img\train',
    #                                                     help='Specify img path')
    # parser.add_argument('--label_path', type=str, default=r'D:\BaiduNetdiskDownload\CV\KITTI\KITTI_YOLOX\label\train',
    #                     help='Specify label path')
    # parser.add_argument('--dst_json', type=str, default=r'D:\BaiduNetdiskDownload\CV\KITTI\train.json', help='Specify generated json file name')



    # parser = argparse.ArgumentParser("Kitti to COCO format")
    # parser.add_argument('--img_path', type=str, default=r'D:\BaiduNetdiskDownload\CV\KITTI\KITTI_YOLOX\img\test',
    #                                                     help='Specify img path')
    # parser.add_argument('--label_path', type=str, default=r'D:\BaiduNetdiskDownload\CV\KITTI\KITTI_YOLOX\label\test',
    #                     help='Specify label path')
    # parser.add_argument('--dst_json', type=str, default=r'D:\BaiduNetdiskDownload\CV\KITTI\test.json', help='Specify generated json file name')
    #

    parser = argparse.ArgumentParser("Kitti to COCO format")
    parser.add_argument('--img_path', type=str, default=r'D:\BaiduNetdiskDownload\CV\KITTI\KITTI_YOLOX\img\val',
                                                        help='Specify img path')
    parser.add_argument('--label_path', type=str, default=r'D:\BaiduNetdiskDownload\CV\KITTI\KITTI_YOLOX\label\val',
                        help='Specify label path')
    parser.add_argument('--dst_json', type=str, default=r'D:\BaiduNetdiskDownload\CV\KITTI\val.json', help='Specify generated json file name')


    return parser

if __name__ == '__main__':
    args = make_parser().parse_args()
    img_root = Path(args.img_path)
    label_root = Path(args.label_path)

    category_dict = {
        1:'Car', 
        2:'Van', 
        3:'Pedestrian', 
        4:'Person_sitting', 
        5:'Truck',  
        6:'Cyclist', 
        7:'Tram'
    }

    category_name2id_dict = {v:k for k, v in category_dict.items()}


    img_list = os.listdir(img_root)

    img_id = 0
    anno_id = 0

    json_images_list = list()
    json_annotations_list = list()
    json_categories_list = list()

    for img_name in tqdm(img_list):

        img = cv2.imread(str(img_root/img_name))
        img_height, img_width, _ = img.shape
        img_dict = {
            'license': None,
            'file_name': img_name,
            'coco_url': None,
            'height': img_height, 
            'width': img_width, 
            'date_captured': None, 
            'flickr_url': None,
            'id': img_id
        }
        json_images_list.append(img_dict)
        
        label_name = Path(img_name).with_suffix('.txt')
        with open(label_root/label_name) as f:
            anno_list = [x.split() for x in f.read().strip().splitlines()]
        for anno in anno_list:
            if anno[0] in category_name2id_dict:
                bbox = [float(anno[4]), float(anno[5]), 
                        float(anno[6])-float(anno[4]), float(anno[7])-float(anno[5])] #   anno[4:8]
                area = bbox[2]*bbox[3]
                
                anno_dict = {
                    'segmentation': None,
                    'area': area,
                    'iscrowd': 0,
                    'image_id': img_id,
                    'bbox': bbox, 
                    'category_id': category_name2id_dict[anno[0]],
                    'id': anno_id
                }
                json_annotations_list.append(anno_dict)
                anno_id += 1
        img_id += 1
        
    for id in category_dict:
        json_categories_list.append({
            'supercategory': None,
            'id': id,
            'name': category_dict[id]
        })
        
    json_dict = {
        'images': json_images_list,
        'annotations': json_annotations_list,
        'categories': json_categories_list
    }


    with open(args.dst_json,"w") as f:
        json.dump(json_dict,f)






    
    
    
    
    
    

 COCO_vis.py

'''
验证转换后的json格式标注的准确性。
运行命令：python tools/COCO_vis.py --img_root ./KITTI_YOLOX/img/train --label_file ./KITTI_YOLOX/train.json
'''

import argparse
from pathlib import Path
import numpy as np
import cv2
from pycocotools.coco import COCO

# parser.add_argument('--img_path', type=str, default=r'D:\BaiduNetdiskDownload\CV\KITTI\KITTI_YOLOX\img\val',
#                     help='Specify img path')
# parser.add_argument('--label_path', type=str, default=r'D:\BaiduNetdiskDownload\CV\KITTI\KITTI_YOLOX\label\val',
#                     help='Specify label path')
# parser.add_argument('--dst_json', type=str, default=r'D:\BaiduNetdiskDownload\CV\KITTI\val.json',
#                     help='Specify generated json file name')


def make_parser():
    parser = argparse.ArgumentParser("")        
    parser.add_argument('--img_root', type=str, default=r'D:\BaiduNetdiskDownload\CV\KITTI\KITTI_YOLOX\img\train', help='Specify img path')
    parser.add_argument('--label_file', type=str, default=r'D:\BaiduNetdiskDownload\CV\KITTI\train.json', help='Specify COCO format label file')

    return parser

if __name__ == '__main__':
    args = make_parser().parse_args()
        
    img_root = args.img_root
    anno_file = args.label_file

    coco = COCO(anno_file)
    img_ids = coco.getImgIds()

    category_list = coco.loadCats(coco.getCatIds())
    label_id2name = dict([(item['id'], item['name']) for item in category_list])

    for img_id in img_ids:
        img_info = coco.loadImgs(img_id)[0]
        print('img name: ', str(Path(img_root)/img_info['file_name']))
        img = cv2.imread(str(Path(img_root)/img_info['file_name']))
        
        img_width = img_info["width"]
        img_height = img_info["height"]
        anno_ids = coco.getAnnIds(imgIds=[img_id], iscrowd=False)
        result_anno_list = list()
        
        for anno_id in anno_ids:
            annotation = coco.loadAnns(anno_id)
            x1 = np.max((0, annotation[0]["bbox"][0]))
            y1 = np.max((0, annotation[0]["bbox"][1]))
            x2 = np.min((img_width, x1 + np.max((0, annotation[0]["bbox"][2]))))
            y2 = np.min((img_height, y1 + np.max((0, annotation[0]["bbox"][3]))))
            
            
            label = label_id2name[annotation[0]['category_id']]
            result_anno_list.append([label, x1, y1, x2, y2])

            cv2.rectangle(img, (int(x1), int(y1)), (int(x2), int(y2)), (0,0,255), 1)
            cv2.putText(img, label, (int(x1), int(y1)), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (128,255,255))
        cv2.imshow('img', img)
        ret = cv2.waitKey(0)    
        if ret == 27:
            exit(0)

2.按照训练COCO数据集合的指令训练KITTI即可

python -m yolox.tools.train -n yolox-s -d 1 -b 32 --fp16

或者： python -m yolox.tools.train -f exps/default/yolox_s.py -d 1 -b 32 --fp

16

 python -m yolox.tools.train  -f exps/kitti_car_detection/yolox_s.py -c  /mnt/d/work/study/detect/7/YOLOX_outputs/yolox_s/best_ckpt.pth      -d 0 -b 16 --fp16

 olox) xuefei@f123:/mnt/d/work/study/detect/7$
(yolox) xuefei@f123:/mnt/d/work/study/detect/7$ python -m yolox.tools.train  -f exps/kitti_car_detection/yolox_s.py  -d 1 -b 16 --fp16
2024-02-05 23:08:04 | INFO     | yolox.core.trainer:130 - args: Namespace(batch_size=16, cache=False, ckpt=None, devices=1, dist_backend='nccl', dist_url=None, exp_file='exps/kitti_car_detection/yolox_s.py', experiment_name='yolox_s', fp16=True, logger='tensorboard', machine_rank=0, name=None, num_machines=1, occupy=False, opts=[], resume=False, start_epoch=None)
2024-02-05 23:08:04 | INFO     | yolox.core.trainer:131 - exp value:
╒═══════════════════╤═══════════════════════════════════════════════════════════════╕
│ keys              │ values                                                        │
╞═══════════════════╪═══════════════════════════════════════════════════════════════╡
│ seed              │ None                                                          │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ output_dir        │ './YOLOX_outputs'                                             │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ print_interval    │ 10                                                            │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ eval_interval     │ 10                                                            │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ num_classes       │ 7                                                             │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ depth             │ 0.33                                                          │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ width             │ 0.5                                                           │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ act               │ 'silu'                                                        │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ data_num_workers  │ 16                                                            │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ input_size        │ (256, 832)                                                    │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ multiscale_range  │ 5                                                             │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ data_dir          │ '/mnt/d/BaiduNetdiskDownload/CV/KITTI/KITTI_YOLOX/img/'       │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ train_ann         │ '/mnt/d/BaiduNetdiskDownload/CV/KITTI/KITTI_YOLOX/train.json' │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ val_ann           │ '/mnt/d/BaiduNetdiskDownload/CV/KITTI/KITTI_YOLOX/val.json'   │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ test_ann          │ '/mnt/d/BaiduNetdiskDownload/CV/KITTI/KITTI_YOLOX/test.json'  │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ mosaic_prob       │ 1.0                                                           │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ mixup_prob        │ 1.0                                                           │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ hsv_prob          │ 1.0                                                           │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ flip_prob         │ 0.5                                                           │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ degrees           │ 10.0                                                          │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ translate         │ 0.1                                                           │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ mosaic_scale      │ (0.1, 2)                                                      │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ enable_mixup      │ True                                                          │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ mixup_scale       │ (0.5, 1.5)                                                    │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ shear             │ 2.0                                                           │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ warmup_epochs     │ 5                                                             │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ max_epoch         │ 300                                                           │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ warmup_lr         │ 0                                                             │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ min_lr_ratio      │ 0.05                                                          │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ basic_lr_per_img  │ 0.00015625                                                    │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ scheduler         │ 'yoloxwarmcos'                                                │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ no_aug_epochs     │ 80                                                            │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ ema               │ True                                                          │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ weight_decay      │ 0.0005                                                        │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ momentum          │ 0.9                                                           │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ save_history_ckpt │ True                                                          │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ exp_name          │ 'yolox_s'                                                     │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ test_size         │ (256, 832)                                                    │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ test_conf         │ 0.01                                                          │
├───────────────────┼───────────────────────────────────────────────────────────────┤
│ nmsthre           │ 0.65                                                          │
╘═══════════════════╧═══════════════════════════════════════════════════════════════╛
2024-02-05 23:08:05 | INFO     | yolox.core.trainer:137 - Model Summary: Params: 8.94M, Gflops: 13.92
2024-02-05 23:08:07 | INFO     | yolox.data.datasets.kitti:64 - loading annotations into memory...
2024-02-05 23:08:07 | INFO     | yolox.data.datasets.kitti:64 - Done (t=0.05s)
2024-02-05 23:08:07 | INFO     | pycocotools.coco:86 - creating index...
2024-02-05 23:08:07 | INFO     | pycocotools.coco:86 - index created!
2024-02-05 23:08:08 | INFO     | yolox.core.trainer:155 - init prefetcher, this might take one minute or less...
2024-02-05 23:08:17 | INFO     | yolox.data.datasets.kitti:64 - loading annotations into memory...
2024-02-05 23:08:17 | INFO     | yolox.data.datasets.kitti:64 - Done (t=0.05s)
2024-02-05 23:08:17 | INFO     | pycocotools.coco:86 - creating index...
2024-02-05 23:08:17 | INFO     | pycocotools.coco:86 - index created!
2024-02-05 23:08:17 | INFO     | yolox.core.trainer:191 - Training start...
2024-02-05 23:08:17 | INFO     | yolox.core.trainer:192 -
YOLOX(
  (backbone): YOLOPAFPN(
    (backbone): CSPDarknet(
      (stem): Focus(
        (conv): BaseConv(
          (conv): Conv2d(12, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(32, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (dark2): Sequential(
        (0): BaseConv(
          (conv): Conv2d(32, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (1): CSPLayer(
          (conv1): BaseConv(
            (conv): Conv2d(64, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(32, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (conv2): BaseConv(
            (conv): Conv2d(64, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(32, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (conv3): BaseConv(
            (conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (m): Sequential(
            (0): Bottleneck(
              (conv1): BaseConv(
                (conv): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(32, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
              (conv2): BaseConv(
                (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn): BatchNorm2d(32, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
            )
          )
        )
      )
      (dark3): Sequential(
        (0): BaseConv(
          (conv): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (1): CSPLayer(
          (conv1): BaseConv(
            (conv): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (conv2): BaseConv(
            (conv): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (conv3): BaseConv(
            (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (m): Sequential(
            (0): Bottleneck(
              (conv1): BaseConv(
                (conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
              (conv2): BaseConv(
                (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
            )
            (1): Bottleneck(
              (conv1): BaseConv(
                (conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
              (conv2): BaseConv(
                (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
            )
            (2): Bottleneck(
              (conv1): BaseConv(
                (conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
              (conv2): BaseConv(
                (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
            )
          )
        )
      )
      (dark4): Sequential(
        (0): BaseConv(
          (conv): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (1): CSPLayer(
          (conv1): BaseConv(
            (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (conv2): BaseConv(
            (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (conv3): BaseConv(
            (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (m): Sequential(
            (0): Bottleneck(
              (conv1): BaseConv(
                (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
              (conv2): BaseConv(
                (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
            )
            (1): Bottleneck(
              (conv1): BaseConv(
                (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
              (conv2): BaseConv(
                (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
            )
            (2): Bottleneck(
              (conv1): BaseConv(
                (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
              (conv2): BaseConv(
                (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
            )
          )
        )
      )
      (dark5): Sequential(
        (0): BaseConv(
          (conv): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (1): SPPBottleneck(
          (conv1): BaseConv(
            (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (m): ModuleList(
            (0): MaxPool2d(kernel_size=5, stride=1, padding=2, dilation=1, ceil_mode=False)
            (1): MaxPool2d(kernel_size=9, stride=1, padding=4, dilation=1, ceil_mode=False)
            (2): MaxPool2d(kernel_size=13, stride=1, padding=6, dilation=1, ceil_mode=False)
          )
          (conv2): BaseConv(
            (conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
        (2): CSPLayer(
          (conv1): BaseConv(
            (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (conv2): BaseConv(
            (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (conv3): BaseConv(
            (conv): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (m): Sequential(
            (0): Bottleneck(
              (conv1): BaseConv(
                (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
              (conv2): BaseConv(
                (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
                (act): SiLU(inplace=True)
              )
            )
          )
        )
      )
    )
    (upsample): Upsample(scale_factor=2.0, mode=nearest)
    (lateral_conv0): BaseConv(
      (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (C3_p4): CSPLayer(
      (conv1): BaseConv(
        (conv): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (conv2): BaseConv(
        (conv): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (conv3): BaseConv(
        (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (conv1): BaseConv(
            (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (conv2): BaseConv(
            (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (reduce_conv1): BaseConv(
      (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (C3_p3): CSPLayer(
      (conv1): BaseConv(
        (conv): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (conv2): BaseConv(
        (conv): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (conv3): BaseConv(
        (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (conv1): BaseConv(
            (conv): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (conv2): BaseConv(
            (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(64, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (bu_conv2): BaseConv(
      (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (C3_n3): CSPLayer(
      (conv1): BaseConv(
        (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (conv2): BaseConv(
        (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (conv3): BaseConv(
        (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (conv1): BaseConv(
            (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (conv2): BaseConv(
            (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
      )
    )
    (bu_conv1): BaseConv(
      (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
      (act): SiLU(inplace=True)
    )
    (C3_n4): CSPLayer(
      (conv1): BaseConv(
        (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (conv2): BaseConv(
        (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (conv3): BaseConv(
        (conv): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(512, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (m): Sequential(
        (0): Bottleneck(
          (conv1): BaseConv(
            (conv): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
          (conv2): BaseConv(
            (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
            (act): SiLU(inplace=True)
          )
        )
      )
    )
  )
  (head): YOLOXHead(
    (cls_convs): ModuleList(
      (0): Sequential(
        (0): BaseConv(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (1): BaseConv(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (1): Sequential(
        (0): BaseConv(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (1): BaseConv(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (2): Sequential(
        (0): BaseConv(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (1): BaseConv(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
    )
    (reg_convs): ModuleList(
      (0): Sequential(
        (0): BaseConv(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (1): BaseConv(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (1): Sequential(
        (0): BaseConv(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (1): BaseConv(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
      (2): Sequential(
        (0): BaseConv(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
        (1): BaseConv(
          (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
          (act): SiLU(inplace=True)
        )
      )
    )
    (cls_preds): ModuleList(
      (0): Conv2d(128, 7, kernel_size=(1, 1), stride=(1, 1))
      (1): Conv2d(128, 7, kernel_size=(1, 1), stride=(1, 1))
      (2): Conv2d(128, 7, kernel_size=(1, 1), stride=(1, 1))
    )
    (reg_preds): ModuleList(
      (0): Conv2d(128, 4, kernel_size=(1, 1), stride=(1, 1))
      (1): Conv2d(128, 4, kernel_size=(1, 1), stride=(1, 1))
      (2): Conv2d(128, 4, kernel_size=(1, 1), stride=(1, 1))
    )
    (obj_preds): ModuleList(
      (0): Conv2d(128, 1, kernel_size=(1, 1), stride=(1, 1))
      (1): Conv2d(128, 1, kernel_size=(1, 1), stride=(1, 1))
      (2): Conv2d(128, 1, kernel_size=(1, 1), stride=(1, 1))
    )
    (stems): ModuleList(
      (0): BaseConv(
        (conv): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (1): BaseConv(
        (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
      (2): BaseConv(
        (conv): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(128, eps=0.001, momentum=0.03, affine=True, track_running_stats=True)
        (act): SiLU(inplace=True)
      )
    )
    (l1_loss): L1Loss()
    (bcewithlog_loss): BCEWithLogitsLoss()
    (iou_loss): IOUloss()
  )
)

