Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,37 @@
-*.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
+*.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
+Recognition/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Structure/PP-DocLayout_plus-L/inference.pdiparams filter=lfs diff=lfs merge=lfs -text

Recognition/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

Recognition/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

Recognition/config.json

@@ -0,0 +1,113 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 70,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 2,
+  "quantization_config": {
+    "bits": 4,
+    "group_size": 128,
+    "quant_method": "awq",
+    "version": "gemm",
+    "zero_point": true
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "text_config": {
+    "_name_or_path": "MonkeyOCR-1.2B-0709",
+    "architectures": [
+      "Qwen2_5_VLForConditionalGeneration"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "image_token_id": null,
+    "initializer_range": 0.02,
+    "intermediate_size": 11008,
+    "max_position_embeddings": 128000,
+    "max_window_layers": 70,
+    "model_type": "qwen2_5_vl_text",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 12,
+    "num_key_value_heads": 2,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_section": [
+        16,
+        24,
+        24
+      ],
+      "rope_type": "default",
+      "type": "default"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": 32768,
+    "tie_word_embeddings": true,
+    "torch_dtype": "float32",
+    "use_cache": false,
+    "use_sliding_window": false,
+    "video_token_id": null,
+    "vision_end_token_id": 151653,
+    "vision_start_token_id": 151652,
+    "vision_token_id": 151654,
+    "vocab_size": 151936
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "in_channels": 3,
+    "in_chans": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 3420,
+    "model_type": "qwen2_5_vl",
+    "num_heads": 16,
+    "out_hidden_size": 2048,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "torch_dtype": "float32",
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 151936
+}

Recognition/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.1,
+  "top_k": 1,
+  "top_p": 0.001,
+  "transformers_version": "4.50.0.dev0"
+}

Recognition/inputs_stats.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c22316a388263bafc234f1def98ffbdacaa3730fa3688f251756c8bfc74a5c90
+size 5710002

Recognition/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0669f5e982744527eb71177f7861f0b3515aec4aa7e7abf66d27604ae50e841f
+size 4414737960

Recognition/outputs_stats.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00325e1830bdf0ddaaa002010ea4e686259f2ba19ef35f2d5868898bb7b22d11
+size 8985570

Recognition/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

Recognition/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Recognition/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

Recognition/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 8196,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

