运行时common.py报错

[Xiao-Qi-Guai]

报错：AttributeError: Can't get attribute 'SPPF' on <module 'models.common' from 'C:\Users\86153\yolov5-mosaic9\models\common.py'>

[positive666]

报错：AttributeError: Can't get attribute 'SPPF' on <module 'models.common' from 'C:\Users\86153\yolov5-mosaic9\models\common.py'>
请提供一个完整的运行命令

[Xiao-Qi-Guai]

(base) C:\Users\86153>activate yolov5

(yolov5) C:\Users\86153>cd yolov5-mosaic9

(yolov5) C:\Users\86153\yolov5-mosaic9>python train.py --data data/voc.yaml --cfg models/yolov5s.yaml --weights weights/yolov5s.pt --batch-size 4 --epochs 50
C:\Users\86153\anaconda3\envs\yolov5\lib\site-packages\torchvision\io\image.py:11: UserWarning: Failed to load image Python extension: Could not find module 'C:\Users\86153\anaconda3\envs\yolov5\Lib\site-packages\torchvision\image.pyd' (or one of its dependencies). Try using the full path with constructor syntax.
warn(f"Failed to load image Python extension: {e}")
Using torch 1.10.2 CUDA:0 (GeForce MX230, 2048MB)

Namespace(adam=False, batch_size=4, bucket='', cache_images=False, cfg='models/yolov5s.yaml', data='data/voc.yaml', device='', epochs=50, evolve=False, exist_ok=False, global_rank=-1, gr=1.0, hyp='data/hyp.scratch.yaml', image_weights=False, img_size=[640, 640], local_rank=-1, log_artifacts=False, log_imgs=16, multi_scale=False, name='exp', noautoanchor=False, nosave=False, notest=False, project='runs/train', quad=False, rect=False, resume=False, save_dir='runs\train\exp5', single_cls=False, sync_bn=False, total_batch_size=4, weights='weights/yolov5s.pt', workers=8, world_size=1)
Start Tensorboard with "tensorboard --logdir runs/train", view at http://localhost:6006/
Hyperparameters {'lr0': 0.01, 'lrf': 0.2, 'momentum': 0.937, 'weight_decay': 0.0005, 'warmup_epochs': 3.0, 'warmup_momentum': 0.8, 'warmup_bias_lr': 0.1, 'box': 0.05, 'cls': 0.3, 'cls_pw': 1.0, 'obj': 0.5, 'obj_pw': 1.0, 'iou_t': 0.2, 'anchor_t': 4.0, 'fl_gamma': 0.0, 'hsv_h': 0.015, 'hsv_s': 0.7, 'hsv_v': 0.4, 'degrees': 0.0, 'translate': 0.1, 'scale': 0.9, 'shear': 0.0, 'perspective': 0.0, 'flipud': 0.0, 'fliplr': 0.5, 'mosaic': 1.0, 'mixup': 0.01}
Traceback (most recent call last):
File "train.py", line 517, in
train(hyp, opt, device, tb_writer, wandb)
File "train.py", line 83, in train
ckpt = torch.load(weights, map_location=device) # load checkpoint
File "C:\Users\86153\anaconda3\envs\yolov5\lib\site-packages\torch\serialization.py", line 607, in load
return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args)
File "C:\Users\86153\anaconda3\envs\yolov5\lib\site-packages\torch\serialization.py", line 882, in _load
result = unpickler.load()
File "C:\Users\86153\anaconda3\envs\yolov5\lib\site-packages\torch\serialization.py", line 875, in find_class
return super().find_class(mod_name, name)
AttributeError: Can't get attribute 'SPPF' on <module 'models.common' from 'C:\Users\86153\yolov5-mosaic9\models\common.py'>

[Xiao-Qi-Guai]