2024-02-05 23:15:59 | INFO     | yolox.core.trainer:203 - ---> start train epoch1
2024-02-05 23:16:04 | INFO     | yolox.core.trainer:261 - epoch: 1/100, iter: 10/250, mem: 2730Mb, iter_time: 0.532s, data_time: 0.001s, total_loss: 15.1, iou_loss: 4.7, l1_loss: 2.4, conf_loss: 7.0, cls_loss: 1.1, lr: 1.600e-07, size: 256, ETA: 3:41:23
2024-02-05 23:16:10 | INFO     | yolox.core.trainer:261 - epoch: 1/100, iter: 20/250, mem: 3169Mb, iter_time: 0.625s, data_time: 0.001s, total_loss: 17.2, iou_loss: 4.6, l1_loss: 2.3, conf_loss: 9.1, cls_loss: 1.1, lr: 6.400e-07, size: 288, ETA: 4:00:46
2024-02-05 23:16:17 | INFO     | yolox.core.trainer:261 - epoch: 1/100, iter: 30/250, mem: 3623Mb, iter_time: 0.672s, data_time: 0.001s, total_loss: 19.7, iou_loss: 4.6, l1_loss: 2.9, conf_loss: 11.1, cls_loss: 1.1, lr: 1.440e-06, size: 352, ETA: 4:13:38
2024-02-05 23:16:20 | INFO     | yolox.core.trainer:261 - epoch: 1/100, iter: 40/250, mem: 3623Mb, iter_time: 0.249s, data_time: 0.005s, total_loss: 12.8, iou_loss: 4.7, l1_loss: 2.1, conf_loss: 5.0, cls_loss: 1.0, lr: 2.560e-06, size: 96, ETA: 3:36:04
2024-02-05 23:16:28 | INFO     | yolox.core.trainer:261 - epoch: 1/100, iter: 50/250, mem: 3623Mb, iter_time: 0.822s, data_time: 0.501s, total_loss: 13.9, iou_loss: 4.6, l1_loss: 2.2, conf_loss: 5.9, cls_loss: 1.1, lr: 4.000e-06, size: 160, ETA: 4:01:09
2024-02-05 23:16:38 | INFO     | yolox.core.trainer:261 - epoch: 1/100, iter: 60/250, mem: 4258Mb, iter_time: 1.034s, data_time: 0.002s, total_loss: 19.6, iou_loss: 4.7, l1_loss: 2.8, conf_loss: 11.1, cls_loss: 1.0, lr: 5.760e-06, size: 416, ETA: 4:32:31
2024-02-05 23:16:42 | INFO     | yolox.core.trainer:261 - epoch: 1/100, iter: 70/250, mem: 4258Mb, iter_time: 0.331s, data_time: 0.001s, total_loss: 18.8, iou_loss: 4.6, l1_loss: 2.9, conf_loss: 10.1, cls_loss: 1.1, lr: 7.840e-06, size: 256, ETA: 4:13:07
2024-02-05 23:16:48 | INFO     | yolox.core.trainer:261 - epoch: 1/100, iter: 80/250, mem: 4258Mb, iter_time: 0.668s, data_time: 0.189s, total_loss: 18.9, iou_loss: 4.7, l1_loss: 2.6, conf_loss: 10.6, cls_loss: 1.1, lr: 1.024e-05, size: 352, ETA: 4:16:03
2024-02-05 23:16:52 | INFO     | yolox.core.trainer:261 - epoch: 1/100, iter: 90/250, mem: 4258Mb, iter_time: 0.392s, data_time: 0.001s, total_loss: 14.7, iou_loss: 4.6, l1_loss: 2.2, conf_loss: 6.7, cls_loss: 1.2, lr: 1.296e-05, size: 192, ETA: 4:05:35
2024-02-05 23:17:00 | INFO     | yolox.core.trainer:261 - epoch: 1/100, iter: 100/250, mem: 4258Mb, iter_time: 0.815s, data_time: 0.024s, total_loss: 20.8, iou_loss: 4.6, l1_loss: 2.4, conf_loss: 12.6, cls_loss: 1.2, lr: 1.600e-05, size: 384, ETA: 4:14:44
2024-02-05 23:17:04 | INFO     | yolox.core.trainer:261 - epoch: 1/100, iter: 110/250, mem: 4258Mb, iter_time: 0.324s, data_time: 0.001s, total_loss: 16.6, iou_loss: 4.6, l1_loss: 2.1, conf_loss: 8.7, cls_loss: 1.2, lr: 1.936e-05, size: 256, ETA: 4:03:42
2024-02-05 23:17:12 | INFO     | yolox.core.trainer:261 - epoch: 1/100, iter: 120/250, mem: 4258Mb, iter_time: 0.796s, data_time: 0.153s, total_loss: 17.6, iou_loss: 4.6, l1_loss: 2.8, conf_loss: 9.1, cls_loss: 1.1, lr: 2.304e-05, size: 320, ETA: 4:10:48
2024-02-05 23:17:20 | INFO     | yolox.core.trainer:261 - epoch: 1/100, iter: 130/250, mem: 4258Mb, iter_time: 0.796s, data_time: 0.233s, total_loss: 18.3, iou_loss: 4.6, l1_loss: 2.5, conf_loss: 10.0, cls_loss: 1.2, lr: 2.704e-05, size: 384, ETA: 4:16:48
2024-02-05 23:17:24 | INFO     | yolox.core.trainer:261 - epoch: 1/100, iter: 140/250, mem: 4258Mb, iter_time: 0.474s, data_time: 0.002s, total_loss: 18.8, iou_loss: 4.6, l1_loss: 2.6, conf_loss: 10.4, cls_loss: 1.2, lr: 3.136e-05, size: 352, ETA: 4:12:24
2024-02-05 23:17:30 | INFO     | yolox.core.trainer:261 - epoch: 1/100, iter: 150/250, mem: 4258Mb, iter_time: 0.611s, data_time: 0.216s, total_loss: 15.7, iou_loss: 4.5, l1_loss: 2.2, conf_loss: 7.8, cls_loss: 1.3, lr: 3.600e-05, size: 288, ETA: 4:12:21
2024-02-05 23:17:38 | INFO     | yolox.core.trainer:261 - epoch: 1/100, iter: 160/250, mem: 4258Mb, iter_time: 0.752s, data_time: 0.313s, total_loss: 17.2, iou_loss: 4.6, l1_loss: 2.8, conf_loss: 8.8, cls_loss: 1.0, lr: 4.096e-05, size: 320, ETA: 4:15:56
2024-02-05 23:17:40 | INFO     | yolox.core.trainer:261 - epoch: 1/100, iter: 170/250, mem: 4258Mb, iter_time: 0.249s, data_time: 0.001s, total_loss: 13.2, iou_loss: 4.6, l1_loss: 2.3, conf_loss: 5.2, cls_loss: 1.0, lr: 4.624e-05, size: 128, ETA: 4:06:51
2024-02-05 23:17:48 | INFO     | yolox.core.trainer:261 - epoch: 1/100, iter: 180/250, mem: 4258Mb, iter_time: 0.750s, data_time: 0.541s, total_loss: 13.3, iou_loss: 4.6, l1_loss: 2.1, conf_loss: 5.5, cls_loss: 1.0, lr: 5.184e-05, size: 128, ETA: 4:10:16
2024-02-05 23:17:52 | INFO     | yolox.core.trainer:261 - epoch: 1/100, iter: 190/250, mem: 4258Mb, iter_time: 0.362s, data_time: 0.001s, total_loss: 15.7, iou_loss: 4.6, l1_loss: 2.7, conf_loss: 7.3, cls_loss: 1.2, lr: 5.776e-05, size: 288, ETA: 4:04:53
2024-02-05 23:18:00 | INFO     | yolox.core.trainer:261 - epoch: 1/100, iter: 200/250, mem: 4258Mb, iter_time: 0.816s, data_time: 0.469s, total_loss: 14.8, iou_loss: 4.5, l1_loss: 2.2, conf_loss: 6.9, cls_loss: 1.2, lr: 6.400e-05, size: 256, ETA: 4:09:24
2024-02-05 23:18:07 | INFO     | yolox.core.trainer:261 - epoch: 1/100, iter: 210/250, mem: 4258Mb, iter_time: 0.774s, data_time: 0.378s, total_loss: 15.5, iou_loss: 4.5, l1_loss: 2.4, conf_loss: 7.3, cls_loss: 1.2, lr: 7.056e-05, size: 288, ETA: 4:12:40
2024-02-05 23:18:09 | INFO     | yolox.core.trainer:261 - epoch: 1/100, iter: 220/250, mem: 4258Mb, iter_time: 0.184s, data_time: 0.002s, total_loss: 12.9, iou_loss: 4.6, l1_loss: 2.1, conf_loss: 5.1, cls_loss: 1.1, lr: 7.744e-05, size: 96, ETA: 4:04:32
2024-02-05 23:18:22 | INFO     | yolox.core.trainer:261 - epoch: 1/100, iter: 230/250, mem: 4287Mb, iter_time: 1.219s, data_time: 0.415s, total_loss: 17.2, iou_loss: 4.5, l1_loss: 2.3, conf_loss: 9.1, cls_loss: 1.3, lr: 8.464e-05, size: 416, ETA: 4:15:41
2024-02-05 23:18:26 | INFO     | yolox.core.trainer:261 - epoch: 1/100, iter: 240/250, mem: 4287Mb, iter_time: 0.451s, data_time: 0.114s, total_loss: 15.0, iou_loss: 4.5, l1_loss: 2.5, conf_loss: 6.9, cls_loss: 1.2, lr: 9.216e-05, size: 256, ETA: 4:12:41
2024-02-05 23:18:31 | INFO     | yolox.core.trainer:261 - epoch: 1/100, iter: 250/250, mem: 4287Mb, iter_time: 0.482s, data_time: 0.001s, total_loss: 15.6, iou_loss: 4.4, l1_loss: 2.4, conf_loss: 7.5, cls_loss: 1.3, lr: 1.000e-04, size: 352, ETA: 4:10:26
2024-02-05 23:18:31 | INFO     | yolox.core.trainer:363 - Save weights to ./YOLOX_outputs/yolox_s
2024-02-05 23:18:32 | INFO     | yolox.core.trainer:203 - ---> start train epoch2
2024-02-05 23:18:38 | INFO     | yolox.core.trainer:261 - epoch: 2/100, iter: 10/250, mem: 4287Mb, iter_time: 0.677s, data_time: 0.141s, total_loss: 16.6, iou_loss: 4.4, l1_loss: 3.0, conf_loss: 8.0, cls_loss: 1.2, lr: 1.082e-04, size: 384, ETA: 4:11:27
2024-02-05 23:18:40 | INFO     | yolox.core.trainer:261 - epoch: 2/100, iter: 20/250, mem: 4287Mb, iter_time: 0.203s, data_time: 0.001s, total_loss: 13.0, iou_loss: 4.5, l1_loss: 2.3, conf_loss: 5.0, cls_loss: 1.1, lr: 1.166e-04, size: 96, ETA: 4:05:08
2024-02-05 23:18:50 | INFO     | yolox.core.trainer:261 - epoch: 2/100, iter: 30/250, mem: 4287Mb, iter_time: 0.971s, data_time: 0.404s, total_loss: 16.9, iou_loss: 4.4, l1_loss: 2.5, conf_loss: 8.7, cls_loss: 1.3, lr: 1.254e-04, size: 384, ETA: 4:10:34
2024-02-05 23:18:55 | INFO     | yolox.core.trainer:261 - epoch: 2/100, iter: 40/250, mem: 4287Mb, iter_time: 0.502s, data_time: 0.256s, total_loss: 13.1, iou_loss: 4.3, l1_loss: 2.2, conf_loss: 5.3, cls_loss: 1.3, lr: 1.346e-04, size: 160, ETA: 4:08:57
2024-02-05 23:19:00 | INFO     | yolox.core.trainer:261 - epoch: 2/100, iter: 50/250, mem: 4287Mb, iter_time: 0.441s, data_time: 0.001s, total_loss: 13.2, iou_loss: 4.3, l1_loss: 2.0, conf_loss: 5.6, cls_loss: 1.4, lr: 1.440e-04, size: 224, ETA: 4:06:37
2024-02-05 23:19:07 | INFO     | yolox.core.trainer:261 - epoch: 2/100, iter: 60/250, mem: 4287Mb, iter_time: 0.693s, data_time: 0.385s, total_loss: 13.2, iou_loss: 4.2, l1_loss: 2.3, conf_loss: 5.4, cls_loss: 1.3, lr: 1.538e-04, size: 224, ETA: 4:07:46
2024-02-05 23:19:15 | INFO     | yolox.core.trainer:261 - epoch: 2/100, iter: 70/250, mem: 4287Mb, iter_time: 0.825s, data_time: 0.275s, total_loss: 14.8, iou_loss: 4.1, l1_loss: 2.5, conf_loss: 6.8, cls_loss: 1.4, lr: 1.638e-04, size: 384, ETA: 4:10:32
2024-02-05 23:19:17 | INFO     | yolox.core.trainer:261 - epoch: 2/100, iter: 80/250, mem: 4287Mb, iter_time: 0.231s, data_time: 0.001s, total_loss: 12.6, iou_loss: 4.2, l1_loss: 2.0, conf_loss: 5.0, cls_loss: 1.4, lr: 1.742e-04, size: 160, ETA: 4:05:43
2024-02-05 23:19:25 | INFO     | yolox.core.trainer:261 - epoch: 2/100, iter: 90/250, mem: 4287Mb, iter_time: 0.763s, data_time: 0.539s, total_loss: 12.5, iou_loss: 4.4, l1_loss: 2.1, conf_loss: 4.9, cls_loss: 1.2, lr: 1.850e-04, size: 96, ETA: 4:07:37
2024-02-05 23:19:28 | INFO     | yolox.core.trainer:261 - epoch: 2/100, iter: 100/250, mem: 4287Mb, iter_time: 0.318s, data_time: 0.001s, total_loss: 13.3, iou_loss: 4.2, l1_loss: 2.1, conf_loss: 5.5, cls_loss: 1.4, lr: 1.960e-04, size: 256, ETA: 4:04:11
2024-02-05 23:19:39 | INFO     | yolox.core.trainer:261 - epoch: 2/100, iter: 110/250, mem: 4287Mb, iter_time: 1.127s, data_time: 0.508s, total_loss: 13.4, iou_loss: 4.0, l1_loss: 2.3, conf_loss: 5.7, cls_loss: 1.4, lr: 2.074e-04, size: 352, ETA: 4:10:10
2024-02-05 23:19:48 | INFO     | yolox.core.trainer:261 - epoch: 2/100, iter: 120/250, mem: 4287Mb, iter_time: 0.844s, data_time: 0.423s, total_loss: 13.0, iou_loss: 4.1, l1_loss: 2.2, conf_loss: 5.3, cls_loss: 1.4, lr: 2.190e-04, size: 288, ETA: 4:12:40
