-
I am a newcomer. If I want to train my dataset, which parameters need to be modified and the number of classifications is below 80
-
Hi, Happy Spring Festival, thx for your great work!
I did a performance analysis on the inference of the torch code and it seems that the `reshape` operation in `FrozenBatchNorm2d` (`src/nn/backbon…
-
你好，我想问一下rtdetr的pytorch版本在训练开始是没有打印模型结构吗，如果是的话，我想问一下我想看模型结构，代码应该如何改呢
-
### Search before asking
- [X] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and found no similar feature requests.
### Description
When I train with the o…
-
I have added an option to switch to Timm backbones, and added a configuration for 'mobilenetv3_small_050.lamb_in1k' and 'resnet18.fb_swsl_ig1b_ft_in1k'
See my fork/commit:
https://github.com/ramon…
-
作者您好，请问rtdetr_pytorch配置文件中对学习率的设置是与GPU数量相关的吗？如果要在自己的数据集上进行微调，应该如何设置学习率？感谢！！
-
请问如果要更换主干网络的话，要在哪个文件中进行修改呢
-
Hi,
I tested an onnx model converted (by export_onnx.py) from a torch model (trained with config rtdetr_r50vd_6x). The onnx model is always much slower than the torch model, no matter the CPU, GPU,…
-
作者你好，
现在只有rtdetr_paddle里有infer程序，在torch版本里如何进行推断呢？还有paddle和torch训练出来的精度一样吗
-
https://github.com/lyuwenyu/RT-DETR/blob/main/rtdetr_pytorch/tools/export_onnx.py Line:78
这个逻辑是不是有点问题，dynamic变成了1的固定batchsize