数据集放在 datasets/coco_minitrain_10k
数据集目录结构如下:
datasets/
└── coco_mintrain_10k/
├── annotations/
│ ├── instances_train2017.json
│ ├── instances_val2017.json
│ ├── ... (其他标注文件)
├── train2017/
│ ├── 000000000001.jpg
│ ├── ... (其他训练图像)
├── val2017/
│ ├── 000000000001.jpg
│ ├── ... (其他验证图像)
└── test2017/
├── 000000000001.jpg
├── ... (其他测试图像)
conda creaet -n yolo11_py310 python=3.10
conda activate yolo11_py310
pip install -U -r train/requirements.txt
先下载预训练权重:
bash 0_download_wgts.sh
执行预测测试:
bash 1_run_predict_yolo11.sh
预测结果保存在 runs
文件夹下,效果如下:
已经准备好一键训练肩膀,直接执行训练脚本:
bash 2_run_train_yolo11.sh
其中其作用的代码很简单,就在 train/train_yolo11.py
中,如下:
# Load a model
model = YOLO(curr_path + "/wgts/yolo11n.pt")
# Train the model
train_results = model.train(
data= curr_path + "/cfg/coco128.yaml", # path to dataset YAML
epochs=100, # number of training epochs
imgsz=640, # training image size
device="0", # device to run on, i.e. device=0 or device=0,1,2,3 or device=cpu
)
# Evaluate model performance on the validation set
metrics = model.val()
主要就是配置一下训练参数,如数据集路径、训练轮数、显卡ID、图片大小等,然后执行训练即可
训练完成后,训练日志会在 runs/train
文件夹下,比如训练中 val 预测图片如下:
这样就完成了算法训练
使用 TensorRT 进行算法部署
直接执行一键导出ONNX脚本:
bash 3_run_export_onnx.sh
在脚本中已经对ONNX做了sim的简化
生成的ONNX以及_simONNX模型保存在wgts
文件夹下
直接去NVIDIA的官网下载(https://developer.nvidia.com/tensorrt/download)对应版本的tensorrt TAR包,解压基本步骤如下:
tar zxvf TensorRT-xxx-.tar.gz
# 软链trtexec
sudo ln -s /path/to/TensorRT/bin/trtexec /usr/local/bin
# 验证一下
trtexec --help
# 安装trt的python接口
cd python
pip install tensorrt-xxx.whl
直接执行一键生成trt模型引擎的脚本:
bash 4_build_trt_engine.sh
正常会在wgts
路径下生成yolo11n.engine,并有类似如下的日志:
[10/02/2024-21:28:48] [V] === Explanations of the performance metrics ===
[10/02/2024-21:28:48] [V] Total Host Walltime: the host walltime from when the first query (after warmups) is enqueued to when the last query is completed.
[10/02/2024-21:28:48] [V] GPU Compute Time: the GPU latency to execute the kernels for a query.
[10/02/2024-21:28:48] [V] Total GPU Compute Time: the summation of the GPU Compute Time of all the queries. If this is significantly shorter than Total Host Walltime, the GPU may be under-utilized because of host-side overheads or data transfers.
[10/02/2024-21:28:48] [V] Throughput: the observed throughput computed by dividing the number of queries by the Total Host Walltime. If this is significantly lower than the reciprocal of GPU Compute Time, the GPU may be under-utilized because of host-side overheads or data transfers.
[10/02/2024-21:28:48] [V] Enqueue Time: the host latency to enqueue a query. If this is longer than GPU Compute Time, the GPU may be under-utilized.
[10/02/2024-21:28:48] [V] H2D Latency: the latency for host-to-device data transfers for input tensors of a single query.
[10/02/2024-21:28:48] [V] D2H Latency: the latency for device-to-host data transfers for output tensors of a single query.
[10/02/2024-21:28:48] [V] Latency: the summation of H2D Latency, GPU Compute Time, and D2H Latency. This is the latency to infer a single query.
[10/02/2024-21:28:48] [I]
&&&& PASSED TensorRT.trtexec [TensorRT v100500] [b18] # trtexec --onnx=../wgts/yolo11n_sim.onnx --saveEngine=../wgts/yolo11n.engine --fp16 --verbose
直接执行一键推理脚本:
bash 5_infer_trt.sh
实际的trt推理脚本在 deploy/infer_trt.py
推理成功会有如下日志:
------ trt infer success! ------
推理结果保存在 deploy/output.jpg
如下:
好文章,需要你的鼓励
后来广为人知的“云上奥运”这一说法,正是从这一刻起走上历史舞台。云计算这一概念,也随之被越来越多的人所熟知。乘云科技CEO郝凯对此深有感受,因为在2017年春节过后不久,他的公司开始成为阿里云的合作伙伴,加入了滚滚而来的云计算大潮中。同一年,郝凯带领团队也第一次参加了阿里云的“双11”活动,实现了800万元的销售业绩。
随着各行各业数字化变革的不断深入,人类社会正加速迈向智能化。作为智能世界和数字经济的坚实底座,数据中心也迎来了蓬勃发展。面