2024-02-05 23:19:50 | INFO     | yolox.core.trainer:261 - epoch: 2/100, iter: 130/250, mem: 4287Mb, iter_time: 0.243s, data_time: 0.001s, total_loss: 12.3, iou_loss: 4.1, l1_loss: 2.0, conf_loss: 4.8, cls_loss: 1.4, lr: 2.310e-04, size: 192, ETA: 4:08:32
2024-02-05 23:19:58 | INFO     | yolox.core.trainer:261 - epoch: 2/100, iter: 140/250, mem: 4287Mb, iter_time: 0.822s, data_time: 0.496s, total_loss: 11.9, iou_loss: 4.0, l1_loss: 2.1, conf_loss: 4.5, cls_loss: 1.2, lr: 2.434e-04, size: 224, ETA: 4:10:43
2024-02-05 23:20:07 | INFO     | yolox.core.trainer:261 - epoch: 2/100, iter: 150/250, mem: 4287Mb, iter_time: 0.848s, data_time: 0.280s, total_loss: 13.5, iou_loss: 3.9, l1_loss: 2.7, conf_loss: 5.5, cls_loss: 1.4, lr: 2.560e-04, size: 384, ETA: 4:13:02
2024-02-05 23:20:11 | INFO     | yolox.core.trainer:261 - epoch: 2/100, iter: 160/250, mem: 4287Mb, iter_time: 0.388s, data_time: 0.001s, total_loss: 13.2, iou_loss: 4.0, l1_loss: 2.3, conf_loss: 5.5, cls_loss: 1.4, lr: 2.690e-04, size: 288, ETA: 4:10:39
2024-02-05 23:20:19 | INFO     | yolox.core.trainer:261 - epoch: 2/100, iter: 170/250, mem: 4287Mb, iter_time: 0.807s, data_time: 0.294s, total_loss: 13.0, iou_loss: 3.9, l1_loss: 2.2, conf_loss: 5.6, cls_loss: 1.3, lr: 2.822e-04, size: 352, ETA: 4:12:27
2024-02-05 23:20:26 | INFO     | yolox.core.trainer:261 - epoch: 2/100, iter: 180/250, mem: 4287Mb, iter_time: 0.702s, data_time: 0.001s, total_loss: 13.2, iou_loss: 3.7, l1_loss: 2.3, conf_loss: 5.8, cls_loss: 1.4, lr: 2.958e-04, size: 416, ETA: 4:13:09
2024-02-05 23:20:29 | INFO     | yolox.core.trainer:261 - epoch: 2/100, iter: 190/250, mem: 4287Mb, iter_time: 0.325s, data_time: 0.020s, total_loss: 11.8, iou_loss: 3.9, l1_loss: 2.0, conf_loss: 4.6, cls_loss: 1.3, lr: 3.098e-04, size: 224, ETA: 4:10:19
2024-02-05 23:20:37 | INFO     | yolox.core.trainer:261 - epoch: 2/100, iter: 200/250, mem: 4287Mb, iter_time: 0.823s, data_time: 0.469s, total_loss: 12.0, iou_loss: 3.9, l1_loss: 2.2, conf_loss: 4.7, cls_loss: 1.2, lr: 3.240e-04, size: 256, ETA: 4:12:08
2024-02-05 23:20:40 | INFO     | yolox.core.trainer:261 - epoch: 2/100, iter: 210/250, mem: 4287Mb, iter_time: 0.255s, data_time: 0.001s, total_loss: 11.6, iou_loss: 4.0, l1_loss: 2.1, conf_loss: 4.3, cls_loss: 1.3, lr: 3.386e-04, size: 192, ETA: 4:08:50
2024-02-05 23:20:48 | INFO     | yolox.core.trainer:261 - epoch: 2/100, iter: 220/250, mem: 4287Mb, iter_time: 0.807s, data_time: 0.555s, total_loss: 10.8, iou_loss: 3.9, l1_loss: 1.9, conf_loss: 3.8, cls_loss: 1.2, lr: 3.534e-04, size: 160, ETA: 4:10:28
2024-02-05 23:20:56 | INFO     | yolox.core.trainer:261 - epoch: 2/100, iter: 230/250, mem: 4287Mb, iter_time: 0.797s, data_time: 0.490s, total_loss: 11.6, iou_loss: 3.9, l1_loss: 2.0, conf_loss: 4.4, cls_loss: 1.3, lr: 3.686e-04, size: 224, ETA: 4:11:55
2024-02-05 23:21:00 | INFO     | yolox.core.trainer:261 - epoch: 2/100, iter: 240/250, mem: 4287Mb, iter_time: 0.372s, data_time: 0.001s, total_loss: 11.8, iou_loss: 3.7, l1_loss: 2.0, conf_loss: 4.8, cls_loss: 1.3, lr: 3.842e-04, size: 288, ETA: 4:09:47
2024-02-05 23:21:09 | INFO     | yolox.core.trainer:261 - epoch: 2/100, iter: 250/250, mem: 4287Mb, iter_time: 0.964s, data_time: 0.209s, total_loss: 13.0, iou_loss: 3.7, l1_loss: 2.2, conf_loss: 5.8, cls_loss: 1.4, lr: 4.000e-04, size: 416, ETA: 4:12:34
2024-02-05 23:21:09 | INFO     | yolox.core.trainer:363 - Save weights to ./YOLOX_outputs/yolox_s
2024-02-05 23:21:10 | INFO     | yolox.core.trainer:203 - ---> start train epoch3
2024-02-05 23:21:12 | INFO     | yolox.core.trainer:261 - epoch: 3/100, iter: 10/250, mem: 4287Mb, iter_time: 0.213s, data_time: 0.001s, total_loss: 11.6, iou_loss: 4.2, l1_loss: 1.9, conf_loss: 4.4, cls_loss: 1.2, lr: 4.162e-04, size: 96, ETA: 4:09:13
2024-02-05 23:21:22 | INFO     | yolox.core.trainer:261 - epoch: 3/100, iter: 20/250, mem: 4287Mb, iter_time: 1.001s, data_time: 0.259s, total_loss: 12.7, iou_loss: 3.7, l1_loss: 2.3, conf_loss: 5.5, cls_loss: 1.3, lr: 4.326e-04, size: 416, ETA: 4:12:10
2024-02-05 23:21:26 | INFO     | yolox.core.trainer:261 - epoch: 3/100, iter: 30/250, mem: 4287Mb, iter_time: 0.419s, data_time: 0.227s, total_loss: 11.8, iou_loss: 4.2, l1_loss: 1.9, conf_loss: 4.5, cls_loss: 1.2, lr: 4.494e-04, size: 96, ETA: 4:10:32
2024-02-05 23:21:29 | INFO     | yolox.core.trainer:261 - epoch: 3/100, iter: 40/250, mem: 4287Mb, iter_time: 0.290s, data_time: 0.002s, total_loss: 11.3, iou_loss: 3.8, l1_loss: 2.0, conf_loss: 4.2, cls_loss: 1.2, lr: 4.666e-04, size: 224, ETA: 4:07:59
2024-02-05 23:21:37 | INFO     | yolox.core.trainer:261 - epoch: 3/100, iter: 50/250, mem: 4287Mb, iter_time: 0.811s, data_time: 0.536s, total_loss: 11.4, iou_loss: 4.0, l1_loss: 2.1, conf_loss: 4.2, cls_loss: 1.1, lr: 4.840e-04, size: 192, ETA: 4:09:23
2024-02-05 23:21:45 | INFO     | yolox.core.trainer:261 - epoch: 3/100, iter: 60/250, mem: 4287Mb, iter_time: 0.798s, data_time: 0.566s, total_loss: 11.1, iou_loss: 3.9, l1_loss: 1.8, conf_loss: 4.2, cls_loss: 1.2, lr: 5.018e-04, size: 160, ETA: 4:10:38
2024-02-05 23:21:50 | INFO     | yolox.core.trainer:261 - epoch: 3/100, iter: 70/250, mem: 4287Mb, iter_time: 0.472s, data_time: 0.001s, total_loss: 12.3, iou_loss: 3.7, l1_loss: 2.1, conf_loss: 5.3, cls_loss: 1.1, lr: 5.198e-04, size: 352, ETA: 4:09:31
2024-02-05 23:21:58 | INFO     | yolox.core.trainer:261 - epoch: 3/100, iter: 80/250, mem: 4287Mb, iter_time: 0.750s, data_time: 0.266s, total_loss: 12.4, iou_loss: 3.6, l1_loss: 1.9, conf_loss: 5.8, cls_loss: 1.2, lr: 5.382e-04, size: 352, ETA: 4:10:22
2024-02-05 23:22:00 | INFO     | yolox.core.trainer:261 - epoch: 3/100, iter: 90/250, mem: 4287Mb, iter_time: 0.198s, data_time: 0.001s, total_loss: 11.1, iou_loss: 3.9, l1_loss: 1.9, conf_loss: 4.2, cls_loss: 1.1, lr: 5.570e-04, size: 128, ETA: 4:07:24
2024-02-05 23:22:07 | INFO     | yolox.core.trainer:261 - epoch: 3/100, iter: 100/250, mem: 4287Mb, iter_time: 0.743s, data_time: 0.486s, total_loss: inf, iou_loss: 3.7, l1_loss: inf, conf_loss: 3.9, cls_loss: 1.1, lr: 5.760e-04, size: 160, ETA: 4:08:12
2024-02-05 23:22:16 | INFO     | yolox.core.trainer:261 - epoch: 3/100, iter: 110/250, mem: 4287Mb, iter_time: 0.858s, data_time: 0.463s, total_loss: 11.5, iou_loss: 3.6, l1_loss: 2.0, conf_loss: 4.8, cls_loss: 1.1, lr: 5.954e-04, size: 288, ETA: 4:09:45
2024-02-05 23:22:23 | INFO     | yolox.core.trainer:261 - epoch: 3/100, iter: 120/250, mem: 4287Mb, iter_time: 0.714s, data_time: 0.001s, total_loss: 12.1, iou_loss: 3.6, l1_loss: 2.1, conf_loss: 5.3, cls_loss: 1.1, lr: 6.150e-04, size: 416, ETA: 4:10:18
2024-02-05 23:22:28 | INFO     | yolox.core.trainer:261 - epoch: 3/100, iter: 130/250, mem: 4287Mb, iter_time: 0.526s, data_time: 0.014s, total_loss: 11.5, iou_loss: 3.6, l1_loss: 2.1, conf_loss: 4.7, cls_loss: 1.1, lr: 6.350e-04, size: 352, ETA: 4:09:37
2024-02-05 23:22:36 | INFO     | yolox.core.trainer:261 - epoch: 3/100, iter: 140/250, mem: 4287Mb, iter_time: 0.779s, data_time: 0.357s, total_loss: 11.1, iou_loss: 3.6, l1_loss: 1.8, conf_loss: 4.5, cls_loss: 1.2, lr: 6.554e-04, size: 288, ETA: 4:10:34
2024-02-05 23:22:40 | INFO     | yolox.core.trainer:261 - epoch: 3/100, iter: 150/250, mem: 4287Mb, iter_time: 0.427s, data_time: 0.001s, total_loss: 11.8, iou_loss: 3.5, l1_loss: 1.9, conf_loss: 5.2, cls_loss: 1.2, lr: 6.760e-04, size: 320, ETA: 4:09:16
2024-02-05 23:22:46 | INFO     | yolox.core.trainer:261 - epoch: 3/100, iter: 160/250, mem: 4287Mb, iter_time: 0.601s, data_time: 0.352s, total_loss: 10.4, iou_loss: 3.7, l1_loss: 1.7, conf_loss: 3.9, cls_loss: 1.1, lr: 6.970e-04, size: 128, ETA: 4:09:05
2024-02-05 23:22:50 | INFO     | yolox.core.trainer:261 - epoch: 3/100, iter: 170/250, mem: 4287Mb, iter_time: 0.398s, data_time: 0.015s, total_loss: 11.9, iou_loss: 3.7, l1_loss: 2.1, conf_loss: 4.6, cls_loss: 1.4, lr: 7.182e-04, size: 288, ETA: 4:07:41
2024-02-05 23:22:58 | INFO     | yolox.core.trainer:261 - epoch: 3/100, iter: 180/250, mem: 4287Mb, iter_time: 0.736s, data_time: 0.381s, total_loss: 11.0, iou_loss: 3.6, l1_loss: 1.9, conf_loss: 4.3, cls_loss: 1.2, lr: 7.398e-04, size: 256, ETA: 4:08:19
2024-02-05 23:23:07 | INFO     | yolox.core.trainer:261 - epoch: 3/100, iter: 190/250, mem: 4287Mb, iter_time: 0.894s, data_time: 0.183s, total_loss: 11.9, iou_loss: 3.5, l1_loss: 1.9, conf_loss: 5.2, cls_loss: 1.3, lr: 7.618e-04, size: 416, ETA: 4:09:52
2024-02-05 23:23:11 | INFO     | yolox.core.trainer:261 - epoch: 3/100, iter: 200/250, mem: 4287Mb, iter_time: 0.472s, data_time: 0.001s, total_loss: 11.3, iou_loss: 3.5, l1_loss: 1.9, conf_loss: 4.6, cls_loss: 1.3, lr: 7.840e-04, size: 352, ETA: 4:08:56
2024-02-05 23:23:17 | INFO     | yolox.core.trainer:261 - epoch: 3/100, iter: 210/250, mem: 4287Mb, iter_time: 0.624s, data_time: 0.185s, total_loss: 10.8, iou_loss: 3.4, l1_loss: 1.6, conf_loss: 4.6, cls_loss: 1.2, lr: 8.066e-04, size: 320, ETA: 4:08:53
2024-02-05 23:23:25 | INFO     | yolox.core.trainer:261 - epoch: 3/100, iter: 220/250, mem: 4287Mb, iter_time: 0.703s, data_time: 0.358s, total_loss: 10.9, iou_loss: 3.5, l1_loss: 1.7, conf_loss: 4.4, cls_loss: 1.3, lr: 8.294e-04, size: 256, ETA: 4:09:17
2024-02-05 23:23:29 | INFO     | yolox.core.trainer:261 - epoch: 3/100, iter: 230/250, mem: 4287Mb, iter_time: 0.476s, data_time: 0.001s, total_loss: 11.6, iou_loss: 3.5, l1_loss: 1.9, conf_loss: 5.0, cls_loss: 1.2, lr: 8.526e-04, size: 352, ETA: 4:08:24
