EOT

README.md

@@ -0,0 +1,49 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+datasets:
+- doc_lay_net
+model-index:
+- name: Deformable-DETR-Document-Layout-Analyzer
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Deformable-DETR-Document-Layout-Analyzer
+
+This model was trained from scratch on the doc_lay_net dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 24
+- eval_batch_size: 24
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 2
+
+### Framework versions
+
+- Transformers 4.49.0
+- Pytorch 2.6.0+cu124
+- Datasets 2.21.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,85 @@
+{
+  "_name_or_path": "/home/ubuntu/DETR/Deformable-DETR-Document-Layout-Analyzer/checkpoint-17500",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "DeformableDetrForObjectDetection"
+  ],
+  "attention_dropout": 0.0,
+  "auxiliary_loss": true,
+  "backbone": "resnet50",
+  "backbone_config": null,
+  "backbone_kwargs": {
+    "in_chans": 3,
+    "out_indices": [
+      2,
+      3,
+      4
+    ]
+  },
+  "bbox_cost": 5,
+  "bbox_loss_coefficient": 5,
+  "class_cost": 1,
+  "d_model": 256,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 1024,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_n_points": 4,
+  "dice_loss_coefficient": 1,
+  "dilation": false,
+  "disable_custom_kernels": false,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 1024,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "encoder_n_points": 4,
+  "eos_coefficient": 0.1,
+  "focal_alpha": 0.25,
+  "giou_cost": 2,
+  "giou_loss_coefficient": 2,
+  "id2label": {
+    "0": "Caption",
+    "1": "Footnote",
+    "2": "Formula",
+    "3": "List-item",
+    "4": "Page-footer",
+    "5": "Page-header",
+    "6": "Picture",
+    "7": "Section-header",
+    "8": "Table",
+    "9": "Text",
+    "10": "Title"
+  },
+  "init_std": 0.02,
+  "init_xavier_std": 1.0,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "Caption": 0,
+    "Footnote": 1,
+    "Formula": 2,
+    "List-item": 3,
+    "Page-footer": 4,
+    "Page-header": 5,
+    "Picture": 6,
+    "Section-header": 7,
+    "Table": 8,
+    "Text": 9,
+    "Title": 10
+  },
+  "mask_loss_coefficient": 1,
+  "max_position_embeddings": 1024,
+  "model_type": "deformable_detr",
+  "num_channels": 3,
+  "num_feature_levels": 4,
+  "num_queries": 300,
+  "position_embedding_type": "sine",
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "two_stage": false,
+  "two_stage_num_proposals": 300,
+  "use_pretrained_backbone": true,
+  "use_timm_backbone": true,
+  "with_box_refine": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9cbca200dd66928dd7c765bfe20d9594a1c06e46f4598c636e4f59ce0acb882
+size 160686748

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "do_convert_annotations": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "format": "coco_detection",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "DeformableDetrImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "pad_size": null,
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 1333,
+    "shortest_edge": 800
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:663f79a578a02dafa6a93a8ca91530fe051c9ac65bbebc404eac4154c79f943c
+size 5368