Relation/config.json

@@ -0,0 +1,1063 @@
+{
+  "architectures": [
+    "LayoutLMv3ForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "coordinate_size": 171,
+  "eos_token_id": 2,
+  "has_relative_attention_bias": true,
+  "has_spatial_attention_bias": true,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27",
+    "28": "LABEL_28",
+    "29": "LABEL_29",
+    "30": "LABEL_30",
+    "31": "LABEL_31",
+    "32": "LABEL_32",
+    "33": "LABEL_33",
+    "34": "LABEL_34",
+    "35": "LABEL_35",
+    "36": "LABEL_36",
+    "37": "LABEL_37",
+    "38": "LABEL_38",
+    "39": "LABEL_39",
+    "40": "LABEL_40",
+    "41": "LABEL_41",
+    "42": "LABEL_42",
+    "43": "LABEL_43",
+    "44": "LABEL_44",
+    "45": "LABEL_45",
+    "46": "LABEL_46",
+    "47": "LABEL_47",
+    "48": "LABEL_48",
+    "49": "LABEL_49",
+    "50": "LABEL_50",
+    "51": "LABEL_51",
+    "52": "LABEL_52",
+    "53": "LABEL_53",
+    "54": "LABEL_54",
+    "55": "LABEL_55",
+    "56": "LABEL_56",
+    "57": "LABEL_57",
+    "58": "LABEL_58",
+    "59": "LABEL_59",
+    "60": "LABEL_60",
+    "61": "LABEL_61",
+    "62": "LABEL_62",
+    "63": "LABEL_63",
+    "64": "LABEL_64",
+    "65": "LABEL_65",
+    "66": "LABEL_66",
+    "67": "LABEL_67",
+    "68": "LABEL_68",
+    "69": "LABEL_69",
+    "70": "LABEL_70",
+    "71": "LABEL_71",
+    "72": "LABEL_72",
+    "73": "LABEL_73",
+    "74": "LABEL_74",
+    "75": "LABEL_75",
+    "76": "LABEL_76",
+    "77": "LABEL_77",
+    "78": "LABEL_78",
+    "79": "LABEL_79",
+    "80": "LABEL_80",
+    "81": "LABEL_81",
+    "82": "LABEL_82",
+    "83": "LABEL_83",
+    "84": "LABEL_84",
+    "85": "LABEL_85",
+    "86": "LABEL_86",
+    "87": "LABEL_87",
+    "88": "LABEL_88",
+    "89": "LABEL_89",
+    "90": "LABEL_90",
+    "91": "LABEL_91",
+    "92": "LABEL_92",
+    "93": "LABEL_93",
+    "94": "LABEL_94",
+    "95": "LABEL_95",
+    "96": "LABEL_96",
+    "97": "LABEL_97",
+    "98": "LABEL_98",
+    "99": "LABEL_99",
+    "100": "LABEL_100",
+    "101": "LABEL_101",
+    "102": "LABEL_102",
+    "103": "LABEL_103",
+    "104": "LABEL_104",
+    "105": "LABEL_105",
+    "106": "LABEL_106",
+    "107": "LABEL_107",
+    "108": "LABEL_108",
+    "109": "LABEL_109",
+    "110": "LABEL_110",
+    "111": "LABEL_111",
+    "112": "LABEL_112",
+    "113": "LABEL_113",
+    "114": "LABEL_114",
+    "115": "LABEL_115",
+    "116": "LABEL_116",
+    "117": "LABEL_117",
+    "118": "LABEL_118",
+    "119": "LABEL_119",
+    "120": "LABEL_120",
+    "121": "LABEL_121",
+    "122": "LABEL_122",
+    "123": "LABEL_123",
+    "124": "LABEL_124",
+    "125": "LABEL_125",
+    "126": "LABEL_126",
+    "127": "LABEL_127",
+    "128": "LABEL_128",
+    "129": "LABEL_129",
+    "130": "LABEL_130",
+    "131": "LABEL_131",
+    "132": "LABEL_132",
+    "133": "LABEL_133",
+    "134": "LABEL_134",
+    "135": "LABEL_135",
+    "136": "LABEL_136",
+    "137": "LABEL_137",
+    "138": "LABEL_138",
+    "139": "LABEL_139",
+    "140": "LABEL_140",
+    "141": "LABEL_141",
+    "142": "LABEL_142",
+    "143": "LABEL_143",
+    "144": "LABEL_144",
+    "145": "LABEL_145",
+    "146": "LABEL_146",
+    "147": "LABEL_147",
+    "148": "LABEL_148",
+    "149": "LABEL_149",
+    "150": "LABEL_150",
+    "151": "LABEL_151",
+    "152": "LABEL_152",
+    "153": "LABEL_153",
+    "154": "LABEL_154",
+    "155": "LABEL_155",
+    "156": "LABEL_156",
+    "157": "LABEL_157",
+    "158": "LABEL_158",
+    "159": "LABEL_159",
+    "160": "LABEL_160",
+    "161": "LABEL_161",
+    "162": "LABEL_162",
+    "163": "LABEL_163",
+    "164": "LABEL_164",
+    "165": "LABEL_165",
+    "166": "LABEL_166",
+    "167": "LABEL_167",
+    "168": "LABEL_168",
+    "169": "LABEL_169",
+    "170": "LABEL_170",
+    "171": "LABEL_171",
+    "172": "LABEL_172",
+    "173": "LABEL_173",
+    "174": "LABEL_174",
+    "175": "LABEL_175",
+    "176": "LABEL_176",
+    "177": "LABEL_177",
+    "178": "LABEL_178",
+    "179": "LABEL_179",
+    "180": "LABEL_180",
+    "181": "LABEL_181",
+    "182": "LABEL_182",