2024-02-05 23:23:37 | INFO     | yolox.core.trainer:261 - epoch: 3/100, iter: 240/250, mem: 4287Mb, iter_time: 0.799s, data_time: 0.084s, total_loss: 11.2, iou_loss: 3.3, l1_loss: 1.9, conf_loss: 4.8, cls_loss: 1.2, lr: 8.762e-04, size: 416, ETA: 4:09:18
2024-02-05 23:23:40 | INFO     | yolox.core.trainer:261 - epoch: 3/100, iter: 250/250, mem: 4287Mb, iter_time: 0.295s, data_time: 0.001s, total_loss: 10.7, iou_loss: 3.6, l1_loss: 1.9, conf_loss: 4.1, cls_loss: 1.2, lr: 9.000e-04, size: 224, ETA: 4:07:28
2024-02-05 23:23:40 | INFO     | yolox.core.trainer:363 - Save weights to ./YOLOX_outputs/yolox_s
2024-02-05 23:23:41 | INFO     | yolox.core.trainer:203 - ---> start train epoch4
2024-02-05 23:23:47 | INFO     | yolox.core.trainer:261 - epoch: 4/100, iter: 10/250, mem: 4287Mb, iter_time: 0.570s, data_time: 0.333s, total_loss: 10.4, iou_loss: 3.9, l1_loss: 1.8, conf_loss: 3.6, cls_loss: 1.2, lr: 9.242e-04, size: 128, ETA: 4:07:09
2024-02-05 23:23:55 | INFO     | yolox.core.trainer:261 - epoch: 4/100, iter: 20/250, mem: 4287Mb, iter_time: 0.868s, data_time: 0.510s, total_loss: 10.7, iou_loss: 3.5, l1_loss: 1.7, conf_loss: 4.2, cls_loss: 1.3, lr: 9.486e-04, size: 256, ETA: 4:08:23
2024-02-05 23:23:57 | INFO     | yolox.core.trainer:261 - epoch: 4/100, iter: 30/250, mem: 4287Mb, iter_time: 0.196s, data_time: 0.001s, total_loss: 10.2, iou_loss: 3.9, l1_loss: 1.8, conf_loss: 3.5, cls_loss: 1.0, lr: 9.734e-04, size: 96, ETA: 4:06:07
2024-02-05 23:24:09 | INFO     | yolox.core.trainer:261 - epoch: 4/100, iter: 40/250, mem: 4287Mb, iter_time: 1.158s, data_time: 0.422s, total_loss: 11.2, iou_loss: 3.4, l1_loss: 1.7, conf_loss: 4.7, cls_loss: 1.3, lr: 9.986e-04, size: 416, ETA: 4:08:49
2024-02-05 23:24:14 | INFO     | yolox.core.trainer:261 - epoch: 4/100, iter: 50/250, mem: 4287Mb, iter_time: 0.527s, data_time: 0.263s, total_loss: 10.3, iou_loss: 3.6, l1_loss: 1.5, conf_loss: 3.9, cls_loss: 1.1, lr: 1.024e-03, size: 192, ETA: 4:08:15
2024-02-05 23:24:18 | INFO     | yolox.core.trainer:261 - epoch: 4/100, iter: 60/250, mem: 4287Mb, iter_time: 0.414s, data_time: 0.036s, total_loss: 10.5, iou_loss: 3.5, l1_loss: 1.7, conf_loss: 4.1, cls_loss: 1.2, lr: 1.050e-03, size: 288, ETA: 4:07:09
2024-02-05 23:24:27 | INFO     | yolox.core.trainer:261 - epoch: 4/100, iter: 70/250, mem: 4287Mb, iter_time: 0.855s, data_time: 0.285s, total_loss: 10.8, iou_loss: 3.4, l1_loss: 1.8, conf_loss: 4.4, cls_loss: 1.2, lr: 1.076e-03, size: 384, ETA: 4:08:14
2024-02-05 23:24:30 | INFO     | yolox.core.trainer:261 - epoch: 4/100, iter: 80/250, mem: 4287Mb, iter_time: 0.333s, data_time: 0.001s, total_loss: 9.9, iou_loss: 3.4, l1_loss: 1.6, conf_loss: 3.7, cls_loss: 1.2, lr: 1.102e-03, size: 256, ETA: 4:06:46
2024-02-05 23:24:37 | INFO     | yolox.core.trainer:261 - epoch: 4/100, iter: 90/250, mem: 4287Mb, iter_time: 0.652s, data_time: 0.400s, total_loss: 10.0, iou_loss: 3.6, l1_loss: 1.7, conf_loss: 3.5, cls_loss: 1.2, lr: 1.129e-03, size: 160, ETA: 4:06:51
2024-02-05 23:24:46 | INFO     | yolox.core.trainer:261 - epoch: 4/100, iter: 100/250, mem: 4287Mb, iter_time: 0.895s, data_time: 0.544s, total_loss: 10.1, iou_loss: 3.6, l1_loss: 1.7, conf_loss: 3.8, cls_loss: 1.1, lr: 1.156e-03, size: 256, ETA: 4:08:05
2024-02-05 23:24:48 | INFO     | yolox.core.trainer:261 - epoch: 4/100, iter: 110/250, mem: 4287Mb, iter_time: 0.198s, data_time: 0.001s, total_loss: 10.2, iou_loss: 3.8, l1_loss: 1.7, conf_loss: 3.5, cls_loss: 1.1, lr: 1.183e-03, size: 96, ETA: 4:06:01
2024-02-05 23:24:56 | INFO     | yolox.core.trainer:261 - epoch: 4/100, iter: 120/250, mem: 4287Mb, iter_time: 0.848s, data_time: 0.592s, total_loss: 10.1, iou_loss: 3.7, l1_loss: 1.6, conf_loss: 3.6, cls_loss: 1.2, lr: 1.211e-03, size: 160, ETA: 4:07:01
2024-02-05 23:25:04 | INFO     | yolox.core.trainer:261 - epoch: 4/100, iter: 130/250, mem: 4287Mb, iter_time: 0.790s, data_time: 0.339s, total_loss: 9.9, iou_loss: 3.2, l1_loss: 1.5, conf_loss: 4.1, cls_loss: 1.1, lr: 1.239e-03, size: 320, ETA: 4:07:43
2024-02-05 23:25:08 | INFO     | yolox.core.trainer:261 - epoch: 4/100, iter: 140/250, mem: 4287Mb, iter_time: 0.355s, data_time: 0.024s, total_loss: 10.2, iou_loss: 3.5, l1_loss: 1.6, conf_loss: 3.9, cls_loss: 1.2, lr: 1.267e-03, size: 256, ETA: 4:06:26
2024-02-05 23:25:15 | INFO     | yolox.core.trainer:261 - epoch: 4/100, iter: 150/250, mem: 4287Mb, iter_time: 0.754s, data_time: 0.511s, total_loss: 9.8, iou_loss: 3.8, l1_loss: 1.6, conf_loss: 3.3, cls_loss: 1.0, lr: 1.296e-03, size: 128, ETA: 4:06:58
2024-02-05 23:25:23 | INFO     | yolox.core.trainer:261 - epoch: 4/100, iter: 160/250, mem: 4287Mb, iter_time: 0.722s, data_time: 0.001s, total_loss: 11.0, iou_loss: 3.4, l1_loss: 1.7, conf_loss: 4.8, cls_loss: 1.1, lr: 1.325e-03, size: 416, ETA: 4:07:20
2024-02-05 23:25:30 | INFO     | yolox.core.trainer:261 - epoch: 4/100, iter: 170/250, mem: 4287Mb, iter_time: 0.727s, data_time: 0.020s, total_loss: 10.5, iou_loss: 3.2, l1_loss: 1.6, conf_loss: 4.5, cls_loss: 1.2, lr: 1.354e-03, size: 416, ETA: 4:07:43
2024-02-05 23:25:35 | INFO     | yolox.core.trainer:261 - epoch: 4/100, iter: 180/250, mem: 4287Mb, iter_time: 0.513s, data_time: 0.263s, total_loss: 9.4, iou_loss: 3.5, l1_loss: 1.4, conf_loss: 3.5, cls_loss: 1.0, lr: 1.384e-03, size: 192, ETA: 4:07:09
2024-02-05 23:25:38 | INFO     | yolox.core.trainer:261 - epoch: 4/100, iter: 190/250, mem: 4287Mb, iter_time: 0.297s, data_time: 0.019s, total_loss: 9.8, iou_loss: 3.4, l1_loss: 1.5, conf_loss: 3.7, cls_loss: 1.2, lr: 1.414e-03, size: 224, ETA: 4:05:42
2024-02-05 23:25:46 | INFO     | yolox.core.trainer:261 - epoch: 4/100, iter: 200/250, mem: 4287Mb, iter_time: 0.858s, data_time: 0.427s, total_loss: 10.1, iou_loss: 3.3, l1_loss: 1.7, conf_loss: 3.9, cls_loss: 1.3, lr: 1.444e-03, size: 320, ETA: 4:06:38
2024-02-05 23:25:53 | INFO     | yolox.core.trainer:261 - epoch: 4/100, iter: 210/250, mem: 4287Mb, iter_time: 0.694s, data_time: 0.482s, total_loss: 9.6, iou_loss: 3.8, l1_loss: 1.5, conf_loss: 3.3, cls_loss: 1.0, lr: 1.475e-03, size: 96, ETA: 4:06:51
2024-02-05 23:25:56 | INFO     | yolox.core.trainer:261 - epoch: 4/100, iter: 220/250, mem: 4287Mb, iter_time: 0.262s, data_time: 0.054s, total_loss: 9.2, iou_loss: 3.6, l1_loss: 1.5, conf_loss: 3.1, cls_loss: 0.9, lr: 1.505e-03, size: 128, ETA: 4:05:17
2024-02-05 23:26:06 | INFO     | yolox.core.trainer:261 - epoch: 4/100, iter: 230/250, mem: 4287Mb, iter_time: 0.946s, data_time: 0.442s, total_loss: 9.7, iou_loss: 3.2, l1_loss: 1.5, conf_loss: 3.9, cls_loss: 1.1, lr: 1.537e-03, size: 352, ETA: 4:06:33
2024-02-05 23:26:10 | INFO     | yolox.core.trainer:261 - epoch: 4/100, iter: 240/250, mem: 4287Mb, iter_time: 0.427s, data_time: 0.001s, total_loss: 10.1, iou_loss: 3.3, l1_loss: 1.5, conf_loss: 4.1, cls_loss: 1.1, lr: 1.568e-03, size: 320, ETA: 4:05:41
2024-02-05 23:26:16 | INFO     | yolox.core.trainer:261 - epoch: 4/100, iter: 250/250, mem: 4287Mb, iter_time: 0.629s, data_time: 0.273s, total_loss: 9.9, iou_loss: 3.3, l1_loss: 1.5, conf_loss: 4.0, cls_loss: 1.1, lr: 1.600e-03, size: 256, ETA: 4:05:39
2024-02-05 23:26:16 | INFO     | yolox.core.trainer:363 - Save weights to ./YOLOX_outputs/yolox_s
2024-02-05 23:26:17 | INFO     | yolox.core.trainer:203 - ---> start train epoch5
2024-02-05 23:26:25 | INFO     | yolox.core.trainer:261 - epoch: 5/100, iter: 10/250, mem: 4287Mb, iter_time: 0.785s, data_time: 0.213s, total_loss: 9.9, iou_loss: 3.2, l1_loss: 1.7, conf_loss: 3.8, cls_loss: 1.1, lr: 1.632e-03, size: 384, ETA: 4:06:13
2024-02-05 23:26:27 | INFO     | yolox.core.trainer:261 - epoch: 5/100, iter: 20/250, mem: 4287Mb, iter_time: 0.210s, data_time: 0.001s, total_loss: 9.9, iou_loss: 3.8, l1_loss: 1.6, conf_loss: 3.5, cls_loss: 1.0, lr: 1.665e-03, size: 96, ETA: 4:04:31
2024-02-05 23:26:37 | INFO     | yolox.core.trainer:261 - epoch: 5/100, iter: 30/250, mem: 4287Mb, iter_time: 0.967s, data_time: 0.388s, total_loss: 9.5, iou_loss: 3.1, l1_loss: 1.5, conf_loss: 3.9, cls_loss: 1.0, lr: 1.697e-03, size: 384, ETA: 4:05:48
2024-02-05 23:26:43 | INFO     | yolox.core.trainer:261 - epoch: 5/100, iter: 40/250, mem: 4287Mb, iter_time: 0.597s, data_time: 0.333s, total_loss: 9.1, iou_loss: 3.4, l1_loss: 1.4, conf_loss: 3.2, cls_loss: 1.0, lr: 1.731e-03, size: 160, ETA: 4:05:38
2024-02-05 23:26:45 | INFO     | yolox.core.trainer:261 - epoch: 5/100, iter: 50/250, mem: 4287Mb, iter_time: 0.260s, data_time: 0.024s, total_loss: 8.9, iou_loss: 3.3, l1_loss: 1.4, conf_loss: 3.1, cls_loss: 1.1, lr: 1.764e-03, size: 160, ETA: 4:04:10
2024-02-05 23:26:53 | INFO     | yolox.core.trainer:261 - epoch: 5/100, iter: 60/250, mem: 4287Mb, iter_time: 0.801s, data_time: 0.518s, total_loss: 8.4, iou_loss: 3.2, l1_loss: 1.3, conf_loss: 2.9, cls_loss: 1.0, lr: 1.798e-03, size: 192, ETA: 4:04:47
2024-02-05 23:26:57 | INFO     | yolox.core.trainer:261 - epoch: 5/100, iter: 70/250, mem: 4287Mb, iter_time: 0.394s, data_time: 0.016s, total_loss: 9.2, iou_loss: 3.2, l1_loss: 1.4, conf_loss: 3.3, cls_loss: 1.2, lr: 1.832e-03, size: 288, ETA: 4:03:52
2024-02-05 23:27:06 | INFO     | yolox.core.trainer:261 - epoch: 5/100, iter: 80/250, mem: 4287Mb, iter_time: 0.928s, data_time: 0.367s, total_loss: 10.0, iou_loss: 3.2, l1_loss: 1.6, conf_loss: 4.0, cls_loss: 1.1, lr: 1.866e-03, size: 384, ETA: 4:04:56
2024-02-05 23:27:12 | INFO     | yolox.core.trainer:261 - epoch: 5/100, iter: 90/250, mem: 4287Mb, iter_time: 0.572s, data_time: 0.320s, total_loss: 8.9, iou_loss: 3.4, l1_loss: 1.3, conf_loss: 3.1, cls_loss: 1.1, lr: 1.901e-03, size: 160, ETA: 4:04:40
2024-02-05 23:27:16 | INFO     | yolox.core.trainer:261 - epoch: 5/100, iter: 100/250, mem: 4287Mb, iter_time: 0.431s, data_time: 0.007s, total_loss: 9.1, iou_loss: 3.1, l1_loss: 1.4, conf_loss: 3.6, cls_loss: 1.0, lr: 1.936e-03, size: 320, ETA: 4:03:54
