CAANLP

Results 24 comments of CAANLP

> 自己的类别是76 ,训练时 ,提示这个错误,请问怎么解决的 你好,我也有一个问题想请教您,在我使用自己的数据集(10类别)使用train_seg.py进行训练时,出现了,和RuntimeError: shape '[42, 74, -1]' is invalid for input of size 38707200的报错。如果您能帮到我将万分感谢。

> 解决了吗 我遇到了同样的问题 你好,我也有一个问题想请教您,在我使用自己的数据集(10类别)使用train_seg.py进行训练时,出现了,和RuntimeError: shape '[42, 74, -1]' is invalid for input of size 38707200的报错。如果您能帮到我将万分感谢。

> Hi! Thank you for your help! I tried using the YOLOSegTrainer instead of the YOLOEPETrainer. But, unfortunately, when I try infering with the fine tuned model and the method...

> 我又搜索了一下,在 ultralytics github 上也发现了同样的问题[。](https://github.com/ultralytics/ultralytics/issues/19977)他们的回复里有一些建议。 你好,我也有一个问题想请教您,在我使用自己的数据集(10类别)使用train_seg.py进行训练时,出现了,和RuntimeError: shape '[42, 74, -1]' is invalid for input of size 38707200的报错。如果您能帮到我将万分感谢。

> 嗨!感谢团队的努力! > > 我根据您提供的带有边界框注释的自定义数据集上的这个 colab 笔记本对模型进行了微调:[https://colab.research.google.com/drive/1y-r4y_owfFAfyqbqP2t64H7IqjURkKwe?usp=sharing#scrollTo=Ez5mFaoZBL9o] > > 现在我想使用自定义模型并通过文本提示进行预测并使用以下代码: > > ``` > ``` > NAMES = ["needle"] # > > model = YOLOE("train2/weights/best.pt").cuda() > > model.set_classes(NAMES, model.get_text_pe(NAMES)) >...

你好,请问你这个问题解决了吗?我也出现了这个问题:ultralytics\utils\tal.py", line 342, in make_ancho h, w = feats[i].shape[2:] if isinstance(feats, list) else (int(feats[i][0]), int(feats[i][1])) ValueError: not enough values to unpack (expected 2, got 0)

> Hello, I used the yoloe-11l-seg-det.pt model loaded in yoloe-multi-source-predict-vp train train_vp.py, and the model loading showed AMP: checks passed, but when Starting training reported the above error, I printed...

> Hi,thanks the work.I want to build custom dataset for adding new categories.How can I train the model to maintain the open-set detection capability? May I ask if your issue...

> do u find ways to keep capability? May I ask if your issue has been resolved? Can you provide some guidance or constructive suggestions?