-
I used the shunted transformer in mmdetection and found that the GPU memory usage is very high. Can you release the code for detection and segmentation?
-
### Feature request
Hi, I went through optimum's code base and could not find support for object detection models. Is there plan to add ORTModelForObjectDetection just like ORTModelForImageClassifica…
-
- I have finetuned Microsoft Model for Table Structure detection using this script [https://github.com/microsoft/table-transformer/tree/main#model-training](url)
- It has saved a .pth model object
-…
-
## Description
We have observed that the current implementation using Table Transformer is not achieving satisfactory performance in accurately detecting rows and columns within tables, particularly …
-
Thanks for your amazing work!
I'm sorry if this is a very basic question but I just got started with mmdet. How can I train the Swin-Transformer given in the configs and models for only the detection…
-
Hello @XianrenYty
Thank you for the great work..
How to leverage this framework for object detection/segmentation in transformers,?
Best,
@jaiswati
-
### 📚 The doc issue
Does Swin impl in this repo support arbitrary dynamic execution-time-defined input resolution (same as other backbones)?
Initially Swin was trained to support only one reso…
-
Reproduce:
Scan the following text locations with ScanCode 31.2.4:
|Incorrect detection | Text location
|--------------------|------------------------------|
|GPL-2.0-only AND LicenseRef-scanc…
-
I am using this snippet of code to augment a dataset:
```
augmentor = createAugmentor("detection", "coco", "coco", "linear", "/content/train", {"outputPath": "/content/train_new"})
transformer = tr…
ghost updated
3 years ago
-
Hi. Thank you for your contribution.
Can OTO be used for pruning Transformers? I want to apply it to a DETR-like object detection model(DINO:https://github.com/IDEA-Research/DINO). Is this feasible?…