2024-02-05 23:27:24 | INFO     | yolox.core.trainer:261 - epoch: 5/100, iter: 110/250, mem: 4287Mb, iter_time: 0.733s, data_time: 0.335s, total_loss: 9.6, iou_loss: 3.2, l1_loss: 1.5, conf_loss: 3.7, cls_loss: 1.2, lr: 1.971e-03, size: 288, ETA: 4:04:14
2024-02-05 23:27:31 | INFO     | yolox.core.trainer:261 - epoch: 5/100, iter: 120/250, mem: 4287Mb, iter_time: 0.762s, data_time: 0.200s, total_loss: 9.9, iou_loss: 3.2, l1_loss: 1.6, conf_loss: 3.7, cls_loss: 1.3, lr: 2.007e-03, size: 384, ETA: 4:04:40
2024-02-05 23:27:39 | INFO     | yolox.core.trainer:261 - epoch: 5/100, iter: 130/250, mem: 4287Mb, iter_time: 0.715s, data_time: 0.001s, total_loss: 9.3, iou_loss: 3.1, l1_loss: 1.5, conf_loss: 3.6, cls_loss: 1.1, lr: 2.043e-03, size: 416, ETA: 4:04:55
2024-02-05 23:27:42 | INFO     | yolox.core.trainer:261 - epoch: 5/100, iter: 140/250, mem: 4287Mb, iter_time: 0.339s, data_time: 0.101s, total_loss: 9.1, iou_loss: 3.4, l1_loss: 1.4, conf_loss: 3.2, cls_loss: 1.1, lr: 2.079e-03, size: 160, ETA: 4:03:51
2024-02-05 23:27:47 | INFO     | yolox.core.trainer:261 - epoch: 5/100, iter: 150/250, mem: 4287Mb, iter_time: 0.475s, data_time: 0.053s, total_loss: 9.6, iou_loss: 3.1, l1_loss: 1.5, conf_loss: 3.8, cls_loss: 1.2, lr: 2.116e-03, size: 320, ETA: 4:03:16
2024-02-05 23:27:55 | INFO     | yolox.core.trainer:261 - epoch: 5/100, iter: 160/250, mem: 4287Mb, iter_time: 0.869s, data_time: 0.312s, total_loss: 9.3, iou_loss: 3.1, l1_loss: 1.5, conf_loss: 3.5, cls_loss: 1.1, lr: 2.153e-03, size: 384, ETA: 4:04:03
2024-02-05 23:28:01 | INFO     | yolox.core.trainer:261 - epoch: 5/100, iter: 170/250, mem: 4287Mb, iter_time: 0.589s, data_time: 0.159s, total_loss: 8.6, iou_loss: 3.1, l1_loss: 1.4, conf_loss: 3.0, cls_loss: 1.1, lr: 2.190e-03, size: 320, ETA: 4:03:52
2024-02-05 23:28:05 | INFO     | yolox.core.trainer:261 - epoch: 5/100, iter: 180/250, mem: 4287Mb, iter_time: 0.384s, data_time: 0.005s, total_loss: 8.8, iou_loss: 3.2, l1_loss: 1.4, conf_loss: 3.1, cls_loss: 1.1, lr: 2.228e-03, size: 288, ETA: 4:02:59
2024-02-05 23:28:13 | INFO     | yolox.core.trainer:261 - epoch: 5/100, iter: 190/250, mem: 4287Mb, iter_time: 0.823s, data_time: 0.325s, total_loss: 9.3, iou_loss: 3.0, l1_loss: 1.5, conf_loss: 3.6, cls_loss: 1.1, lr: 2.266e-03, size: 352, ETA: 4:03:35
2024-02-05 23:28:20 | INFO     | yolox.core.trainer:261 - epoch: 5/100, iter: 200/250, mem: 4287Mb, iter_time: 0.664s, data_time: 0.264s, total_loss: 8.5, iou_loss: 3.1, l1_loss: 1.4, conf_loss: 3.0, cls_loss: 1.0, lr: 2.304e-03, size: 288, ETA: 4:03:39
2024-02-05 23:28:24 | INFO     | yolox.core.trainer:261 - epoch: 5/100, iter: 210/250, mem: 4287Mb, iter_time: 0.386s, data_time: 0.001s, total_loss: 8.8, iou_loss: 3.1, l1_loss: 1.4, conf_loss: 3.2, cls_loss: 1.1, lr: 2.343e-03, size: 288, ETA: 4:02:48
2024-02-05 23:28:32 | INFO     | yolox.core.trainer:261 - epoch: 5/100, iter: 220/250, mem: 4287Mb, iter_time: 0.831s, data_time: 0.264s, total_loss: 9.2, iou_loss: 3.2, l1_loss: 1.5, conf_loss: 3.5, cls_loss: 1.1, lr: 2.381e-03, size: 384, ETA: 4:03:25
2024-02-05 23:28:34 | INFO     | yolox.core.trainer:261 - epoch: 5/100, iter: 230/250, mem: 4287Mb, iter_time: 0.208s, data_time: 0.001s, total_loss: 8.7, iou_loss: 3.5, l1_loss: 1.3, conf_loss: 2.8, cls_loss: 1.1, lr: 2.421e-03, size: 128, ETA: 4:02:00
2024-02-05 23:28:42 | INFO     | yolox.core.trainer:261 - epoch: 5/100, iter: 240/250, mem: 4287Mb, iter_time: 0.746s, data_time: 0.516s, total_loss: 9.0, iou_loss: 3.7, l1_loss: 1.5, conf_loss: 2.8, cls_loss: 1.0, lr: 2.460e-03, size: 96, ETA: 4:02:20
2024-02-05 23:28:50 | INFO     | yolox.core.trainer:261 - epoch: 5/100, iter: 250/250, mem: 4287Mb, iter_time: 0.774s, data_time: 0.459s, total_loss: 9.8, iou_loss: 3.4, l1_loss: 1.5, conf_loss: 3.9, cls_loss: 1.1, lr: 2.500e-03, size: 224, ETA: 4:02:44
2024-02-05 23:28:50 | INFO     | yolox.core.trainer:363 - Save weights to ./YOLOX_outputs/yolox_s
2024-02-05 23:28:50 | INFO     | yolox.core.trainer:203 - ---> start train epoch6
2024-02-05 23:28:54 | INFO     | yolox.core.trainer:261 - epoch: 6/100, iter: 10/250, mem: 4287Mb, iter_time: 0.324s, data_time: 0.001s, total_loss: 9.2, iou_loss: 3.2, l1_loss: 1.5, conf_loss: 3.4, cls_loss: 1.1, lr: 2.500e-03, size: 256, ETA: 4:01:44
2024-02-05 23:29:01 | INFO     | yolox.core.trainer:261 - epoch: 6/100, iter: 20/250, mem: 4287Mb, iter_time: 0.723s, data_time: 0.374s, total_loss: 8.6, iou_loss: 3.1, l1_loss: 1.4, conf_loss: 3.1, cls_loss: 1.1, lr: 2.500e-03, size: 256, ETA: 4:01:59
2024-02-05 23:29:09 | INFO     | yolox.core.trainer:261 - epoch: 6/100, iter: 30/250, mem: 4287Mb, iter_time: 0.813s, data_time: 0.001s, total_loss: 9.4, iou_loss: 3.1, l1_loss: 1.6, conf_loss: 3.7, cls_loss: 1.0, lr: 2.500e-03, size: 416, ETA: 4:02:30
2024-02-05 23:29:13 | INFO     | yolox.core.trainer:261 - epoch: 6/100, iter: 40/250, mem: 4287Mb, iter_time: 0.421s, data_time: 0.001s, total_loss: 8.5, iou_loss: 3.0, l1_loss: 1.2, conf_loss: 3.2, cls_loss: 1.1, lr: 2.499e-03, size: 288, ETA: 4:01:48
2024-02-05 23:29:19 | INFO     | yolox.core.trainer:261 - epoch: 6/100, iter: 50/250, mem: 4287Mb, iter_time: 0.601s, data_time: 0.330s, total_loss: 9.2, iou_loss: 3.3, l1_loss: 1.5, conf_loss: 3.2, cls_loss: 1.2, lr: 2.499e-03, size: 192, ETA: 4:01:40
2024-02-05 23:29:23 | INFO     | yolox.core.trainer:261 - epoch: 6/100, iter: 60/250, mem: 4287Mb, iter_time: 0.335s, data_time: 0.053s, total_loss: 8.3, iou_loss: 3.1, l1_loss: 1.3, conf_loss: 2.9, cls_loss: 1.0, lr: 2.499e-03, size: 224, ETA: 4:00:44
2024-02-05 23:29:31 | INFO     | yolox.core.trainer:261 - epoch: 6/100, iter: 70/250, mem: 4287Mb, iter_time: 0.831s, data_time: 0.434s, total_loss: 8.7, iou_loss: 3.1, l1_loss: 1.3, conf_loss: 3.2, cls_loss: 1.1, lr: 2.498e-03, size: 288, ETA: 4:01:18
2024-02-05 23:29:38 | INFO     | yolox.core.trainer:261 - epoch: 6/100, iter: 80/250, mem: 4287Mb, iter_time: 0.718s, data_time: 0.417s, total_loss: 8.5, iou_loss: 3.2, l1_loss: 1.3, conf_loss: 2.9, cls_loss: 1.1, lr: 2.497e-03, size: 224, ETA: 4:01:30
2024-02-05 23:29:45 | INFO     | yolox.core.trainer:261 - epoch: 6/100, iter: 90/250, mem: 4287Mb, iter_time: 0.709s, data_time: 0.002s, total_loss: 9.6, iou_loss: 3.1, l1_loss: 1.5, conf_loss: 3.8, cls_loss: 1.2, lr: 2.497e-03, size: 416, ETA: 4:01:41
2024-02-05 23:29:49 | INFO     | yolox.core.trainer:261 - epoch: 6/100, iter: 100/250, mem: 4287Mb, iter_time: 0.428s, data_time: 0.219s, total_loss: 9.5, iou_loss: 3.7, l1_loss: 1.5, conf_loss: 3.2, cls_loss: 1.1, lr: 2.496e-03, size: 96, ETA: 4:01:03
2024-02-05 23:29:57 | INFO     | yolox.core.trainer:261 - epoch: 6/100, iter: 110/250, mem: 4287Mb, iter_time: 0.782s, data_time: 0.347s, total_loss: 9.0, iou_loss: 3.1, l1_loss: 1.3, conf_loss: 3.5, cls_loss: 1.1, lr: 2.495e-03, size: 320, ETA: 4:01:26
2024-02-05 23:30:02 | INFO     | yolox.core.trainer:261 - epoch: 6/100, iter: 120/250, mem: 4287Mb, iter_time: 0.430s, data_time: 0.001s, total_loss: 8.1, iou_loss: 2.9, l1_loss: 1.3, conf_loss: 2.9, cls_loss: 1.0, lr: 2.494e-03, size: 320, ETA: 4:00:49
2024-02-05 23:30:08 | INFO     | yolox.core.trainer:261 - epoch: 6/100, iter: 130/250, mem: 4287Mb, iter_time: 0.611s, data_time: 0.352s, total_loss: 8.1, iou_loss: 3.2, l1_loss: 1.2, conf_loss: 2.8, cls_loss: 1.0, lr: 2.493e-03, size: 192, ETA: 4:00:42
2024-02-05 23:30:11 | INFO     | yolox.core.trainer:261 - epoch: 6/100, iter: 140/250, mem: 4287Mb, iter_time: 0.295s, data_time: 0.069s, total_loss: 8.8, iou_loss: 3.4, l1_loss: 1.4, conf_loss: 2.9, cls_loss: 1.1, lr: 2.492e-03, size: 160, ETA: 3:59:42
2024-02-05 23:30:19 | INFO     | yolox.core.trainer:261 - epoch: 6/100, iter: 150/250, mem: 4287Mb, iter_time: 0.821s, data_time: 0.502s, total_loss: 8.0, iou_loss: 3.1, l1_loss: 1.1, conf_loss: 2.8, cls_loss: 1.0, lr: 2.491e-03, size: 224, ETA: 4:00:12
2024-02-05 23:30:26 | INFO     | yolox.core.trainer:261 - epoch: 6/100, iter: 160/250, mem: 4287Mb, iter_time: 0.728s, data_time: 0.494s, total_loss: 7.8, iou_loss: 3.2, l1_loss: 1.3, conf_loss: 2.4, cls_loss: 1.0, lr: 2.489e-03, size: 128, ETA: 4:00:26
2024-02-05 23:30:29 | INFO     | yolox.core.trainer:261 - epoch: 6/100, iter: 170/250, mem: 4287Mb, iter_time: 0.259s, data_time: 0.056s, total_loss: 8.4, iou_loss: 3.5, l1_loss: 1.4, conf_loss: 2.5, cls_loss: 1.0, lr: 2.488e-03, size: 96, ETA: 3:59:21
2024-02-05 23:30:37 | INFO     | yolox.core.trainer:261 - epoch: 6/100, iter: 180/250, mem: 4287Mb, iter_time: 0.831s, data_time: 0.598s, total_loss: 8.1, iou_loss: 3.4, l1_loss: 1.2, conf_loss: 2.4, cls_loss: 1.1, lr: 2.487e-03, size: 96, ETA: 3:59:51
2024-02-05 23:30:44 | INFO     | yolox.core.trainer:261 - epoch: 6/100, iter: 190/250, mem: 4287Mb, iter_time: 0.701s, data_time: 0.478s, total_loss: 8.4, iou_loss: 3.3, l1_loss: 1.2, conf_loss: 2.8, cls_loss: 1.0, lr: 2.485e-03, size: 128, ETA: 4:00:00
2024-02-05 23:30:53 | INFO     | yolox.core.trainer:261 - epoch: 6/100, iter: 200/250, mem: 4287Mb, iter_time: 0.839s, data_time: 0.001s, total_loss: 9.1, iou_loss: 3.0, l1_loss: 1.5, conf_loss: 3.5, cls_loss: 1.0, lr: 2.483e-03, size: 416, ETA: 4:00:31
2024-02-05 23:30:56 | INFO     | yolox.core.trainer:261 - epoch: 6/100, iter: 210/250, mem: 4287Mb, iter_time: 0.313s, data_time: 0.013s, total_loss: 8.4, iou_loss: 3.2, l1_loss: 1.3, conf_loss: 2.9, cls_loss: 1.1, lr: 2.482e-03, size: 224, ETA: 3:59:37
2024-02-05 23:31:00 | INFO     | yolox.core.trainer:261 - epoch: 6/100, iter: 220/250, mem: 4287Mb, iter_time: 0.392s, data_time: 0.018s, total_loss: 8.5, iou_loss: 3.1, l1_loss: 1.3, conf_loss: 2.9, cls_loss: 1.2, lr: 2.480e-03, size: 288, ETA: 3:58:55
