YOLOv8训练致笔记本关机问题咨询及硬件需求查询

一、笔记本硬件配置 #

Processor : AMD Ryzen 7 4800H with Radeon Graphics            2.90 GHz
Installed RAM : 16.0 GB (15.4 GB usable)
Windows Edition : Windows 11 Home Single Language
Version : 22H2
OS : 22621.1555
NVIDIA GTX GEFORCE 1650 GRAPHICS CARD
NVIDIA DRIVER : 31.0.15.3161

二、已安装的Python及CUDA环境 #

Python 3.10.11

---------------------------------------------------------------------------------------+
| NVIDIA-SMI 531.61                 Driver Version: 531.61       CUDA Version: 12.1     |
|-----------------------------------------+----------------------+----------------------+ 
| GPU  Name                      TCC/WDDM | Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf            Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|                                         |                      |               MIG M. |
|=========================================+======================+======================|
|   0  NVIDIA GeForce GTX 1650       WDDM | 00000000:01:00.0 Off |                  N/A |
| N/A   44C    P0               15W /  N/A|      0MiB /  4096MiB |      0%      Default |
|                                         |                      |                  N/A |
+-----------------------------------------+----------------------+----------------------+

+---------------------------------------------------------------------------------------+
| Processes:                                                                            |
|  GPU   GI   CI        PID   Type   Process name                            GPU Memory |
|        ID   ID                                                             Usage      |
|=======================================================================================|
|  No running processes found                                                           |
+---------------------------------------------------------------------------------------+

三、问题描述 #

运行以下Python代码进行YOLOv8目标检测模型训练时，笔记本在第一个epoch就会关机，需排查原因：

import tensorflow as tf
from ultralytics import YOLO
print("Num GPUs Available: ", len(tf.config.list_physical_devices('GPU')))
print(tf.test.is_built_with_cuda())
print(tf.config.list_physical_devices('GPU'))

# Create a TensorFlow session with GPU growth enabled
config = tf.compat.v1.ConfigProto()
config.gpu_options.allow_growth = True
sess = tf.compat.v1.Session(config=config)
physical_devices = tf.config.list_physical_devices('GPU')
tf.config.experimental.set_memory_growth(physical_devices[0], True)
print(tf.test.is_built_with_cuda())
# Run your code in the session
with sess.as_default():
   # Load the model.
   model = YOLO('yolov8n.pt')
   
   # Training.
   results = model.train(
      data='data.yaml',
      imgsz=640,
      epochs=5,
      batch=8,
      name='yolov8n_custom')

四、额外咨询 #

希望了解YOLOv8的硬件要求。

内容的提问来源于stack exchange，提问作者SomeCrazyProgrammer