Instructions to use merve/rfdetr-docvqa-media3-trainval-agree1-medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use merve/rfdetr-docvqa-media3-trainval-agree1-medium with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("object-detection", model="merve/rfdetr-docvqa-media3-trainval-agree1-medium")# Load model directly from transformers import AutoImageProcessor, AutoModelForObjectDetection processor = AutoImageProcessor.from_pretrained("merve/rfdetr-docvqa-media3-trainval-agree1-medium") model = AutoModelForObjectDetection.from_pretrained("merve/rfdetr-docvqa-media3-trainval-agree1-medium") - Notebooks
- Google Colab
- Kaggle
| { | |
| "activation_dropout": 0.0, | |
| "activation_function": "silu", | |
| "architectures": [ | |
| "RfDetrForObjectDetection" | |
| ], | |
| "attention_bias": true, | |
| "attention_dropout": 0.0, | |
| "auxiliary_loss": true, | |
| "backbone_config": { | |
| "apply_layernorm": true, | |
| "attention_probs_dropout_prob": 0.0, | |
| "drop_path_rate": 0.0, | |
| "dtype": "float32", | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.0, | |
| "hidden_size": 384, | |
| "image_size": 576, | |
| "initializer_range": 0.02, | |
| "layer_norm_eps": 1e-06, | |
| "layerscale_value": 1.0, | |
| "mlp_ratio": 4, | |
| "model_type": "rf_detr_dinov2", | |
| "num_attention_heads": 6, | |
| "num_channels": 3, | |
| "num_hidden_layers": 12, | |
| "num_windows": 2, | |
| "out_features": [ | |
| "stage3", | |
| "stage6", | |
| "stage9", | |
| "stage12" | |
| ], | |
| "out_indices": [ | |
| 3, | |
| 6, | |
| 9, | |
| 12 | |
| ], | |
| "patch_size": 16, | |
| "qkv_bias": true, | |
| "reshape_hidden_states": true, | |
| "stage_names": [ | |
| "stem", | |
| "stage1", | |
| "stage2", | |
| "stage3", | |
| "stage4", | |
| "stage5", | |
| "stage6", | |
| "stage7", | |
| "stage8", | |
| "stage9", | |
| "stage10", | |
| "stage11", | |
| "stage12" | |
| ], | |
| "use_mask_token": true, | |
| "use_swiglu_ffn": false, | |
| "window_block_indexes": [ | |
| 0, | |
| 1, | |
| 2, | |
| 4, | |
| 5, | |
| 7, | |
| 8, | |
| 10, | |
| 11 | |
| ] | |
| }, | |
| "bbox_cost": 5, | |
| "bbox_loss_coefficient": 5, | |
| "c2f_num_blocks": 3, | |
| "class_cost": 2, | |
| "class_loss_coefficient": 1, | |
| "d_model": 256, | |
| "decoder_activation_function": "relu", | |
| "decoder_cross_attention_heads": 16, | |
| "decoder_ffn_dim": 2048, | |
| "decoder_layers": 4, | |
| "decoder_n_points": 2, | |
| "decoder_self_attention_heads": 8, | |
| "dice_loss_coefficient": 1, | |
| "disable_custom_kernels": true, | |
| "dropout": 0.1, | |
| "dtype": "float32", | |
| "eos_coefficient": 0.1, | |
| "focal_alpha": 0.25, | |
| "giou_cost": 2, | |
| "giou_loss_coefficient": 2, | |
| "group_detr": 13, | |
| "hidden_expansion": 0.5, | |
| "id2label": { | |
| "0": "chart", | |
| "1": "image", | |
| "2": "signature" | |
| }, | |
| "init_std": 0.02, | |
| "intermediate_size": 1024, | |
| "label2id": { | |
| "chart": 0, | |
| "image": 1, | |
| "signature": 2 | |
| }, | |
| "layer_norm_eps": 1e-05, | |
| "mask_class_loss_coefficient": 5.0, | |
| "mask_dice_loss_coefficient": 5.0, | |
| "mask_downsample_ratio": 4, | |
| "mask_loss_coefficient": 1, | |
| "mask_point_sample_ratio": 16, | |
| "model_type": "rf_detr", | |
| "num_feature_levels": 1, | |
| "num_queries": 300, | |
| "projector_scale_factors": [ | |
| 1.0 | |
| ], | |
| "segmentation_head_activation_function": "gelu", | |
| "transformers_version": "5.12.1", | |
| "use_cache": false | |
| } | |