2024-02-05 23:31:07 | INFO     | yolox.core.trainer:261 - epoch: 6/100, iter: 230/250, mem: 4287Mb, iter_time: 0.731s, data_time: 0.374s, total_loss: 8.6, iou_loss: 3.1, l1_loss: 1.3, conf_loss: 3.1, cls_loss: 1.1, lr: 2.478e-03, size: 256, ETA: 3:59:09
2024-02-05 23:31:15 | INFO     | yolox.core.trainer:261 - epoch: 6/100, iter: 240/250, mem: 4287Mb, iter_time: 0.777s, data_time: 0.289s, total_loss: 8.7, iou_loss: 2.9, l1_loss: 1.4, conf_loss: 3.3, cls_loss: 1.1, lr: 2.476e-03, size: 352, ETA: 3:59:29
2024-02-05 23:31:22 | INFO     | yolox.core.trainer:261 - epoch: 6/100, iter: 250/250, mem: 4287Mb, iter_time: 0.705s, data_time: 0.001s, total_loss: 9.3, iou_loss: 3.1, l1_loss: 1.5, conf_loss: 3.7, cls_loss: 1.1, lr: 2.474e-03, size: 416, ETA: 3:59:38
2024-02-05 23:31:22 | INFO     | yolox.core.trainer:363 - Save weights to ./YOLOX_outputs/yolox_s
2024-02-05 23:31:23 | INFO     | yolox.core.trainer:203 - ---> start train epoch7
2024-02-05 23:31:26 | INFO     | yolox.core.trainer:261 - epoch: 7/100, iter: 10/250, mem: 4287Mb, iter_time: 0.336s, data_time: 0.001s, total_loss: 7.9, iou_loss: 3.0, l1_loss: 1.3, conf_loss: 2.6, cls_loss: 1.0, lr: 2.472e-03, size: 256, ETA: 3:58:49
2024-02-05 23:31:33 | INFO     | yolox.core.trainer:261 - epoch: 7/100, iter: 20/250, mem: 4287Mb, iter_time: 0.663s, data_time: 0.452s, total_loss: 8.6, iou_loss: 3.5, l1_loss: 1.3, conf_loss: 2.8, cls_loss: 1.0, lr: 2.470e-03, size: 96, ETA: 3:58:51
2024-02-05 23:31:35 | INFO     | yolox.core.trainer:261 - epoch: 7/100, iter: 30/250, mem: 4287Mb, iter_time: 0.267s, data_time: 0.079s, total_loss: 8.5, iou_loss: 3.6, l1_loss: 1.3, conf_loss: 2.6, cls_loss: 1.0, lr: 2.467e-03, size: 96, ETA: 3:57:52
2024-02-05 23:31:43 | INFO     | yolox.core.trainer:261 - epoch: 7/100, iter: 40/250, mem: 4287Mb, iter_time: 0.778s, data_time: 0.561s, total_loss: 8.3, iou_loss: 3.5, l1_loss: 1.3, conf_loss: 2.6, cls_loss: 1.0, lr: 2.465e-03, size: 128, ETA: 3:58:12
2024-02-05 23:31:51 | INFO     | yolox.core.trainer:261 - epoch: 7/100, iter: 50/250, mem: 4287Mb, iter_time: 0.806s, data_time: 0.011s, total_loss: 9.5, iou_loss: 3.0, l1_loss: 1.5, conf_loss: 3.9, cls_loss: 1.1, lr: 2.463e-03, size: 416, ETA: 3:58:35
2024-02-05 23:31:54 | INFO     | yolox.core.trainer:261 - epoch: 7/100, iter: 60/250, mem: 4287Mb, iter_time: 0.286s, data_time: 0.056s, total_loss: 8.9, iou_loss: 3.3, l1_loss: 1.3, conf_loss: 3.2, cls_loss: 1.0, lr: 2.460e-03, size: 160, ETA: 3:57:41
2024-02-05 23:32:02 | INFO     | yolox.core.trainer:261 - epoch: 7/100, iter: 70/250, mem: 4287Mb, iter_time: 0.797s, data_time: 0.476s, total_loss: 7.8, iou_loss: 3.0, l1_loss: 1.2, conf_loss: 2.5, cls_loss: 1.0, lr: 2.458e-03, size: 224, ETA: 3:58:03
2024-02-05 23:32:07 | INFO     | yolox.core.trainer:261 - epoch: 7/100, iter: 80/250, mem: 4287Mb, iter_time: 0.531s, data_time: 0.002s, total_loss: 9.3, iou_loss: 3.1, l1_loss: 1.5, conf_loss: 3.6, cls_loss: 1.1, lr: 2.455e-03, size: 384, ETA: 3:57:45
2024-02-05 23:32:15 | INFO     | yolox.core.trainer:261 - epoch: 7/100, iter: 90/250, mem: 4287Mb, iter_time: 0.794s, data_time: 0.083s, total_loss: 8.9, iou_loss: 2.9, l1_loss: 1.4, conf_loss: 3.4, cls_loss: 1.1, lr: 2.452e-03, size: 416, ETA: 3:58:06
2024-02-05 23:32:20 | INFO     | yolox.core.trainer:261 - epoch: 7/100, iter: 100/250, mem: 4287Mb, iter_time: 0.499s, data_time: 0.169s, total_loss: 8.5, iou_loss: 3.1, l1_loss: 1.3, conf_loss: 3.1, cls_loss: 1.0, lr: 2.449e-03, size: 256, ETA: 3:57:44
2024-02-05 23:32:23 | INFO     | yolox.core.trainer:261 - epoch: 7/100, iter: 110/250, mem: 4287Mb, iter_time: 0.242s, data_time: 0.043s, total_loss: 8.6, iou_loss: 3.5, l1_loss: 1.2, conf_loss: 3.0, cls_loss: 0.9, lr: 2.446e-03, size: 96, ETA: 3:56:44
2024-02-05 23:32:32 | INFO     | yolox.core.trainer:261 - epoch: 7/100, iter: 120/250, mem: 4287Mb, iter_time: 0.956s, data_time: 0.397s, total_loss: 8.9, iou_loss: 3.0, l1_loss: 1.3, conf_loss: 3.7, cls_loss: 1.0, lr: 2.443e-03, size: 384, ETA: 3:57:28
2024-02-05 23:32:34 | INFO     | yolox.core.trainer:261 - epoch: 7/100, iter: 130/250, mem: 4287Mb, iter_time: 0.194s, data_time: 0.001s, total_loss: inf, iou_loss: 3.6, l1_loss: inf, conf_loss: 3.9, cls_loss: 1.2, lr: 2.440e-03, size: 96, ETA: 3:56:23
2024-02-05 23:32:42 | INFO     | yolox.core.trainer:261 - epoch: 7/100, iter: 140/250, mem: 4287Mb, iter_time: 0.753s, data_time: 0.442s, total_loss: 8.2, iou_loss: 3.1, l1_loss: 1.3, conf_loss: 2.7, cls_loss: 1.1, lr: 2.437e-03, size: 224, ETA: 3:56:37
2024-02-05 23:32:49 | INFO     | yolox.core.trainer:261 - epoch: 7/100, iter: 150/250, mem: 4287Mb, iter_time: 0.757s, data_time: 0.492s, total_loss: 8.3, iou_loss: 3.2, l1_loss: 1.2, conf_loss: 2.9, cls_loss: 1.0, lr: 2.434e-03, size: 192, ETA: 3:56:53
2024-02-05 23:32:53 | INFO     | yolox.core.trainer:261 - epoch: 7/100, iter: 160/250, mem: 4287Mb, iter_time: 0.416s, data_time: 0.001s, total_loss: 8.7, iou_loss: 2.9, l1_loss: 1.3, conf_loss: 3.4, cls_loss: 1.1, lr: 2.431e-03, size: 320, ETA: 3:56:19
2024-02-05 23:33:00 | INFO     | yolox.core.trainer:261 - epoch: 7/100, iter: 170/250, mem: 4287Mb, iter_time: 0.693s, data_time: 0.303s, total_loss: 8.1, iou_loss: 3.0, l1_loss: 1.3, conf_loss: 2.7, cls_loss: 1.0, lr: 2.427e-03, size: 288, ETA: 3:56:25
2024-02-05 23:33:07 | INFO     | yolox.core.trainer:261 - epoch: 7/100, iter: 180/250, mem: 4287Mb, iter_time: 0.678s, data_time: 0.367s, total_loss: 7.7, iou_loss: 3.0, l1_loss: 1.2, conf_loss: 2.5, cls_loss: 1.1, lr: 2.424e-03, size: 224, ETA: 3:56:29
2024-02-05 23:33:10 | INFO     | yolox.core.trainer:261 - epoch: 7/100, iter: 190/250, mem: 4287Mb, iter_time: 0.260s, data_time: 0.046s, total_loss: 8.1, iou_loss: 3.2, l1_loss: 1.3, conf_loss: 2.6, cls_loss: 1.1, lr: 2.420e-03, size: 160, ETA: 3:55:35
2024-02-05 23:33:19 | INFO     | yolox.core.trainer:261 - epoch: 7/100, iter: 200/250, mem: 4287Mb, iter_time: 0.881s, data_time: 0.387s, total_loss: 8.3, iou_loss: 2.9, l1_loss: 1.3, conf_loss: 3.1, cls_loss: 0.9, lr: 2.417e-03, size: 352, ETA: 3:56:06
2024-02-05 23:33:21 | INFO     | yolox.core.trainer:261 - epoch: 7/100, iter: 210/250, mem: 4287Mb, iter_time: 0.238s, data_time: 0.001s, total_loss: 8.0, iou_loss: 3.0, l1_loss: 1.2, conf_loss: 2.8, cls_loss: 1.0, lr: 2.413e-03, size: 192, ETA: 3:55:10
2024-02-05 23:33:30 | INFO     | yolox.core.trainer:261 - epoch: 7/100, iter: 220/250, mem: 4287Mb, iter_time: 0.928s, data_time: 0.372s, total_loss: 8.3, iou_loss: 2.9, l1_loss: 1.3, conf_loss: 3.1, cls_loss: 1.0, lr: 2.409e-03, size: 384, ETA: 3:55:47
2024-02-05 23:33:36 | INFO     | yolox.core.trainer:261 - epoch: 7/100, iter: 230/250, mem: 4287Mb, iter_time: 0.597s, data_time: 0.342s, total_loss: 7.8, iou_loss: 3.1, l1_loss: 1.2, conf_loss: 2.6, cls_loss: 0.9, lr: 2.405e-03, size: 192, ETA: 3:55:40
2024-02-05 23:33:41 | INFO     | yolox.core.trainer:261 - epoch: 7/100, iter: 240/250, mem: 4287Mb, iter_time: 0.477s, data_time: 0.003s, total_loss: 8.4, iou_loss: 3.0, l1_loss: 1.3, conf_loss: 3.0, cls_loss: 1.2, lr: 2.401e-03, size: 352, ETA: 3:55:16
2024-02-05 23:33:46 | INFO     | yolox.core.trainer:261 - epoch: 7/100, iter: 250/250, mem: 4287Mb, iter_time: 0.538s, data_time: 0.335s, total_loss: 7.8, iou_loss: 3.2, l1_loss: 1.1, conf_loss: 2.6, cls_loss: 0.9, lr: 2.397e-03, size: 128, ETA: 3:55:01
2024-02-05 23:33:46 | INFO     | yolox.core.trainer:363 - Save weights to ./YOLOX_outputs/yolox_s
2024-02-05 23:33:47 | INFO     | yolox.core.trainer:203 - ---> start train epoch8
2024-02-05 23:33:54 | INFO     | yolox.core.trainer:261 - epoch: 8/100, iter: 10/250, mem: 4287Mb, iter_time: 0.662s, data_time: 0.438s, total_loss: 7.8, iou_loss: 3.2, l1_loss: 1.2, conf_loss: 2.4, cls_loss: 1.0, lr: 2.393e-03, size: 160, ETA: 3:55:02
2024-02-05 23:33:56 | INFO     | yolox.core.trainer:261 - epoch: 8/100, iter: 20/250, mem: 4287Mb, iter_time: 0.245s, data_time: 0.037s, total_loss: 7.6, iou_loss: 3.2, l1_loss: 1.2, conf_loss: 2.2, cls_loss: 0.9, lr: 2.389e-03, size: 128, ETA: 3:54:09
2024-02-05 23:34:04 | INFO     | yolox.core.trainer:261 - epoch: 8/100, iter: 30/250, mem: 4287Mb, iter_time: 0.765s, data_time: 0.546s, total_loss: 7.1, iou_loss: 3.1, l1_loss: 1.1, conf_loss: 2.0, cls_loss: 0.9, lr: 2.385e-03, size: 128, ETA: 3:54:24
2024-02-05 23:34:06 | INFO     | yolox.core.trainer:261 - epoch: 8/100, iter: 40/250, mem: 4287Mb, iter_time: 0.245s, data_time: 0.001s, total_loss: 7.9, iou_loss: 3.1, l1_loss: 1.1, conf_loss: 2.6, cls_loss: 1.0, lr: 2.381e-03, size: 192, ETA: 3:53:31
2024-02-05 23:34:14 | INFO     | yolox.core.trainer:261 - epoch: 8/100, iter: 50/250, mem: 4287Mb, iter_time: 0.739s, data_time: 0.505s, total_loss: 8.1, iou_loss: 3.2, l1_loss: 1.2, conf_loss: 2.6, cls_loss: 1.0, lr: 2.376e-03, size: 160, ETA: 3:53:42
2024-02-05 23:34:21 | INFO     | yolox.core.trainer:261 - epoch: 8/100, iter: 60/250, mem: 4287Mb, iter_time: 0.744s, data_time: 0.548s, total_loss: 8.5, iou_loss: 3.5, l1_loss: 1.3, conf_loss: 2.5, cls_loss: 1.2, lr: 2.372e-03, size: 96, ETA: 3:53:54
2024-02-05 23:34:23 | INFO     | yolox.core.trainer:261 - epoch: 8/100, iter: 70/250, mem: 4287Mb, iter_time: 0.227s, data_time: 0.001s, total_loss: 7.7, iou_loss: 3.1, l1_loss: 1.1, conf_loss: 2.4, cls_loss: 1.1, lr: 2.367e-03, size: 160, ETA: 3:53:00
2024-02-05 23:34:33 | INFO     | yolox.core.trainer:261 - epoch: 8/100, iter: 80/250, mem: 4287Mb, iter_time: 0.994s, data_time: 0.428s, total_loss: 8.4, iou_loss: 2.9, l1_loss: 1.2, conf_loss: 3.1, cls_loss: 1.1, lr: 2.363e-03, size: 384, ETA: 3:53:43
