-
> python3 projects/IDOL/train_net.py --config-file projects/IDOL/configs/ytvis19_swinL.yaml --num-gpus 2
Traceback (most recent call last):
File "projects/IDOL/train_net.py", line 26, in
f…
-
### 问题确认 Search before asking
- [X] 我已经搜索过问题，但是没有找到解答。I have searched the question and found no related answer.
### 请提出你的问题 Please ask your question
RT-DETR是否可在边缘端设备或手机上部署？
-
相比于yolo系列，您的代码的数据增强并没有多少，那我就很好奇，如果rt-detr采用了更多的数据增强，比如yolo系列的，是否还能进一步涨点呢
-
@fmassa, could you please help me understand what's the purpose `mask` beside the image tensors? In particular, I am referring to the mask created here:
https://github.com/facebookresearch/detr/blo…
-
Hi!
I am observing CPU RAM memory leaks when training RT-DETR with PyTorch on multiple GPUs after the first evaluation. After that, the RAM usage increased from ~30GB to ~100GB, and continously inc…
-
Hi there @alcinos I have had great results using DETR in object detection but would like to extend this to segment the detected objects. How do I modify my existing object detection model for instance…
-
### 问题确认 Search before asking
- [X] 我已经搜索过问题，但是没有找到解答。I have searched the question and found no related answer.
### 请提出你的问题 Please ask your question
当使用DETR训练自己的数据集时，发现训练500个epoch以后，精度仍然非常低，mAP只有5…
-
### Model description
DFFT is a new fully Transformer-based object detector. The model doesn't require a decoder, unlike DETR.
### Open source status
- [X] The model implementation is available
- […
-
Hi, @lifuguan, thank you for your mmdetection implentation for UP-DETR, I'm trying to follow your work, but found that some details in the original paper is not implementated in this repo, e.g. the at…
-
when using trained model, 8% got this error
[1] 75076 killed python main.py --model allenai/unifiedqa-t5-base --user_msg rationale detr
resource_tracker.py:216: UserWarning: resource_tra…