Duplicate from PaddlePaddle/PP-DocLayout_plus-L_safetensors

Co-authored-by: Yizhan Huang <Bvicii@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,48 @@
+---
+license: apache-2.0
+library_name: PaddleOCR
+language:
+- en
+- zh
+pipeline_tag: image-to-text
+tags:
+- OCR
+- PaddlePaddle
+- PaddleOCR
+- layout_detection
+---
+
+# PP-DocLayout_plus-L
+
+## Introduction
+
+A higher-precision layout area localization model trained on a self-built dataset containing Chinese and English papers, PPT, multi-layout magazines, contracts, books, exams, ancient books and research reports using RT-DETR-L. The layout detection model includes 20 common categories: document title, paragraph title, text, page number, abstract, table, references, footnotes, header, footer, algorithm, formula, formula number, image, table, seal, figure_table title, chart, and sidebar text and lists of references. The key metrics are as follow:
+
+| Model| mAP(0.5) (%) | 
+|  --- | --- | 
+|PP-DocLayout_plus-L |  83.2 | 
+
+**Note**: the evaluation set of the above precision indicators is the self built version sub area detection data set, including Chinese and English papers, magazines, newspapers, research reports PPT、 1000 document type pictures such as test papers and textbooks.
+
+## Model Usage
+
+```python
+import requests
+from PIL import Image
+from transformers import AutoImageProcessor, AutoModelForObjectDetection
+
+model_path = "PaddlePaddle/PP-DocLayout_plus-L_safetensors"
+model = AutoModelForObjectDetection.from_pretrained(model_path)
+image_processor = AutoImageProcessor.from_pretrained(model_path)
+
+image = Image.open(requests.get("https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/layout.jpg", stream=True).raw)
+inputs = image_processor(images=image, return_tensors="pt")
+
+outputs = model(**inputs)
+results = image_processor.post_process_object_detection(outputs, target_sizes=[image.size[::-1]])
+for result in results:
+    for score, label_id, box in zip(result["scores"], result["labels"], result["boxes"]):
+        score, label = score.item(), label_id.item()
+        box = [round(i, 2) for i in box.tolist()]
+        print(f"{model.config.id2label[label]}: {score:.2f} {box}")
+```

config.json

@@ -0,0 +1,232 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "silu",
+  "anchor_image_size": null,
+  "attention_dropout": 0.0,
+  "auxiliary_loss": true,
+  "backbone_config": {
+    "arch": "L",
+    "depths": [
+      3,
+      4,
+      6,
+      3
+    ],
+    "embedding_size": 64,
+    "hidden_act": "relu",
+    "hidden_sizes": [
+      256,
+      512,
+      1024,
+      2048
+    ],
+    "initializer_range": 0.02,
+    "model_type": "hgnet_v2",
+    "num_channels": 3,
+    "out_features": [
+      "stage2",
+      "stage3",
+      "stage4"
+    ],
+    "out_indices": [
+      2,
+      3,
+      4
+    ],
+    "stage_downsample": [
+      false,
+      true,
+      true,
+      true
+    ],
+    "stage_downsample_strides": [
+      2,
+      2,
+      2,
+      2
+    ],
+    "stage_in_channels": [
+      48,
+      128,
+      512,
+      1024
+    ],
+    "stage_kernel_size": [
+      3,
+      3,
+      5,
+      5
+    ],
+    "stage_light_block": [
+      false,
+      false,
+      true,
+      true
+    ],
+    "stage_mid_channels": [
+      48,
+      96,
+      192,
+      384
+    ],
+    "stage_names": [
+      "stem",
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4"
+    ],
+    "stage_num_blocks": [
+      1,
+      1,
+      3,
+      1
+    ],
+    "stage_numb_of_layers": [
+      6,
+      6,
+      6,
+      6
+    ],
+    "stage_out_channels": [
+      128,
+      512,
+      1024,
+      2048
+    ],
+    "stem_channels": [
+      3,
+      32,
+      48
+    ],
+    "stem_strides": [
+      2,
+      1,
+      1,
+      2,
+      1
+    ],
+    "use_learnable_affine_block": false,
+    "return_idx": [
+      1,
+      2,
+      3
+    ],
+    "freeze_stem_only": true,
+    "freeze_at": 0,
+    "freeze_norm": false,
+    "lr_mult_list": [
+      0.05,
+      0.05,
+      0.1,
+      0.15,
+      0.2
+    ]
+  },
+  "batch_norm_eps": 1e-05,
+  "box_noise_scale": 1.0,
+  "d_model": 256,
+  "decoder_activation_function": "relu",
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 1024,
+  "decoder_in_channels": [
+    256,
+    256,
+    256
+  ],
+  "decoder_layers": 6,
+  "decoder_n_points": 4,
+  "disable_custom_kernels": true,
+  "dropout": 0.0,
+  "encode_proj_layers": [
+    2
+  ],
+  "encoder_activation_function": "gelu",
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 1024,
+  "encoder_hidden_dim": 256,
+  "encoder_in_channels": [
+    512,
+    1024,
+    2048
+  ],
+  "encoder_layers": 1,
+  "eos_coefficient": 0.0001,
+  "eval_size": null,
+  "feat_strides": [
+    8,
+    16,
+    32
+  ],
+  "focal_loss_alpha": 0.75,
+  "focal_loss_gamma": 2.0,
+  "freeze_backbone_batch_norms": true,
+  "hidden_expansion": 1.0,
+  "id2label": {
+    "0": "paragraph_title",
+    "1": "image",
+    "10": "doc_title",
+    "11": "footnote",
+    "12": "header",
+    "13": "algorithm",
+    "14": "footer",
+    "15": "seal",
+    "16": "chart",
+    "17": "formula_number",
+    "18": "aside_text",
+    "19": "reference_content",
+    "2": "text",
+    "3": "number",
+    "4": "abstract",
+    "5": "content",
+    "6": "figure_title",
+    "7": "formula",
+    "8": "table",
+    "9": "reference"
+  },
+  "initializer_bias_prior_prob": null,
+  "initializer_range": 0.01,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "abstract": 4,
+    "algorithm": 13,
+    "aside_text": 18,
+    "chart": 16,
+    "content": 5,
+    "doc_title": 10,
+    "figure_title": 6,
+    "footer": 14,
+    "footnote": 11,
+    "formula": 7,
+    "formula_number": 17,
+    "header": 12,
+    "image": 1,
+    "number": 3,
+    "paragraph_title": 0,
+    "reference": 9,
+    "reference_content": 19,
+    "seal": 15,
+    "table": 8,
+    "text": 2
+  },
+  "label_noise_ratio": 0.5,
+  "layer_norm_eps": 1e-05,
+  "learn_initial_query": false,
+  "matcher_alpha": 0.25,
+  "matcher_bbox_cost": 5.0,
+  "matcher_class_cost": 2.0,
+  "matcher_gamma": 2.0,
+  "matcher_giou_cost": 2.0,
+  "model_type": "rt_detr",
+  "normalize_before": false,
+  "num_denoising": 100,
+  "num_feature_levels": 3,
+  "num_queries": 300,
+  "positional_encoding_temperature": 10000,
+  "transformers_version": "5.3.0.dev0",
+  "use_focal_loss": true,
+  "weight_loss_bbox": 5.0,
+  "weight_loss_giou": 2.0,
+  "weight_loss_vfl": 1.0,
+  "with_box_refine": true
+}