+    "183": "LABEL_183",
+    "184": "LABEL_184",
+    "185": "LABEL_185",
+    "186": "LABEL_186",
+    "187": "LABEL_187",
+    "188": "LABEL_188",
+    "189": "LABEL_189",
+    "190": "LABEL_190",
+    "191": "LABEL_191",
+    "192": "LABEL_192",
+    "193": "LABEL_193",
+    "194": "LABEL_194",
+    "195": "LABEL_195",
+    "196": "LABEL_196",
+    "197": "LABEL_197",
+    "198": "LABEL_198",
+    "199": "LABEL_199",
+    "200": "LABEL_200",
+    "201": "LABEL_201",
+    "202": "LABEL_202",
+    "203": "LABEL_203",
+    "204": "LABEL_204",
+    "205": "LABEL_205",
+    "206": "LABEL_206",
+    "207": "LABEL_207",
+    "208": "LABEL_208",
+    "209": "LABEL_209",
+    "210": "LABEL_210",
+    "211": "LABEL_211",
+    "212": "LABEL_212",
+    "213": "LABEL_213",
+    "214": "LABEL_214",
+    "215": "LABEL_215",
+    "216": "LABEL_216",
+    "217": "LABEL_217",
+    "218": "LABEL_218",
+    "219": "LABEL_219",
+    "220": "LABEL_220",
+    "221": "LABEL_221",
+    "222": "LABEL_222",
+    "223": "LABEL_223",
+    "224": "LABEL_224",
+    "225": "LABEL_225",
+    "226": "LABEL_226",
+    "227": "LABEL_227",
+    "228": "LABEL_228",
+    "229": "LABEL_229",
+    "230": "LABEL_230",
+    "231": "LABEL_231",
+    "232": "LABEL_232",
+    "233": "LABEL_233",
+    "234": "LABEL_234",
+    "235": "LABEL_235",
+    "236": "LABEL_236",
+    "237": "LABEL_237",
+    "238": "LABEL_238",
+    "239": "LABEL_239",
+    "240": "LABEL_240",
+    "241": "LABEL_241",
+    "242": "LABEL_242",
+    "243": "LABEL_243",
+    "244": "LABEL_244",
+    "245": "LABEL_245",
+    "246": "LABEL_246",
+    "247": "LABEL_247",
+    "248": "LABEL_248",
+    "249": "LABEL_249",
+    "250": "LABEL_250",
+    "251": "LABEL_251",
+    "252": "LABEL_252",
+    "253": "LABEL_253",
+    "254": "LABEL_254",
+    "255": "LABEL_255",
+    "256": "LABEL_256",
+    "257": "LABEL_257",
+    "258": "LABEL_258",
+    "259": "LABEL_259",
+    "260": "LABEL_260",
+    "261": "LABEL_261",
+    "262": "LABEL_262",
+    "263": "LABEL_263",
+    "264": "LABEL_264",
+    "265": "LABEL_265",
+    "266": "LABEL_266",
+    "267": "LABEL_267",
+    "268": "LABEL_268",
+    "269": "LABEL_269",
+    "270": "LABEL_270",
+    "271": "LABEL_271",
+    "272": "LABEL_272",
+    "273": "LABEL_273",
+    "274": "LABEL_274",
+    "275": "LABEL_275",
+    "276": "LABEL_276",
+    "277": "LABEL_277",
+    "278": "LABEL_278",
+    "279": "LABEL_279",
+    "280": "LABEL_280",
+    "281": "LABEL_281",
+    "282": "LABEL_282",
+    "283": "LABEL_283",
+    "284": "LABEL_284",
+    "285": "LABEL_285",
+    "286": "LABEL_286",
+    "287": "LABEL_287",
+    "288": "LABEL_288",
+    "289": "LABEL_289",
+    "290": "LABEL_290",
+    "291": "LABEL_291",
+    "292": "LABEL_292",
+    "293": "LABEL_293",
+    "294": "LABEL_294",
+    "295": "LABEL_295",
+    "296": "LABEL_296",
+    "297": "LABEL_297",
+    "298": "LABEL_298",
+    "299": "LABEL_299",
+    "300": "LABEL_300",
+    "301": "LABEL_301",
+    "302": "LABEL_302",
+    "303": "LABEL_303",
+    "304": "LABEL_304",
+    "305": "LABEL_305",
+    "306": "LABEL_306",
+    "307": "LABEL_307",
+    "308": "LABEL_308",
+    "309": "LABEL_309",
+    "310": "LABEL_310",
+    "311": "LABEL_311",
+    "312": "LABEL_312",
+    "313": "LABEL_313",
+    "314": "LABEL_314",
+    "315": "LABEL_315",
+    "316": "LABEL_316",
+    "317": "LABEL_317",
+    "318": "LABEL_318",
+    "319": "LABEL_319",
+    "320": "LABEL_320",
+    "321": "LABEL_321",
+    "322": "LABEL_322",
+    "323": "LABEL_323",
+    "324": "LABEL_324",
+    "325": "LABEL_325",
+    "326": "LABEL_326",
+    "327": "LABEL_327",
+    "328": "LABEL_328",
+    "329": "LABEL_329",
+    "330": "LABEL_330",
+    "331": "LABEL_331",
+    "332": "LABEL_332",
+    "333": "LABEL_333",
+    "334": "LABEL_334",
+    "335": "LABEL_335",
+    "336": "LABEL_336",
+    "337": "LABEL_337",
+    "338": "LABEL_338",
+    "339": "LABEL_339",
+    "340": "LABEL_340",
+    "341": "LABEL_341",
+    "342": "LABEL_342",
+    "343": "LABEL_343",
+    "344": "LABEL_344",
