Instructions to use SenseTime/deformable-detr-single-scale with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SenseTime/deformable-detr-single-scale with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("object-detection", model="SenseTime/deformable-detr-single-scale")# Load model directly from transformers import AutoImageProcessor, AutoModelForObjectDetection processor = AutoImageProcessor.from_pretrained("SenseTime/deformable-detr-single-scale") model = AutoModelForObjectDetection.from_pretrained("SenseTime/deformable-detr-single-scale") - Notebooks
- Google Colab
- Kaggle
Memory issue with Deformable DETR
#2
by Kc6699c - opened
I am using Deformable DETR, I have a H100 server to experiment. However the memory usage is very high. The image resolution is 376p, the total training images is 6500 but the utilisation of the total VRAM during training is 95GB on H100 server. Is it expected? Any memory leak issues?