-
Hi,It's me again,I'm new to this. so there's a lot I don't understand.Sorry to bother you again and again.
1、when I finish training,I got a log.txt file,and then I ran the plot_utils.py to read the l…
-
### Question
请问我想把image_size修改为1248x832，我应该在哪里修改
### 补充信息
_No response_
-
我根据readme训练了dancetrack数据集，训练完成后提交到dancetrack评估失败了。
我下载了仓库中的权重，测试发现可以正常提交。
我的训练指令：
````
python -m torch.distributed.run --nproc_per_node=2 main.py \
--mode train \
--use-d…
-
## 背景
PyTorch 最近在 2.1.0 版本发布了 `torch.export` 功能，提供了以 PyTorch 2.x 的 dynamo 为核心的模型导出方法。其功能上与我们 Paddle 动转静模型导出 `paddle.jit.save` 相类似，因此我们想要建设一个 repo 能够自动对比 `torch.export` 和 `paddle.jit.save` 的导出成功与否，[…
-
Hi, thanks for your great work!
I'd like to know if the deformable transformer can be used by another package because the environment in my project conflicts with mmcv, and its source code behaves ba…
-
Thanks for the great work!
In the paper, the authors use MViT to extract high-quality class-specific proposals using image-level labels based on its great generalization ability. Thus, a straightfo…
fushh updated
10 months ago
-
### 是否愿意提交PR Are you willing to submit a PR?
- [X] Yes I'd like to help by submitting a PR!
-
Hi,
I just wanted to know if it can be used as an object detection model too for detecting bounding Boxes etc for the documents.
I have [asked a similar question here](https://stackoverflow.com/q…
-
Hi, thank you for your great contribution.
As you have mentioned in [#99 ](https://github.com/lyuwenyu/RT-DETR/issues/99#issuecomment-1779196475) target boxes are converted to `XYXY` then to `CXCY`.…
-
### bug描述 Describe the Bug
我目前的工作是把GroundDino这个模型，部署在paddle_inference上，使用C++推理。
在开发过程中，我发现原生的GroundDino模型，在pytorch环境下，同一张图，推理一次仅需要300ms，而paddle实现的代码工程，推理同一张图需要850ms，请问有没有可以指导一下不？或者可以指出一下排查方向不？
pa…