为什么你的param模型里有out0 out1 out2 我只有out0
为什么你的param模型里有out0 out1 out2 我只有out0
因为你没看我的知乎，导出的torchscript不对
File "C:\Users\Administrator\Desktop\yolov8-triplemu\ultralytics_init_.py", line 5, in
from ultralytics.hub import start
File "C:\Users\Administrator\Desktop\yolov8-triplemu\ultralytics\hub_init_.py", line 5, in
from ultralytics.hub.auth import Auth
File "C:\Users\Administrator\Desktop\yolov8-triplemu\ultralytics\hub\auth.py", line 5, in
from ultralytics.hub.utils import HUB_API_ROOT, PREFIX, request_with_credentials
File "C:\Users\Administrator\Desktop\yolov8-triplemu\ultralytics\hub\utils.py", line 14, in
from ultralytics.yolo.utils import (ENVIRONMENT, LOGGER, ONLINE, RANK, SETTINGS, TESTS_RUNNING, TQDM_BAR_FORMAT,
File "C:\Users\Administrator\Desktop\yolov8-triplemu\ultralytics\yolo_init_.py", line 3, in
from . import v8
File "C:\Users\Administrator\Desktop\yolov8-triplemu\ultralytics\yolo\v8_init_.py", line 3, in
from ultralytics.yolo.v8 import classify, detect, pose, segment
File "C:\Users\Administrator\Desktop\yolov8-triplemu\ultralytics\yolo\v8\classify_init_.py", line 4, in
from ultralytics.yolo.v8.classify.train import ClassificationTrainer, train
File "C:\Users\Administrator\Desktop\yolov8-triplemu\ultralytics\yolo\v8\classify\train.py", line 6, in
from ultralytics.nn.tasks import ClassificationModel, attempt_load_one_weight
File "C:\Users\Administrator\Desktop\yolov8-triplemu\ultralytics\nn\tasks.py", line 11, in
from ultralytics.nn.modules import (C1, C2, C3, C3TR, SPP, SPPF, Bottleneck, BottleneckCSP, C2f, C3Ghost, C3x, Classify,
File "C:\Users\Administrator\Desktop\yolov8-triplemu\ultralytics\nn\modules.py", line 558
return x, mc, p
^
IndentationError: unexpected indent
我改的V8源码下的ultralytics\nn\modules.py 内容 按知乎改的
我用ncnn官方仓库里的onnx2ncnn转出来的param里面就只有out0，然后ncnn自己的样例代码里面使用的又都是out0,out1,out2,令人费解
我用ncnn官方仓库里的onnx2ncnn转出来的param里面就只有out0，然后ncnn自己的样例代码里面使用的又都是out0,out1,out2,令人费解
我也有同样的疑问，yolov8转的onnx还是直接ncnn用可视化工具看都是一个输出，但是ncnn的样例需要三个输出。可视化对比了别人的三个输出的模型，发现一个输出的比三个输出的前面是一样的但后续多了很多流程，难道多的这些就是后处理？
ncnn-examples copied to clipboard
triple-Mu
