-
I use my custom dataset to train, but when i finish a eval (not first eval ,but the maybe 7th) an "AssertionError" occur : AssertionError: A prediction has class=6, but the dataset only has 5 classes …
-
Hi, Deformable Detr origin git can support different batch_size.
Why MOTR V2 only support batch_size ==1 ?
-
v2.x： https://github.com/open-mmlab/mmdetection/blob/2.x/mmdet/models/dense_heads/deformable_detr_head.py#L183
How to implement the same function in v3.x?
-
### Question
您好，请问在模型微调方面，除了对backbone进行冻结某些层进行微调完，还有其他微调方式吗？可以引入Lora等参数高效微调的方法吗？另外可以对transformer层进行什么样的微调吗
### 补充信息
_No response_
-
Unread papers that might give a new idea:
- [ ] [Attention Augmented Convolutional Networks](https://arxiv.org/abs/1904.09925)
- [ ] [Instances as Queries](https://arxiv.org/abs/2105.01928)
- [x] [Se…
-
-
Hi Marcos,
Can you please explain the motivation for changing the models output format in [this commit](https://github.com/marcoslucianops/DeepStream-Yolo/commit/b451b036b2fa9f8b92cb13bb5f4585f8883…
-
HPR adds huge training cost to baselines:
1. all three branches need bipartite matching to calculate losses
2. Data Re-Augmentation doubles the training images (possibly equals to more training sche…
fushh updated
3 months ago
-
如果想给RT-DETR换detection库的ppdet里的主干的话，主干网络的预训练权重在哪下载（backbone里没给出链接），是否可以用clas库里的预训练权重
-
hi,
torchrun --nproc_per_node=4 tools/train.py -c configs/rtdetr/rtdetr_r50vd_6x_coco.yml
when I try to train with multi-gpu command, Runtime error occured.
what is that mean?
Averaged sta…