+    "345": "LABEL_345",
+    "346": "LABEL_346",
+    "347": "LABEL_347",
+    "348": "LABEL_348",
+    "349": "LABEL_349",
+    "350": "LABEL_350",
+    "351": "LABEL_351",
+    "352": "LABEL_352",
+    "353": "LABEL_353",
+    "354": "LABEL_354",
+    "355": "LABEL_355",
+    "356": "LABEL_356",
+    "357": "LABEL_357",
+    "358": "LABEL_358",
+    "359": "LABEL_359",
+    "360": "LABEL_360",
+    "361": "LABEL_361",
+    "362": "LABEL_362",
+    "363": "LABEL_363",
+    "364": "LABEL_364",
+    "365": "LABEL_365",
+    "366": "LABEL_366",
+    "367": "LABEL_367",
+    "368": "LABEL_368",
+    "369": "LABEL_369",
+    "370": "LABEL_370",
+    "371": "LABEL_371",
+    "372": "LABEL_372",
+    "373": "LABEL_373",
+    "374": "LABEL_374",
+    "375": "LABEL_375",
+    "376": "LABEL_376",
+    "377": "LABEL_377",
+    "378": "LABEL_378",
+    "379": "LABEL_379",
+    "380": "LABEL_380",
+    "381": "LABEL_381",
+    "382": "LABEL_382",
+    "383": "LABEL_383",
+    "384": "LABEL_384",
+    "385": "LABEL_385",
+    "386": "LABEL_386",
+    "387": "LABEL_387",
+    "388": "LABEL_388",
+    "389": "LABEL_389",
+    "390": "LABEL_390",
+    "391": "LABEL_391",
+    "392": "LABEL_392",
+    "393": "LABEL_393",
+    "394": "LABEL_394",
+    "395": "LABEL_395",
+    "396": "LABEL_396",
+    "397": "LABEL_397",
+    "398": "LABEL_398",
+    "399": "LABEL_399",
+    "400": "LABEL_400",
+    "401": "LABEL_401",
+    "402": "LABEL_402",
+    "403": "LABEL_403",
+    "404": "LABEL_404",
+    "405": "LABEL_405",
+    "406": "LABEL_406",
+    "407": "LABEL_407",
+    "408": "LABEL_408",
+    "409": "LABEL_409",
+    "410": "LABEL_410",
+    "411": "LABEL_411",
+    "412": "LABEL_412",
+    "413": "LABEL_413",
+    "414": "LABEL_414",
+    "415": "LABEL_415",
+    "416": "LABEL_416",
+    "417": "LABEL_417",
+    "418": "LABEL_418",
+    "419": "LABEL_419",
+    "420": "LABEL_420",
+    "421": "LABEL_421",
+    "422": "LABEL_422",
+    "423": "LABEL_423",
+    "424": "LABEL_424",
+    "425": "LABEL_425",
+    "426": "LABEL_426",
+    "427": "LABEL_427",
+    "428": "LABEL_428",
+    "429": "LABEL_429",
+    "430": "LABEL_430",
+    "431": "LABEL_431",
+    "432": "LABEL_432",
+    "433": "LABEL_433",
+    "434": "LABEL_434",
+    "435": "LABEL_435",
+    "436": "LABEL_436",
+    "437": "LABEL_437",
+    "438": "LABEL_438",
+    "439": "LABEL_439",
+    "440": "LABEL_440",
+    "441": "LABEL_441",
+    "442": "LABEL_442",
+    "443": "LABEL_443",
+    "444": "LABEL_444",
+    "445": "LABEL_445",
+    "446": "LABEL_446",
+    "447": "LABEL_447",
+    "448": "LABEL_448",
+    "449": "LABEL_449",
+    "450": "LABEL_450",
+    "451": "LABEL_451",
+    "452": "LABEL_452",
+    "453": "LABEL_453",
+    "454": "LABEL_454",
+    "455": "LABEL_455",
+    "456": "LABEL_456",
+    "457": "LABEL_457",
+    "458": "LABEL_458",
+    "459": "LABEL_459",
+    "460": "LABEL_460",
+    "461": "LABEL_461",
+    "462": "LABEL_462",
+    "463": "LABEL_463",
+    "464": "LABEL_464",
+    "465": "LABEL_465",
+    "466": "LABEL_466",
+    "467": "LABEL_467",
+    "468": "LABEL_468",
+    "469": "LABEL_469",
+    "470": "LABEL_470",
+    "471": "LABEL_471",
+    "472": "LABEL_472",
+    "473": "LABEL_473",
+    "474": "LABEL_474",
+    "475": "LABEL_475",
+    "476": "LABEL_476",
+    "477": "LABEL_477",
+    "478": "LABEL_478",
+    "479": "LABEL_479",
+    "480": "LABEL_480",
+    "481": "LABEL_481",
+    "482": "LABEL_482",
+    "483": "LABEL_483",
+    "484": "LABEL_484",
+    "485": "LABEL_485",
+    "486": "LABEL_486",
+    "487": "LABEL_487",
+    "488": "LABEL_488",
+    "489": "LABEL_489",
+    "490": "LABEL_490",
+    "491": "LABEL_491",
+    "492": "LABEL_492",
+    "493": "LABEL_493",
+    "494": "LABEL_494",
+    "495": "LABEL_495",
+    "496": "LABEL_496",
+    "497": "LABEL_497",
+    "498": "LABEL_498",
+    "499": "LABEL_499",
+    "500": "LABEL_500",
+    "501": "LABEL_501",
+    "502": "LABEL_502",
+    "503": "LABEL_503",
+    "504": "LABEL_504",
+    "505": "LABEL_505",
+    "506": "LABEL_506",
