Object Detection
Transformers
Safetensors
rt_detr_v2
document-layout-analysis
finance
rtdetr-v2
cuda
tf32
Instructions to use AutomatosX/AXDocLayout-M-v1.5-CUDA-TF32 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AutomatosX/AXDocLayout-M-v1.5-CUDA-TF32 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("object-detection", model="AutomatosX/AXDocLayout-M-v1.5-CUDA-TF32")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForObjectDetection tokenizer = AutoTokenizer.from_pretrained("AutomatosX/AXDocLayout-M-v1.5-CUDA-TF32") model = AutoModelForObjectDetection.from_pretrained("AutomatosX/AXDocLayout-M-v1.5-CUDA-TF32", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Publish owner-selected H5.1 as v1.5 with qualified CUDA profile and preserved tradeoffs
6536f3b verified Download preprocessor_config.json from AutomatosX/AXDocLayout-M-v1.5-CUDA-TF32: direct link, hf CLI and curl.
- Browser
- Download file 444 Bytes
-
https://huggingface.co/AutomatosX/AXDocLayout-M-v1.5-CUDA-TF32/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://AutomatosX/AXDocLayout-M-v1.5-CUDA-TF32/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/AutomatosX/AXDocLayout-M-v1.5-CUDA-TF32/resolve/main/preprocessor_config.json
444 Bytes
| { | |
| "do_convert_annotations": true, | |
| "do_normalize": false, | |
| "do_pad": false, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "format": "coco_detection", | |
| "image_mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "image_processor_type": "RTDetrImageProcessor", | |
| "image_std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| "pad_size": null, | |
| "resample": 2, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "height": 640, | |
| "width": 640 | |
| } | |
| } | |