预训练(pre-training/trained)与微调(fine tuning)

                    版权声明:本文为博主原创文章,引用时请附上链接。                        https://blog.youkuaiyun.com/abc13526222160/article/details/89320108                    </div>
                                                <link rel="stylesheet" href="https://csdnimg.cn/release/phoenix/template/css/ck_htmledit_views-cd6c485e8b.css">
                                                        <div id="content_views" class="markdown_views prism-dracula">
                    <!-- flowchart 箭头图标 勿删 -->
                    <svg xmlns="http://www.w3.org/2000/svg" style="display: none;">
                        <path stroke-linecap="round" d="M5,0 0,2.5 5,5z" id="raphael-marker-block" style="-webkit-tap-highlight-color: rgba(0, 0, 0, 0);"></path>
                    </svg>
                    <p></p><div class="toc"><h3><a name="t0"></a>文章目录</h3><ul><ul><ul><li><a href="#_1" rel="nofollow" target="_self">一、什么是预训练和微调?</a></li><li><a href="#_7" rel="nofollow" target="_self">二、预训练和微调的作用</a></li></ul></ul></ul></div><p></p>

一、什么是预训练和微调?

  • 预训练( p r e − t r a i n i n g / t r a i n e d p r e − t r a i n i n g / t r a i n e d p r e − t r a i n i n g / t r a i n e d pre−training/trainedpre−training/trained pre-training/trained pretraining/trainedpretraining/trainedpretraining/trainedInception 等模型都提供了自己的训练参数,以便人们可以拿来微调。这样既节省了时间和计算资源,又能很快的达到较好的效果。
  • 参考文献: https://www.jianshu.com/p/330ee6e7ceda

                </div>
                <link href="https://csdnimg.cn/release/phoenix/mdeditor/markdown_views-e44c3c0e64.css" rel="stylesheet">
                                </div>
用自有数据集 YOLO-World -s 用自有 yolo格式的热成像 人脸检测 训练数据集 微调 s_stage2-4466ab94.pth的背景下, 以下是 官方微调教程 Fine-tuning YOLO-World Fine-tuning YOLO-World is easy and we provide the samples for COCO object detection as a simple guidance. Fine-tuning Requirements Fine-tuning YOLO-World is cheap: it does not require 32 GPUs for multi-node distributed training. 8 GPUs or even 1 GPU is enough. it does not require the long schedule, e.g., 300 epochs or 500 epochs for training YOLOv5 or YOLOv8. 80 epochs or fewer is enough considering that we provide the good pre-trained weights. Data Preparation The fine-tuning dataset should have the similar format as the that of the pre-training dataset. We suggest you refer to docs/data for more details about how to build the datasets: if you fine-tune YOLO-World for close-set / custom vocabulary object detection, using MultiModalDataset with a text json is preferred. if you fine-tune YOLO-World for open-vocabulary detection with rich texts or grounding tasks, using MixedGroundingDataset is preferred. Hyper-parameters and Config Please refer to the config for fine-tuning YOLO-World-L on COCO for more details. Basic config file: If the fine-tuning dataset contains mask annotations: base = ('…/…/third_party/mmyolo/configs/yolov8/yolov8_l_mask-refine_syncbn_fast_8xb16-500e_coco.py') 复制 base = (‘…/…/third_party/mmyolo/configs/yolov8/yolov8_l_mask-refine_syncbn_fast_8xb16-500e_coco.py’) python If the fine-tuning dataset doesn’t contain mask annotations: base = ('…/…/third_party/mmyolo/configs/yolov8/yolov8_l_syncbn_fast_8xb16-500e_coco.py') 复制 base = (‘…/…/third_party/mmyolo/configs/yolov8/yolov8_l_syncbn_fast_8xb16-500e_coco.py’) python Training Schemes: Reducing the epochs and adjusting the learning rate _base_.val_interval_stage2)]) 复制 _base_.val_interval_stage2)]) python Datasets: _delete_=True, type=&#39;MultiModalDataset&#39;, type=&#39;YOLOv5CocoDataset&#39;, data_r
03-27
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值