+    "507": "LABEL_507",
+    "508": "LABEL_508",
+    "509": "LABEL_509"
+  },
+  "initializer_range": 0.02,
+  "input_size": 224,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_100": 100,
+    "LABEL_101": 101,
+    "LABEL_102": 102,
+    "LABEL_103": 103,
+    "LABEL_104": 104,
+    "LABEL_105": 105,
+    "LABEL_106": 106,
+    "LABEL_107": 107,
+    "LABEL_108": 108,
+    "LABEL_109": 109,
+    "LABEL_11": 11,
+    "LABEL_110": 110,
+    "LABEL_111": 111,
+    "LABEL_112": 112,
+    "LABEL_113": 113,
+    "LABEL_114": 114,
+    "LABEL_115": 115,
+    "LABEL_116": 116,
+    "LABEL_117": 117,
+    "LABEL_118": 118,
+    "LABEL_119": 119,
+    "LABEL_12": 12,
+    "LABEL_120": 120,
+    "LABEL_121": 121,
+    "LABEL_122": 122,
+    "LABEL_123": 123,
+    "LABEL_124": 124,
+    "LABEL_125": 125,
+    "LABEL_126": 126,
+    "LABEL_127": 127,
+    "LABEL_128": 128,
+    "LABEL_129": 129,
+    "LABEL_13": 13,
+    "LABEL_130": 130,
+    "LABEL_131": 131,
+    "LABEL_132": 132,
+    "LABEL_133": 133,
+    "LABEL_134": 134,
+    "LABEL_135": 135,
+    "LABEL_136": 136,
+    "LABEL_137": 137,
+    "LABEL_138": 138,
+    "LABEL_139": 139,
+    "LABEL_14": 14,
+    "LABEL_140": 140,
+    "LABEL_141": 141,
+    "LABEL_142": 142,
+    "LABEL_143": 143,
+    "LABEL_144": 144,
+    "LABEL_145": 145,
+    "LABEL_146": 146,
+    "LABEL_147": 147,
+    "LABEL_148": 148,
+    "LABEL_149": 149,
+    "LABEL_15": 15,
+    "LABEL_150": 150,
+    "LABEL_151": 151,
+    "LABEL_152": 152,
+    "LABEL_153": 153,
+    "LABEL_154": 154,
+    "LABEL_155": 155,
+    "LABEL_156": 156,
+    "LABEL_157": 157,
+    "LABEL_158": 158,
+    "LABEL_159": 159,
+    "LABEL_16": 16,
+    "LABEL_160": 160,
+    "LABEL_161": 161,
+    "LABEL_162": 162,
+    "LABEL_163": 163,
+    "LABEL_164": 164,
+    "LABEL_165": 165,
+    "LABEL_166": 166,
+    "LABEL_167": 167,
+    "LABEL_168": 168,
+    "LABEL_169": 169,
+    "LABEL_17": 17,
+    "LABEL_170": 170,
+    "LABEL_171": 171,
+    "LABEL_172": 172,
+    "LABEL_173": 173,
+    "LABEL_174": 174,
+    "LABEL_175": 175,
+    "LABEL_176": 176,
+    "LABEL_177": 177,
+    "LABEL_178": 178,
+    "LABEL_179": 179,
+    "LABEL_18": 18,
+    "LABEL_180": 180,
+    "LABEL_181": 181,
+    "LABEL_182": 182,
+    "LABEL_183": 183,
+    "LABEL_184": 184,
+    "LABEL_185": 185,
+    "LABEL_186": 186,
+    "LABEL_187": 187,
+    "LABEL_188": 188,
+    "LABEL_189": 189,
+    "LABEL_19": 19,
+    "LABEL_190": 190,
+    "LABEL_191": 191,
+    "LABEL_192": 192,
+    "LABEL_193": 193,
+    "LABEL_194": 194,
+    "LABEL_195": 195,
+    "LABEL_196": 196,
+    "LABEL_197": 197,
+    "LABEL_198": 198,
+    "LABEL_199": 199,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_200": 200,
+    "LABEL_201": 201,
+    "LABEL_202": 202,
+    "LABEL_203": 203,
+    "LABEL_204": 204,
+    "LABEL_205": 205,
+    "LABEL_206": 206,
+    "LABEL_207": 207,
+    "LABEL_208": 208,
+    "LABEL_209": 209,
+    "LABEL_21": 21,
+    "LABEL_210": 210,
+    "LABEL_211": 211,
+    "LABEL_212": 212,
+    "LABEL_213": 213,
+    "LABEL_214": 214,
+    "LABEL_215": 215,
+    "LABEL_216": 216,
+    "LABEL_217": 217,
+    "LABEL_218": 218,
+    "LABEL_219": 219,
+    "LABEL_22": 22,
+    "LABEL_220": 220,
+    "LABEL_221": 221,
+    "LABEL_222": 222,
+    "LABEL_223": 223,
+    "LABEL_224": 224,
+    "LABEL_225": 225,
+    "LABEL_226": 226,
+    "LABEL_227": 227,
+    "LABEL_228": 228,
+    "LABEL_229": 229,
+    "LABEL_23": 23,
+    "LABEL_230": 230,
+    "LABEL_231": 231,
+    "LABEL_232": 232,
+    "LABEL_233": 233,
+    "LABEL_234": 234,
+    "LABEL_235": 235,
+    "LABEL_236": 236,
+    "LABEL_237": 237,
+    "LABEL_238": 238,
+    "LABEL_239": 239,
+    "LABEL_24": 24,
+    "LABEL_240": 240,
+    "LABEL_241": 241,
+    "LABEL_242": 242,
+    "LABEL_243": 243,
+    "LABEL_244": 244,
+    "LABEL_245": 245,
+    "LABEL_246": 246,
+    "LABEL_247": 247,
+    "LABEL_248": 248,
+    "LABEL_249": 249,
+    "LABEL_25": 25,
+    "LABEL_250": 250,
+    "LABEL_251": 251,
+    "LABEL_252": 252,
+    "LABEL_253": 253,