inference.yml

@@ -0,0 +1,123 @@
+mode: paddle
+draw_threshold: 0.5
+metric: COCO
+use_dynamic_shape: false
+Global:
+  model_name: PP-DocLayout_plus-L
+arch: DETR
+min_subgraph_size: 3
+Preprocess:
+- interp: 2
+  keep_ratio: false
+  target_size:
+  - 800
+  - 800
+  type: Resize
+- mean:
+  - 0.0
+  - 0.0
+  - 0.0
+  norm_type: none
+  std:
+  - 1.0
+  - 1.0
+  - 1.0
+  type: NormalizeImage
+- type: Permute
+label_list:
+- paragraph_title
+- image
+- text
+- number
+- abstract
+- content
+- figure_title
+- formula
+- table
+- reference
+- doc_title
+- footnote
+- header
+- algorithm
+- footer
+- seal
+- chart
+- formula_number
+- aside_text
+- reference_content
+Hpi:
+  backend_configs:
+    paddle_infer:
+      trt_dynamic_shapes: &id001
+        im_shape:
+        - - 1
+          - 2
+        - - 1
+          - 2
+        - - 8
+          - 2
+        image:
+        - - 1
+          - 3
+          - 800
+          - 800
+        - - 1
+          - 3
+          - 800
+          - 800
+        - - 8
+          - 3
+          - 800
+          - 800
+        scale_factor:
+        - - 1
+          - 2
+        - - 1
+          - 2
+        - - 8
+          - 2
+      trt_dynamic_shape_input_data:
+        im_shape:
+        - - 800
+          - 800
+        - - 800
+          - 800
+        - - 800
+          - 800
+          - 800
+          - 800
+          - 800
+          - 800
+          - 800
+          - 800
+          - 800
+          - 800
+          - 800
+          - 800
+          - 800
+          - 800
+          - 800
+          - 800
+        scale_factor:
+        - - 2
+          - 2
+        - - 1
+          - 1
+        - - 0.67
+          - 0.67
+          - 0.67
+          - 0.67
+          - 0.67
+          - 0.67
+          - 0.67
+          - 0.67
+          - 0.67
+          - 0.67
+          - 0.67
+          - 0.67
+          - 0.67
+          - 0.67
+          - 0.67
+          - 0.67
+    tensorrt:
+      dynamic_shapes: *id001

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa00c2cf5285eeec58c47d5c91d0950f34d61af8a2a484137790278cca899b98
+size 131776256

preprocessor_config.json

@@ -0,0 +1,36 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_processor_type": "RTDetrImageProcessor",
+  "image_mean": [
+    0,
+    0,
+    0
+  ],
+  "image_std": [
+    1,
+    1,
+    1
+  ],
+  "rescale_factor": 0.00392156862745098,
+  "resample": 3,
+  "size": {
+    "height": 800,
+    "width": 800
+  }
+}