-
### Describe the bug
I installed text generation webui and downloaded the model(TheBloke_Yarn-Mistral-7B-128k-AWQ) and I can't run it. I chose Transofmer as Model loader. I tried installing autoawq b…
-
Hello, thanks for your contributions to RT-DETR! @lyuwenyu
And is there any code in place to save the predictions while inference? I haven't seen relevent setup yet. Could you please tell me more …
-
请问RT-DETR在测试速度时，是否包括后处理过程
```python
results = postprocessors(outputs, orig_target_sizes)
```
-
首先是模型在resume过程中出错，具体原因是模型的字典没有对应上。
如上图所示，下载得到的模型的权重对应在module中而不是model中，并且model应该在第一层级上而不是在ema中。
以上问题我通过修改key值能够解决。
其次是将修改后的模型进行test，得到的结果为0，如下图所示。
测试从pytorch代码中训练出来的模型则具有正常结果，如下图所示。
-
目前都是CV领域的应用，目标检测和语义分割占多数，他们分别有没有负样本的功能？
-
I have found the pretrained models for paddle version, but the pytorch pretrained model seems not be released.
-
Hi, thanks for all the work with the repo @marcoslucianops . I noticed an issue when exporting a RT-DETR pytorch model for earlier versions of deepstream (6.0.1) with the --simplify tag.
Specifica…
-
**Thanks your Great Work**
是否可以提供onnx和pytorch版本模型对应的推理时间或fps，最终trt版本的推理速度和论文没法对齐，想逐步排查问题所在
-
为什么base_ds = [get_coco_api_from_dataset(self.val_dataloader.dataset)这里是val_dataloader，不是在训练吗？
[https://github.com/lyuwenyu/RT-DETR/blob/5b628eaa0a2fc25bdafec7e6148d5296b144af85/rtdetr_pytorch/src/sol…
-
We keep this issue open to collect feature requests from users and hear your voice.
You can either:
- Suggest a new feature by leaving a comment.
- Vote for a feature request with 👍. (Remember …