+    "LABEL_254": 254,
+    "LABEL_255": 255,
+    "LABEL_256": 256,
+    "LABEL_257": 257,
+    "LABEL_258": 258,
+    "LABEL_259": 259,
+    "LABEL_26": 26,
+    "LABEL_260": 260,
+    "LABEL_261": 261,
+    "LABEL_262": 262,
+    "LABEL_263": 263,
+    "LABEL_264": 264,
+    "LABEL_265": 265,
+    "LABEL_266": 266,
+    "LABEL_267": 267,
+    "LABEL_268": 268,
+    "LABEL_269": 269,
+    "LABEL_27": 27,
+    "LABEL_270": 270,
+    "LABEL_271": 271,
+    "LABEL_272": 272,
+    "LABEL_273": 273,
+    "LABEL_274": 274,
+    "LABEL_275": 275,
+    "LABEL_276": 276,
+    "LABEL_277": 277,
+    "LABEL_278": 278,
+    "LABEL_279": 279,
+    "LABEL_28": 28,
+    "LABEL_280": 280,
+    "LABEL_281": 281,
+    "LABEL_282": 282,
+    "LABEL_283": 283,
+    "LABEL_284": 284,
+    "LABEL_285": 285,
+    "LABEL_286": 286,
+    "LABEL_287": 287,
+    "LABEL_288": 288,
+    "LABEL_289": 289,
+    "LABEL_29": 29,
+    "LABEL_290": 290,
+    "LABEL_291": 291,
+    "LABEL_292": 292,
+    "LABEL_293": 293,
+    "LABEL_294": 294,
+    "LABEL_295": 295,
+    "LABEL_296": 296,
+    "LABEL_297": 297,
+    "LABEL_298": 298,
+    "LABEL_299": 299,
+    "LABEL_3": 3,
+    "LABEL_30": 30,
+    "LABEL_300": 300,
+    "LABEL_301": 301,
+    "LABEL_302": 302,
+    "LABEL_303": 303,
+    "LABEL_304": 304,
+    "LABEL_305": 305,
+    "LABEL_306": 306,
+    "LABEL_307": 307,
+    "LABEL_308": 308,
+    "LABEL_309": 309,
+    "LABEL_31": 31,
+    "LABEL_310": 310,
+    "LABEL_311": 311,
+    "LABEL_312": 312,
+    "LABEL_313": 313,
+    "LABEL_314": 314,
+    "LABEL_315": 315,
+    "LABEL_316": 316,
+    "LABEL_317": 317,
+    "LABEL_318": 318,
+    "LABEL_319": 319,
+    "LABEL_32": 32,
+    "LABEL_320": 320,
+    "LABEL_321": 321,
+    "LABEL_322": 322,
+    "LABEL_323": 323,
+    "LABEL_324": 324,
+    "LABEL_325": 325,
+    "LABEL_326": 326,
+    "LABEL_327": 327,
+    "LABEL_328": 328,
+    "LABEL_329": 329,
+    "LABEL_33": 33,
+    "LABEL_330": 330,
+    "LABEL_331": 331,
+    "LABEL_332": 332,
+    "LABEL_333": 333,
+    "LABEL_334": 334,
+    "LABEL_335": 335,
+    "LABEL_336": 336,
+    "LABEL_337": 337,
+    "LABEL_338": 338,
+    "LABEL_339": 339,
+    "LABEL_34": 34,
+    "LABEL_340": 340,
+    "LABEL_341": 341,
+    "LABEL_342": 342,
+    "LABEL_343": 343,
+    "LABEL_344": 344,
+    "LABEL_345": 345,
+    "LABEL_346": 346,
+    "LABEL_347": 347,
+    "LABEL_348": 348,
+    "LABEL_349": 349,
+    "LABEL_35": 35,
+    "LABEL_350": 350,
+    "LABEL_351": 351,
+    "LABEL_352": 352,
+    "LABEL_353": 353,
+    "LABEL_354": 354,
+    "LABEL_355": 355,
+    "LABEL_356": 356,
+    "LABEL_357": 357,
+    "LABEL_358": 358,
+    "LABEL_359": 359,
+    "LABEL_36": 36,
+    "LABEL_360": 360,
+    "LABEL_361": 361,
+    "LABEL_362": 362,
+    "LABEL_363": 363,
+    "LABEL_364": 364,
+    "LABEL_365": 365,
+    "LABEL_366": 366,
+    "LABEL_367": 367,
+    "LABEL_368": 368,
+    "LABEL_369": 369,
+    "LABEL_37": 37,
+    "LABEL_370": 370,
+    "LABEL_371": 371,
+    "LABEL_372": 372,
+    "LABEL_373": 373,
+    "LABEL_374": 374,
+    "LABEL_375": 375,
+    "LABEL_376": 376,
+    "LABEL_377": 377,
+    "LABEL_378": 378,
+    "LABEL_379": 379,
+    "LABEL_38": 38,
+    "LABEL_380": 380,
+    "LABEL_381": 381,
+    "LABEL_382": 382,
+    "LABEL_383": 383,
+    "LABEL_384": 384,
+    "LABEL_385": 385,
+    "LABEL_386": 386,
+    "LABEL_387": 387,
+    "LABEL_388": 388,
+    "LABEL_389": 389,
+    "LABEL_39": 39,
+    "LABEL_390": 390,
+    "LABEL_391": 391,
+    "LABEL_392": 392,
+    "LABEL_393": 393,
+    "LABEL_394": 394,
+    "LABEL_395": 395,
+    "LABEL_396": 396,
+    "LABEL_397": 397,
+    "LABEL_398": 398,
+    "LABEL_399": 399,
+    "LABEL_4": 4,
+    "LABEL_40": 40,
+    "LABEL_400": 400,
+    "LABEL_401": 401,
+    "LABEL_402": 402,
+    "LABEL_403": 403,
+    "LABEL_404": 404,
+    "LABEL_405": 405,
+    "LABEL_406": 406,
+    "LABEL_407": 407,
+    "LABEL_408": 408,
+    "LABEL_409": 409,
+    "LABEL_41": 41,
+    "LABEL_410": 410,
+    "LABEL_411": 411,
+    "LABEL_412": 412,