这是我的运行命令和截图： (base) C:\Users\86153&gt;activate yolov5 (yolov5) C:\Users\86153&gt;cd yolov5-mosaic9 (yolov5) C:\Users\86153\yolov5-mosaic9&gt;python train.py --data data/voc.yaml --cfg models/yolov5s.yaml --weights weights/yolov5s.pt --batch-size 4 --epochs 50 C:\Users\86153\anaconda3\envs\yolov5\lib\site-packages\torchvision\io\image.py:11: UserWarning: Failed to load image Python extension: Could not find module 'C:\Users\86153\anaconda3\envs\yolov5\Lib\site-packages\torchvision\image.pyd' (or one of its dependencies). Try using the full path with constructor syntax. &nbsp; warn(f"Failed to load image Python extension: {e}") Using torch 1.10.2 CUDA:0 (GeForce MX230, 2048MB) Namespace(adam=False, batch_size=4, bucket='', cache_images=False, cfg='models/yolov5s.yaml', data='data/voc.yaml', device='', epochs=50, evolve=False, exist_ok=False, global_rank=-1, gr=1.0, hyp='data/hyp.scratch.yaml', image_weights=False, img_size=[640, 640], local_rank=-1, log_artifacts=False, log_imgs=16, multi_scale=False, name='exp', noautoanchor=False, nosave=False, notest=False, project='runs/train', quad=False, rect=False, resume=False, save_dir='runs\\train\\exp5', single_cls=False, sync_bn=False, total_batch_size=4, weights='weights/yolov5s.pt', workers=8, world_size=1) Start Tensorboard with "tensorboard --logdir runs/train", view at http://localhost:6006/ Hyperparameters {'lr0': 0.01, 'lrf': 0.2, 'momentum': 0.937, 'weight_decay': 0.0005, 'warmup_epochs': 3.0, 'warmup_momentum': 0.8, 'warmup_bias_lr': 0.1, 'box': 0.05, 'cls': 0.3, 'cls_pw': 1.0, 'obj': 0.5, 'obj_pw': 1.0, 'iou_t': 0.2, 'anchor_t': 4.0, 'fl_gamma': 0.0, 'hsv_h': 0.015, 'hsv_s': 0.7, 'hsv_v': 0.4, 'degrees': 0.0, 'translate': 0.1, 'scale': 0.9, 'shear': 0.0, 'perspective': 0.0, 'flipud': 0.0, 'fliplr': 0.5, 'mosaic': 1.0, 'mixup': 0.01} Traceback (most recent call last): &nbsp; File "train.py", line 517, in <module&gt; &nbsp; &nbsp; train(hyp, opt, device, tb_writer, wandb) &nbsp; File "train.py", line 83, in train &nbsp; &nbsp; ckpt = torch.load(weights, map_location=device)&nbsp; # load checkpoint &nbsp; File "C:\Users\86153\anaconda3\envs\yolov5\lib\site-packages\torch\serialization.py", line 607, in load &nbsp; &nbsp; return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args) &nbsp; File "C:\Users\86153\anaconda3\envs\yolov5\lib\site-packages\torch\serialization.py", line 882, in _load &nbsp; &nbsp; result = unpickler.load() &nbsp; File "C:\Users\86153\anaconda3\envs\yolov5\lib\site-packages\torch\serialization.py", line 875, in find_class &nbsp; &nbsp; return super().find_class(mod_name, name) AttributeError: Can't get attribute 'SPPF' on <module 'models.common' from 'C:\\Users\\86153\\yolov5-mosaic9\\models\\common.py'&gt; Message ID: ***@***.***&gt;

[positive666]

最后的错误应该是你的代码模型和 你的权重存在冲突

[Xiao-Qi-Guai]

&nbsp; &nbsp;是不是因为我下载的模型是yolov5-3.1，但是权重文件是对应yolov5-6.1？我还有一个问题，就是如果我想在在输入的时候把4拼换成9拼，只需要根据您发的源码，直接替换load_mosaic函数就可以？

[positive666]

   是不是因为我下载的模型是yolov5-3.1，但是权重文件是对应yolov5-6.1？我还有一个问题，就是如果我想在在输入的时候把4拼换成9拼，只需要根据您发的源码，直接替换load_mosaic函数就可以？

估计是你的代码和权重不匹配，我的代码是最新的一般 MOSAIC的话，你直接看作者源码逻辑里如何启动调用就行 这部分逻辑没区别的

[Xiao-Qi-Guai]

好的，十分感谢你，我再看看作者的源码。

…

------------------&nbsp;原始邮件&nbsp;------------------ 发件人: "positive666/yolov5_research" ***@***.***&gt;; 发送时间:&nbsp;2022年4月6日(星期三) 下午4:08 ***@***.***&gt;; ***@***.***&gt;;"State ***@***.***&gt;; 主题:&nbsp;Re: [positive666/yolov5_research] 运行时common.py报错 (Issue #16) &nbsp; &nbsp;是不是因为我下载的模型是yolov5-3.1，但是权重文件是对应yolov5-6.1？我还有一个问题，就是如果我想在在输入的时候把4拼换成9拼，只需要根据您发的源码，直接替换load_mosaic函数就可以？ 估计是你的代码和权重不匹配，我的代码是最新的一般 MOSAIC的话，你直接看作者源码逻辑里如何启动调用就行 这部分逻辑没区别的 — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you modified the open/close state.Message ID: ***@***.***&gt;

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.