2024-02-05 23:34:39 | INFO     | yolox.core.trainer:261 - epoch: 8/100, iter: 90/250, mem: 4287Mb, iter_time: 0.587s, data_time: 0.057s, total_loss: 8.4, iou_loss: 2.9, l1_loss: 1.3, conf_loss: 3.2, cls_loss: 1.0, lr: 2.358e-03, size: 384, ETA: 3:53:35
2024-02-05 23:34:41 | INFO     | yolox.core.trainer:261 - epoch: 8/100, iter: 100/250, mem: 4287Mb, iter_time: 0.200s, data_time: 0.005s, total_loss: 8.7, iou_loss: 3.5, l1_loss: 1.3, conf_loss: 3.0, cls_loss: 1.0, lr: 2.353e-03, size: 96, ETA: 3:52:38
2024-02-05 23:34:50 | INFO     | yolox.core.trainer:261 - epoch: 8/100, iter: 110/250, mem: 4287Mb, iter_time: 0.844s, data_time: 0.488s, total_loss: 7.5, iou_loss: 2.9, l1_loss: 1.2, conf_loss: 2.5, cls_loss: 1.0, lr: 2.348e-03, size: 256, ETA: 3:53:02
2024-02-05 23:34:54 | INFO     | yolox.core.trainer:261 - epoch: 8/100, iter: 120/250, mem: 4287Mb, iter_time: 0.416s, data_time: 0.001s, total_loss: 8.0, iou_loss: 2.9, l1_loss: 1.2, conf_loss: 2.8, cls_loss: 1.0, lr: 2.343e-03, size: 320, ETA: 3:52:33
2024-02-05 23:34:59 | INFO     | yolox.core.trainer:261 - epoch: 8/100, iter: 130/250, mem: 4287Mb, iter_time: 0.535s, data_time: 0.323s, total_loss: 7.8, iou_loss: 3.0, l1_loss: 1.0, conf_loss: 2.6, cls_loss: 1.2, lr: 2.338e-03, size: 128, ETA: 3:52:18
2024-02-05 23:35:07 | INFO     | yolox.core.trainer:261 - epoch: 8/100, iter: 140/250, mem: 4287Mb, iter_time: 0.779s, data_time: 0.566s, total_loss: 8.0, iou_loss: 3.3, l1_loss: 1.2, conf_loss: 2.5, cls_loss: 1.0, lr: 2.333e-03, size: 128, ETA: 3:52:34
2024-02-05 23:35:11 | INFO     | yolox.core.trainer:261 - epoch: 8/100, iter: 150/250, mem: 4287Mb, iter_time: 0.369s, data_time: 0.001s, total_loss: 7.8, iou_loss: 2.9, l1_loss: 1.0, conf_loss: 2.8, cls_loss: 1.0, lr: 2.328e-03, size: 288, ETA: 3:51:59
2024-02-05 23:35:17 | INFO     | yolox.core.trainer:261 - epoch: 8/100, iter: 160/250, mem: 4287Mb, iter_time: 0.653s, data_time: 0.419s, total_loss: 7.9, iou_loss: 3.1, l1_loss: 1.2, conf_loss: 2.6, cls_loss: 1.1, lr: 2.323e-03, size: 160, ETA: 3:51:59
2024-02-05 23:35:25 | INFO     | yolox.core.trainer:261 - epoch: 8/100, iter: 170/250, mem: 4287Mb, iter_time: 0.765s, data_time: 0.385s, total_loss: 7.7, iou_loss: 2.9, l1_loss: 1.2, conf_loss: 2.6, cls_loss: 1.0, lr: 2.318e-03, size: 288, ETA: 3:52:13
2024-02-05 23:35:29 | INFO     | yolox.core.trainer:261 - epoch: 8/100, iter: 180/250, mem: 4287Mb, iter_time: 0.368s, data_time: 0.001s, total_loss: 7.7, iou_loss: 2.8, l1_loss: 1.2, conf_loss: 2.6, cls_loss: 1.0, lr: 2.312e-03, size: 288, ETA: 3:51:39
2024-02-05 23:35:36 | INFO     | yolox.core.trainer:261 - epoch: 8/100, iter: 190/250, mem: 4287Mb, iter_time: 0.694s, data_time: 0.306s, total_loss: 7.7, iou_loss: 2.8, l1_loss: 1.2, conf_loss: 2.6, cls_loss: 1.0, lr: 2.307e-03, size: 288, ETA: 3:51:43
2024-02-05 23:35:40 | INFO     | yolox.core.trainer:261 - epoch: 8/100, iter: 200/250, mem: 4287Mb, iter_time: 0.410s, data_time: 0.002s, total_loss: 7.7, iou_loss: 2.8, l1_loss: 1.3, conf_loss: 2.7, cls_loss: 1.0, lr: 2.302e-03, size: 320, ETA: 3:51:14
2024-02-05 23:35:45 | INFO     | yolox.core.trainer:261 - epoch: 8/100, iter: 210/250, mem: 4287Mb, iter_time: 0.561s, data_time: 0.301s, total_loss: 7.2, iou_loss: 2.9, l1_loss: 1.1, conf_loss: 2.3, cls_loss: 1.0, lr: 2.296e-03, size: 192, ETA: 3:51:04
2024-02-05 23:35:54 | INFO     | yolox.core.trainer:261 - epoch: 8/100, iter: 220/250, mem: 4287Mb, iter_time: 0.883s, data_time: 0.325s, total_loss: 8.4, iou_loss: 2.9, l1_loss: 1.3, conf_loss: 3.0, cls_loss: 1.2, lr: 2.290e-03, size: 384, ETA: 3:51:30
2024-02-05 23:35:58 | INFO     | yolox.core.trainer:261 - epoch: 8/100, iter: 230/250, mem: 4287Mb, iter_time: 0.414s, data_time: 0.001s, total_loss: 7.7, iou_loss: 2.7, l1_loss: 1.3, conf_loss: 2.7, cls_loss: 1.0, lr: 2.285e-03, size: 320, ETA: 3:51:02
2024-02-05 23:36:06 | INFO     | yolox.core.trainer:261 - epoch: 8/100, iter: 240/250, mem: 4287Mb, iter_time: 0.737s, data_time: 0.183s, total_loss: 7.8, iou_loss: 2.7, l1_loss: 1.3, conf_loss: 2.8, cls_loss: 1.0, lr: 2.279e-03, size: 384, ETA: 3:51:12
2024-02-05 23:36:11 | INFO     | yolox.core.trainer:261 - epoch: 8/100, iter: 250/250, mem: 4287Mb, iter_time: 0.576s, data_time: 0.161s, total_loss: 7.4, iou_loss: 2.8, l1_loss: 1.2, conf_loss: 2.6, cls_loss: 0.9, lr: 2.273e-03, size: 320, ETA: 3:51:03
2024-02-05 23:36:11 | INFO     | yolox.core.trainer:363 - Save weights to ./YOLOX_outputs/yolox_s
2024-02-05 23:36:12 | INFO     | yolox.core.trainer:203 - ---> start train epoch9
2024-02-05 23:36:16 | INFO     | yolox.core.trainer:261 - epoch: 9/100, iter: 10/250, mem: 4287Mb, iter_time: 0.370s, data_time: 0.001s, total_loss: 7.3, iou_loss: 2.7, l1_loss: 1.1, conf_loss: 2.6, cls_loss: 1.0, lr: 2.267e-03, size: 288, ETA: 3:50:30
2024-02-05 23:36:23 | INFO     | yolox.core.trainer:261 - epoch: 9/100, iter: 20/250, mem: 4287Mb, iter_time: 0.708s, data_time: 0.175s, total_loss: 8.6, iou_loss: 2.9, l1_loss: 1.5, conf_loss: 3.1, cls_loss: 1.1, lr: 2.261e-03, size: 384, ETA: 3:50:36
2024-02-05 23:36:28 | INFO     | yolox.core.trainer:261 - epoch: 9/100, iter: 30/250, mem: 4287Mb, iter_time: 0.533s, data_time: 0.001s, total_loss: 7.5, iou_loss: 2.8, l1_loss: 1.2, conf_loss: 2.5, cls_loss: 1.0, lr: 2.255e-03, size: 384, ETA: 3:50:22
2024-02-05 23:36:36 | INFO     | yolox.core.trainer:261 - epoch: 9/100, iter: 40/250, mem: 4287Mb, iter_time: 0.786s, data_time: 0.085s, total_loss: 8.2, iou_loss: 2.8, l1_loss: 1.3, conf_loss: 3.0, cls_loss: 1.1, lr: 2.249e-03, size: 416, ETA: 3:50:37
2024-02-05 23:36:40 | INFO     | yolox.core.trainer:261 - epoch: 9/100, iter: 50/250, mem: 4287Mb, iter_time: 0.409s, data_time: 0.207s, total_loss: 9.1, iou_loss: 3.6, l1_loss: 1.4, conf_loss: 3.1, cls_loss: 1.0, lr: 2.243e-03, size: 96, ETA: 3:50:09
2024-02-05 23:36:43 | INFO     | yolox.core.trainer:261 - epoch: 9/100, iter: 60/250, mem: 4287Mb, iter_time: 0.228s, data_time: 0.005s, total_loss: 7.6, iou_loss: 3.1, l1_loss: 1.1, conf_loss: 2.4, cls_loss: 1.1, lr: 2.237e-03, size: 160, ETA: 3:49:22
2024-02-05 23:36:50 | INFO     | yolox.core.trainer:261 - epoch: 9/100, iter: 70/250, mem: 4287Mb, iter_time: 0.766s, data_time: 0.521s, total_loss: 7.4, iou_loss: 3.0, l1_loss: 1.1, conf_loss: 2.3, cls_loss: 1.0, lr: 2.231e-03, size: 160, ETA: 3:49:34
2024-02-05 23:36:58 | INFO     | yolox.core.trainer:261 - epoch: 9/100, iter: 80/250, mem: 4287Mb, iter_time: 0.783s, data_time: 0.394s, total_loss: 8.4, iou_loss: 2.8, l1_loss: 1.3, conf_loss: 3.1, cls_loss: 1.2, lr: 2.224e-03, size: 288, ETA: 3:49:48
2024-02-05 23:37:00 | INFO     | yolox.core.trainer:261 - epoch: 9/100, iter: 90/250, mem: 4287Mb, iter_time: 0.196s, data_time: 0.007s, total_loss: 8.2, iou_loss: 3.3, l1_loss: 1.1, conf_loss: 2.8, cls_loss: 1.0, lr: 2.218e-03, size: 96, ETA: 3:48:58
2024-02-05 23:37:11 | INFO     | yolox.core.trainer:261 - epoch: 9/100, iter: 100/250, mem: 4287Mb, iter_time: 1.078s, data_time: 0.290s, total_loss: 8.7, iou_loss: 2.9, l1_loss: 1.4, conf_loss: 3.3, cls_loss: 1.1, lr: 2.211e-03, size: 416, ETA: 3:49:44
2024-02-05 23:37:15 | INFO     | yolox.core.trainer:261 - epoch: 9/100, iter: 110/250, mem: 4287Mb, iter_time: 0.411s, data_time: 0.001s, total_loss: 7.8, iou_loss: 2.7, l1_loss: 1.2, conf_loss: 2.8, cls_loss: 1.1, lr: 2.205e-03, size: 288, ETA: 3:49:17
2024-02-05 23:37:19 | INFO     | yolox.core.trainer:261 - epoch: 9/100, iter: 120/250, mem: 4287Mb, iter_time: 0.399s, data_time: 0.109s, total_loss: 8.6, iou_loss: 3.2, l1_loss: 1.3, conf_loss: 3.0, cls_loss: 1.1, lr: 2.198e-03, size: 224, ETA: 3:48:49
2024-02-05 23:37:27 | INFO     | yolox.core.trainer:261 - epoch: 9/100, iter: 130/250, mem: 4287Mb, iter_time: 0.815s, data_time: 0.327s, total_loss: 7.8, iou_loss: 2.8, l1_loss: 1.3, conf_loss: 2.7, cls_loss: 1.0, lr: 2.192e-03, size: 352, ETA: 3:49:07
2024-02-05 23:37:29 | INFO     | yolox.core.trainer:261 - epoch: 9/100, iter: 140/250, mem: 4287Mb, iter_time: 0.226s, data_time: 0.002s, total_loss: 7.6, iou_loss: 3.0, l1_loss: 1.1, conf_loss: 2.5, cls_loss: 1.1, lr: 2.185e-03, size: 192, ETA: 3:48:20
2024-02-05 23:37:38 | INFO     | yolox.core.trainer:261 - epoch: 9/100, iter: 150/250, mem: 4287Mb, iter_time: 0.831s, data_time: 0.411s, total_loss: 7.7, iou_loss: 2.8, l1_loss: 1.3, conf_loss: 2.7, cls_loss: 0.9, lr: 2.178e-03, size: 320, ETA: 3:48:39
2024-02-05 23:37:45 | INFO     | yolox.core.trainer:261 - epoch: 9/100, iter: 160/250, mem: 4287Mb, iter_time: 0.769s, data_time: 0.269s, total_loss: 8.1, iou_loss: 2.9, l1_loss: 1.4, conf_loss: 2.9, cls_loss: 1.0, lr: 2.171e-03, size: 352, ETA: 3:48:51
2024-02-05 23:37:50 | INFO     | yolox.core.trainer:261 - epoch: 9/100, iter: 170/250, mem: 4287Mb, iter_time: 0.415s, data_time: 0.003s, total_loss: 7.3, iou_loss: 2.6, l1_loss: 1.1, conf_loss: 2.7, cls_loss: 0.9, lr: 2.164e-03, size: 320, ETA: 3:48:25
2024-02-05 23:37:55 | INFO     | yolox.core.trainer:261 - epoch: 9/100, iter: 180/250, mem: 4287Mb, iter_time: 0.594s, data_time: 0.347s, total_loss: 7.6, iou_loss: 3.0, l1_loss: 1.1, conf_loss: 2.4, cls_loss: 1.1, lr: 2.157e-03, size: 192, ETA: 3:48:19
2024-02-05 23:37:58 | INFO     | yolox.core.trainer:261 - epoch: 9/100, iter: 190/250, mem: 4287Mb, iter_time: 0.225s, data_time: 0.040s, total_loss: 7.9, iou_loss: 3.3, l1_loss: 1.2, conf_loss: 2.3, cls_loss: 1.1, lr: 2.150e-03, size: 96, ETA: 3:47:34
2024-02-05 23:38:06 | INFO     | yolox.core.trainer:261 - epoch: 9/100, iter: 200/250, mem: 4287Mb, iter_time: 0.818s, data_time: 0.510s, total_loss: 7.6, iou_loss: 2.9, l1_loss: 1.2, conf_loss: 2.5, cls_loss: 1.0, lr: 2.143e-03, size: 224, ETA: 3:47:50