+    "LABEL_413": 413,
+    "LABEL_414": 414,
+    "LABEL_415": 415,
+    "LABEL_416": 416,
+    "LABEL_417": 417,
+    "LABEL_418": 418,
+    "LABEL_419": 419,
+    "LABEL_42": 42,
+    "LABEL_420": 420,
+    "LABEL_421": 421,
+    "LABEL_422": 422,
+    "LABEL_423": 423,
+    "LABEL_424": 424,
+    "LABEL_425": 425,
+    "LABEL_426": 426,
+    "LABEL_427": 427,
+    "LABEL_428": 428,
+    "LABEL_429": 429,
+    "LABEL_43": 43,
+    "LABEL_430": 430,
+    "LABEL_431": 431,
+    "LABEL_432": 432,
+    "LABEL_433": 433,
+    "LABEL_434": 434,
+    "LABEL_435": 435,
+    "LABEL_436": 436,
+    "LABEL_437": 437,
+    "LABEL_438": 438,
+    "LABEL_439": 439,
+    "LABEL_44": 44,
+    "LABEL_440": 440,
+    "LABEL_441": 441,
+    "LABEL_442": 442,
+    "LABEL_443": 443,
+    "LABEL_444": 444,
+    "LABEL_445": 445,
+    "LABEL_446": 446,
+    "LABEL_447": 447,
+    "LABEL_448": 448,
+    "LABEL_449": 449,
+    "LABEL_45": 45,
+    "LABEL_450": 450,
+    "LABEL_451": 451,
+    "LABEL_452": 452,
+    "LABEL_453": 453,
+    "LABEL_454": 454,
+    "LABEL_455": 455,
+    "LABEL_456": 456,
+    "LABEL_457": 457,
+    "LABEL_458": 458,
+    "LABEL_459": 459,
+    "LABEL_46": 46,
+    "LABEL_460": 460,
+    "LABEL_461": 461,
+    "LABEL_462": 462,
+    "LABEL_463": 463,
+    "LABEL_464": 464,
+    "LABEL_465": 465,
+    "LABEL_466": 466,
+    "LABEL_467": 467,
+    "LABEL_468": 468,
+    "LABEL_469": 469,
+    "LABEL_47": 47,
+    "LABEL_470": 470,
+    "LABEL_471": 471,
+    "LABEL_472": 472,
+    "LABEL_473": 473,
+    "LABEL_474": 474,
+    "LABEL_475": 475,
+    "LABEL_476": 476,
+    "LABEL_477": 477,
+    "LABEL_478": 478,
+    "LABEL_479": 479,
+    "LABEL_48": 48,
+    "LABEL_480": 480,
+    "LABEL_481": 481,
+    "LABEL_482": 482,
+    "LABEL_483": 483,
+    "LABEL_484": 484,
+    "LABEL_485": 485,
+    "LABEL_486": 486,
+    "LABEL_487": 487,
+    "LABEL_488": 488,
+    "LABEL_489": 489,
+    "LABEL_49": 49,
+    "LABEL_490": 490,
+    "LABEL_491": 491,
+    "LABEL_492": 492,
+    "LABEL_493": 493,
+    "LABEL_494": 494,
+    "LABEL_495": 495,
+    "LABEL_496": 496,
+    "LABEL_497": 497,
+    "LABEL_498": 498,
+    "LABEL_499": 499,
+    "LABEL_5": 5,
+    "LABEL_50": 50,
+    "LABEL_500": 500,
+    "LABEL_501": 501,
+    "LABEL_502": 502,
+    "LABEL_503": 503,
+    "LABEL_504": 504,
+    "LABEL_505": 505,
+    "LABEL_506": 506,
+    "LABEL_507": 507,
+    "LABEL_508": 508,
+    "LABEL_509": 509,
+    "LABEL_51": 51,
+    "LABEL_52": 52,
+    "LABEL_53": 53,
+    "LABEL_54": 54,
+    "LABEL_55": 55,
+    "LABEL_56": 56,
+    "LABEL_57": 57,
+    "LABEL_58": 58,
+    "LABEL_59": 59,
+    "LABEL_6": 6,
+    "LABEL_60": 60,
+    "LABEL_61": 61,
+    "LABEL_62": 62,
+    "LABEL_63": 63,
+    "LABEL_64": 64,
+    "LABEL_65": 65,
+    "LABEL_66": 66,
+    "LABEL_67": 67,
+    "LABEL_68": 68,
+    "LABEL_69": 69,
+    "LABEL_7": 7,
+    "LABEL_70": 70,
+    "LABEL_71": 71,
+    "LABEL_72": 72,
+    "LABEL_73": 73,
+    "LABEL_74": 74,
+    "LABEL_75": 75,
+    "LABEL_76": 76,
+    "LABEL_77": 77,
+    "LABEL_78": 78,
+    "LABEL_79": 79,
+    "LABEL_8": 8,
+    "LABEL_80": 80,
+    "LABEL_81": 81,
+    "LABEL_82": 82,
+    "LABEL_83": 83,
+    "LABEL_84": 84,
+    "LABEL_85": 85,
+    "LABEL_86": 86,
+    "LABEL_87": 87,
+    "LABEL_88": 88,
+    "LABEL_89": 89,
+    "LABEL_9": 9,
+    "LABEL_90": 90,
+    "LABEL_91": 91,
+    "LABEL_92": 92,
+    "LABEL_93": 93,
+    "LABEL_94": 94,
+    "LABEL_95": 95,
+    "LABEL_96": 96,
+    "LABEL_97": 97,
+    "LABEL_98": 98,
+    "LABEL_99": 99
+  },
+  "layer_norm_eps": 1e-05,
+  "max_2d_position_embeddings": 1024,
+  "max_position_embeddings": 514,
+  "max_rel_2d_pos": 256,
+  "max_rel_pos": 128,
+  "model_type": "layoutlmv3",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "patch_size": 16,
+  "rel_2d_pos_bins": 64,
+  "rel_pos_bins": 32,
+  "second_input_size": 112,
+  "shape_size": 170,
+  "text_embed": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.0",
+  "type_vocab_size": 1,
+  "visual_embed": false,
+  "vocab_size": 50265
+}

