[FishBotCamera]3.结合YOLO实现检测

[2431039560]

小鱼，这个用CPU会有点卡，可以用GPU吗，启动时代码改成gpu好像显示只能用cpu或者跳过

[小鱼]

@2431039560 这个要看yolo那边的了

[jkr]

ImportError: cannot import name 'Detect' from 'models.yolo' (/home/jkr/.local/lib/python3.10/site-packages/ultralytics/models/yolo/init.py)
[ros2run]: Process exited with failure 1
ros2 run yolov5_ros2 yolo_detect_2d --ros-args -p device:=cpu -p image_topic:=/fishbot_camera_raw
在输入这段代码后会显示这个错误

[jkr]

此回复已被删除！

[小鱼]

@jkr yolo安装问题吧，重装试试

[jkr]

@小鱼 重装了一边不太行

[jkr]

@小鱼 (1) In PyTorch 2.6, we changed the default value of the weights_only argument in torch.load from False to True. Re-running torch.load with weights_only set to False will likely succeed, but it can result in arbitrary code execution. Do it only if you got the file from a trusted source.
(2) Alternatively, to load with weights_only=True please check the recommended steps in the following error message.
WeightsUnpickler error: Unsupported global: GLOBAL numpy.core.multiarray._reconstruct was not an allowed global by default. Please use torch.serialization.add_safe_globals([numpy.core.multiarray._reconstruct]) or the torch.serialization.safe_globals([numpy.core.multiarray._reconstruct]) context manager to allowlist this global if you trust this class/function.
重运行完报这个错

[zxcpjp]

要怎么调节阈值啊@小鱼

[zxcpjp]

@小鱼 要怎么调节置信度阈值啊 @小鱼

[zxcpjp]

@zxcpjp 我知道了，是不是 ，修改代码为

    mask = predictions[:, 4] >= 0.6
    filtered_pred = predictions[mask]

    # 使用过滤后的结果
    boxes = filtered_pred[:, :4]
    scores = filtered_pred[:, 4]
    categories = filtered_pred[:, 5]

这样就修改为0.6了 @小鱼

[2648226346]

@小鱼 这个包一直下载失败，怎么解决

[luqixuan]

@2648226346 环境变量设置了吗

[2648226346]

@luqixuan 我是按照网页一步步来的

[2648226346]

@2648226346 环境变量具体是哪一步？