2024-02-05 23:38:13 | INFO     | yolox.core.trainer:261 - epoch: 9/100, iter: 210/250, mem: 4287Mb, iter_time: 0.705s, data_time: 0.472s, total_loss: 7.5, iou_loss: 3.0, l1_loss: 1.1, conf_loss: 2.4, cls_loss: 1.0, lr: 2.136e-03, size: 160, ETA: 3:47:55
2024-02-05 23:38:16 | INFO     | yolox.core.trainer:261 - epoch: 9/100, iter: 220/250, mem: 4287Mb, iter_time: 0.272s, data_time: 0.032s, total_loss: 7.6, iou_loss: 3.1, l1_loss: 1.1, conf_loss: 2.4, cls_loss: 1.0, lr: 2.129e-03, size: 192, ETA: 3:47:15
2024-02-05 23:38:23 | INFO     | yolox.core.trainer:261 - epoch: 9/100, iter: 230/250, mem: 4287Mb, iter_time: 0.763s, data_time: 0.455s, total_loss: 7.6, iou_loss: 2.9, l1_loss: 1.1, conf_loss: 2.5, cls_loss: 1.0, lr: 2.122e-03, size: 224, ETA: 3:47:26
2024-02-05 23:38:31 | INFO     | yolox.core.trainer:261 - epoch: 9/100, iter: 240/250, mem: 4287Mb, iter_time: 0.739s, data_time: 0.313s, total_loss: 7.4, iou_loss: 2.7, l1_loss: 1.2, conf_loss: 2.6, cls_loss: 0.9, lr: 2.114e-03, size: 320, ETA: 3:47:34
2024-02-05 23:38:36 | INFO     | yolox.core.trainer:261 - epoch: 9/100, iter: 250/250, mem: 4287Mb, iter_time: 0.543s, data_time: 0.001s, total_loss: 8.2, iou_loss: 2.9, l1_loss: 1.4, conf_loss: 2.9, cls_loss: 1.1, lr: 2.107e-03, size: 384, ETA: 3:47:23
2024-02-05 23:38:36 | INFO     | yolox.core.trainer:363 - Save weights to ./YOLOX_outputs/yolox_s
2024-02-05 23:38:37 | INFO     | yolox.core.trainer:203 - ---> start train epoch10
2024-02-05 23:38:41 | INFO     | yolox.core.trainer:261 - epoch: 10/100, iter: 10/250, mem: 4287Mb, iter_time: 0.399s, data_time: 0.180s, total_loss: 7.9, iou_loss: 3.2, l1_loss: 1.2, conf_loss: 2.4, cls_loss: 1.1, lr: 2.100e-03, size: 128, ETA: 3:46:57
2024-02-05 23:38:43 | INFO     | yolox.core.trainer:261 - epoch: 10/100, iter: 20/250, mem: 4287Mb, iter_time: 0.223s, data_time: 0.019s, total_loss: 7.8, iou_loss: 3.2, l1_loss: 1.1, conf_loss: 2.4, cls_loss: 1.1, lr: 2.092e-03, size: 128, ETA: 3:46:13
2024-02-05 23:38:51 | INFO     | yolox.core.trainer:261 - epoch: 10/100, iter: 30/250, mem: 4287Mb, iter_time: 0.748s, data_time: 0.531s, total_loss: 7.9, iou_loss: 3.3, l1_loss: 1.2, conf_loss: 2.4, cls_loss: 1.0, lr: 2.085e-03, size: 96, ETA: 3:46:22
2024-02-05 23:38:59 | INFO     | yolox.core.trainer:261 - epoch: 10/100, iter: 40/250, mem: 4287Mb, iter_time: 0.852s, data_time: 0.301s, total_loss: 8.7, iou_loss: 2.9, l1_loss: 1.4, conf_loss: 3.3, cls_loss: 1.0, lr: 2.077e-03, size: 384, ETA: 3:46:41
2024-02-05 23:39:01 | INFO     | yolox.core.trainer:261 - epoch: 10/100, iter: 50/250, mem: 4287Mb, iter_time: 0.220s, data_time: 0.001s, total_loss: 8.1, iou_loss: 3.1, l1_loss: 1.2, conf_loss: 2.9, cls_loss: 0.9, lr: 2.069e-03, size: 160, ETA: 3:45:58
2024-02-05 23:39:10 | INFO     | yolox.core.trainer:261 - epoch: 10/100, iter: 60/250, mem: 4287Mb, iter_time: 0.837s, data_time: 0.398s, total_loss: 7.5, iou_loss: 2.7, l1_loss: 1.2, conf_loss: 2.7, cls_loss: 0.9, lr: 2.062e-03, size: 320, ETA: 3:46:15
2024-02-05 23:39:16 | INFO     | yolox.core.trainer:261 - epoch: 10/100, iter: 70/250, mem: 4287Mb, iter_time: 0.632s, data_time: 0.378s, total_loss: 8.2, iou_loss: 3.2, l1_loss: 1.2, conf_loss: 2.8, cls_loss: 1.0, lr: 2.054e-03, size: 192, ETA: 3:46:13
2024-02-05 23:39:19 | INFO     | yolox.core.trainer:261 - epoch: 10/100, iter: 80/250, mem: 4287Mb, iter_time: 0.276s, data_time: 0.032s, total_loss: 6.8, iou_loss: 2.8, l1_loss: 1.0, conf_loss: 2.1, cls_loss: 0.9, lr: 2.046e-03, size: 192, ETA: 3:45:35
2024-02-05 23:39:27 | INFO     | yolox.core.trainer:261 - epoch: 10/100, iter: 90/250, mem: 4287Mb, iter_time: 0.769s, data_time: 0.471s, total_loss: 6.7, iou_loss: 2.6, l1_loss: 1.0, conf_loss: 2.2, cls_loss: 0.9, lr: 2.038e-03, size: 224, ETA: 3:45:46
2024-02-05 23:39:32 | INFO     | yolox.core.trainer:261 - epoch: 10/100, iter: 100/250, mem: 4287Mb, iter_time: 0.534s, data_time: 0.001s, total_loss: 7.4, iou_loss: 2.6, l1_loss: 1.1, conf_loss: 2.6, cls_loss: 1.0, lr: 2.030e-03, size: 384, ETA: 3:45:34
2024-02-05 23:39:39 | INFO     | yolox.core.trainer:261 - epoch: 10/100, iter: 110/250, mem: 4287Mb, iter_time: 0.666s, data_time: 0.182s, total_loss: 7.6, iou_loss: 2.8, l1_loss: 1.2, conf_loss: 2.7, cls_loss: 1.0, lr: 2.023e-03, size: 352, ETA: 3:45:34
2024-02-05 23:39:45 | INFO     | yolox.core.trainer:261 - epoch: 10/100, iter: 120/250, mem: 4287Mb, iter_time: 0.671s, data_time: 0.138s, total_loss: 7.7, iou_loss: 2.7, l1_loss: 1.3, conf_loss: 2.8, cls_loss: 0.9, lr: 2.015e-03, size: 384, ETA: 3:45:35
2024-02-05 23:39:48 | INFO     | yolox.core.trainer:261 - epoch: 10/100, iter: 130/250, mem: 4287Mb, iter_time: 0.225s, data_time: 0.001s, total_loss: 7.5, iou_loss: 3.0, l1_loss: 1.1, conf_loss: 2.4, cls_loss: 1.0, lr: 2.006e-03, size: 160, ETA: 3:44:54
2024-02-05 23:39:55 | INFO     | yolox.core.trainer:261 - epoch: 10/100, iter: 140/250, mem: 4287Mb, iter_time: 0.731s, data_time: 0.522s, total_loss: 7.2, iou_loss: 3.1, l1_loss: 1.1, conf_loss: 2.1, cls_loss: 1.0, lr: 1.998e-03, size: 96, ETA: 3:45:01
2024-02-05 23:40:03 | INFO     | yolox.core.trainer:261 - epoch: 10/100, iter: 150/250, mem: 4287Mb, iter_time: 0.782s, data_time: 0.348s, total_loss: 7.6, iou_loss: 2.8, l1_loss: 1.3, conf_loss: 2.6, cls_loss: 1.0, lr: 1.990e-03, size: 320, ETA: 3:45:12
2024-02-05 23:40:06 | INFO     | yolox.core.trainer:261 - epoch: 10/100, iter: 160/250, mem: 4287Mb, iter_time: 0.371s, data_time: 0.006s, total_loss: 7.4, iou_loss: 2.8, l1_loss: 1.1, conf_loss: 2.5, cls_loss: 1.0, lr: 1.982e-03, size: 288, ETA: 3:44:45
2024-02-05 23:40:13 | INFO     | yolox.core.trainer:261 - epoch: 10/100, iter: 170/250, mem: 4287Mb, iter_time: 0.699s, data_time: 0.360s, total_loss: 7.6, iou_loss: 2.9, l1_loss: 1.1, conf_loss: 2.5, cls_loss: 1.0, lr: 1.974e-03, size: 256, ETA: 3:44:48
2024-02-05 23:40:15 | INFO     | yolox.core.trainer:261 - epoch: 10/100, iter: 180/250, mem: 4287Mb, iter_time: 0.177s, data_time: 0.001s, total_loss: 8.0, iou_loss: 3.3, l1_loss: 1.1, conf_loss: 2.6, cls_loss: 1.0, lr: 1.966e-03, size: 96, ETA: 3:44:03
2024-02-05 23:40:25 | INFO     | yolox.core.trainer:261 - epoch: 10/100, iter: 190/250, mem: 4287Mb, iter_time: 1.019s, data_time: 0.479s, total_loss: 7.9, iou_loss: 2.7, l1_loss: 1.2, conf_loss: 3.1, cls_loss: 0.9, lr: 1.957e-03, size: 384, ETA: 3:44:37
2024-02-05 23:40:31 | INFO     | yolox.core.trainer:261 - epoch: 10/100, iter: 200/250, mem: 4287Mb, iter_time: 0.575s, data_time: 0.329s, total_loss: 8.0, iou_loss: 3.1, l1_loss: 1.1, conf_loss: 2.7, cls_loss: 1.0, lr: 1.949e-03, size: 160, ETA: 3:44:29
2024-02-05 23:40:33 | INFO     | yolox.core.trainer:261 - epoch: 10/100, iter: 210/250, mem: 4287Mb, iter_time: 0.194s, data_time: 0.001s, total_loss: 7.8, iou_loss: 3.3, l1_loss: 1.2, conf_loss: 2.3, cls_loss: 1.0, lr: 1.940e-03, size: 96, ETA: 3:43:46
2024-02-05 23:40:41 | INFO     | yolox.core.trainer:261 - epoch: 10/100, iter: 220/250, mem: 4287Mb, iter_time: 0.776s, data_time: 0.557s, total_loss: 7.9, iou_loss: 3.3, l1_loss: 1.2, conf_loss: 2.5, cls_loss: 0.9, lr: 1.932e-03, size: 128, ETA: 3:43:56
2024-02-05 23:40:49 | INFO     | yolox.core.trainer:261 - epoch: 10/100, iter: 230/250, mem: 4287Mb, iter_time: 0.766s, data_time: 0.330s, total_loss: 7.7, iou_loss: 2.8, l1_loss: 1.1, conf_loss: 2.8, cls_loss: 1.0, lr: 1.923e-03, size: 320, ETA: 3:44:06
2024-02-05 23:40:51 | INFO     | yolox.core.trainer:261 - epoch: 10/100, iter: 240/250, mem: 4287Mb, iter_time: 0.252s, data_time: 0.012s, total_loss: 7.3, iou_loss: 2.8, l1_loss: 1.1, conf_loss: 2.4, cls_loss: 1.0, lr: 1.915e-03, size: 192, ETA: 3:43:28
2024-02-05 23:40:58 | INFO     | yolox.core.trainer:261 - epoch: 10/100, iter: 250/250, mem: 4287Mb, iter_time: 0.736s, data_time: 0.488s, total_loss: 6.8, iou_loss: 2.7, l1_loss: 1.1, conf_loss: 2.1, cls_loss: 0.9, lr: 1.906e-03, size: 192, ETA: 3:43:35
2024-02-05 23:40:58 | INFO     | yolox.core.trainer:363 - Save weights to ./YOLOX_outputs/yolox_s
  0%|          | 0/125 [00:00<?, ?it/s]libpng error: Read Error
100%|##########| 125/125 [00:27<00:00,  4.62it/s]
2024-02-05 23:41:26 | INFO     | yolox.evaluators.coco_evaluator:235 - Evaluate in main process...
2024-02-05 23:41:30 | INFO     | yolox.evaluators.coco_evaluator:268 - Loading and preparing results...
2024-02-05 23:41:32 | INFO     | yolox.evaluators.coco_evaluator:268 - DONE (t=1.86s)
2024-02-05 23:41:32 | INFO     | pycocotools.coco:366 - creating index...
2024-02-05 23:41:32 | INFO     | pycocotools.coco:366 - index created!
Running per image evaluation...
Evaluate annotation type *bbox*
COCOeval_opt.evaluate() finished in 1.56 seconds.
Accumulating evaluation results...
COCOeval_opt.accumulate() finished in 0.30 seconds.
2024-02-05 23:41:34 | INFO     | yolox.core.trainer:353 -
Average forward time: 4.28 ms, Average NMS time: 1.10 ms, Average inference time: 5.38 ms
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.086
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.189
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.070
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.099
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.092
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.077
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.077
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.149
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.179
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.157
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.193
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.173