Relation/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78a7ca1cb2ba8162b2672641f9d94ebde8b953fdf35c9417c0c8383e82751265
+size 713217212

Structure/PP-DocLayout_plus-L/.mv

@@ -0,0 +1 @@
+Revision:master,CreatedAt:1751519173

Structure/PP-DocLayout_plus-L/README.md

@@ -0,0 +1,137 @@
+---
+license: apache-2.0
+library_name: PaddleOCR
+language:
+- en
+- zh
+pipeline_tag: image-to-text
+tags:
+- OCR
+- PaddlePaddle
+- PaddleOCR
+---
+
+# 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.
+
+
+## Quick Start
+
+### Installation
+
+1. PaddlePaddle
+
+Please refer to the following commands to install PaddlePaddle using pip:
+
+```bash
+# for CUDA11.8
+python -m pip install paddlepaddle-gpu==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/
+
+# for CUDA12.6
+python -m pip install paddlepaddle-gpu==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu126/
+
+# for CPU
+python -m pip install paddlepaddle==3.0.0 -i https://www.paddlepaddle.org.cn/packages/stable/cpu/
+```
+
+For details about PaddlePaddle installation, please refer to the [PaddlePaddle official website](https://www.paddlepaddle.org.cn/en/install/quick).
+
+2. PaddleOCR
+
+Install the latest version of the PaddleOCR inference package from PyPI:
+
+```bash
+python -m pip install paddleocr
+```
+
+
+### Model Usage
+
+You can quickly experience the functionality with a single command:
+
+```bash
+paddleocr layout_detection \
+    --model_name PP-DocLayout_plus-L \
+    -i https://cdn-uploads.huggingface.co/production/uploads/63d7b8ee07cd1aa3c49a2026/N5C68HPVAI-xQAWTxpbA6.jpeg
+```
+
+You can also integrate the model inference of the layout detection module into your project. Before running the following code, please download the sample image to your local machine.
+
+```python
+from paddleocr import LayoutDetection
+
+model = LayoutDetection(model_name="PP-DocLayout_plus-L")
+output = model.predict("N5C68HPVAI-xQAWTxpbA6.jpeg", batch_size=1, layout_nms=True)
+for res in output:
+    res.print()
+    res.save_to_img(save_path="./output/")
+    res.save_to_json(save_path="./output/res.json")
+```
+
+After running, the obtained result is as follows:
+
+```json
+{'res': {'input_path': '/root/.paddlex/predict_input/N5C68HPVAI-xQAWTxpbA6.jpeg', 'page_index': None, 'boxes': [{'cls_id': 2, 'label': 'text', 'score': 0.9870168566703796, 'coordinate': [34.101395, 349.85275, 358.5929, 611.0788]}, {'cls_id': 2, 'label': 'text', 'score': 0.986599326133728, 'coordinate': [34.500305, 647.15753, 358.29437, 848.66925]}, {'cls_id': 2, 'label': 'text', 'score': 0.984662652015686, 'coordinate': [385.71417, 497.41037, 711.22656, 697.8426]}, {'cls_id': 8, 'label': 'table', 'score': 0.9841272234916687, 'coordinate': [73.76732, 105.94854, 321.95355, 298.85074]}, {'cls_id': 8, 'label': 'table', 'score': 0.983431875705719, 'coordinate': [436.95523, 105.81446, 662.71814, 313.4865]}, {'cls_id': 2, 'label': 'text', 'score': 0.9832285642623901, 'coordinate': [385.62766, 346.22888, 710.10205, 458.772]}, {'cls_id': 2, 'label': 'text', 'score': 0.9816107749938965, 'coordinate': [385.78085, 735.19293, 710.5613, 849.97656]}, {'cls_id': 6, 'label': 'figure_title', 'score': 0.9577467441558838, 'coordinate': [34.421764, 20.055021, 358.7124, 76.53721]}, {'cls_id': 6, 'label': 'figure_title', 'score': 0.9505674839019775, 'coordinate': [385.7235, 20.054104, 711.2928, 74.92819]}, {'cls_id': 0, 'label': 'paragraph_title', 'score': 0.9001894593238831, 'coordinate': [386.46353, 477.035, 699.4023, 490.07495]}, {'cls_id': 0, 'label': 'paragraph_title', 'score': 0.8846081495285034, 'coordinate': [35.413055, 627.7365, 185.58315, 640.522]}, {'cls_id': 0, 'label': 'paragraph_title', 'score': 0.8837621808052063, 'coordinate': [387.1759, 716.34235, 524.78345, 729.2588]}, {'cls_id': 0, 'label': 'paragraph_title', 'score': 0.8509567975997925, 'coordinate': [35.50049, 331.18472, 141.64497, 344.81168]}]}}
+```
+
+The visualized image is as follows:
+
+![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/63d7b8ee07cd1aa3c49a2026/5gAq1cFy1IX_wX26C2XmM.jpeg)
+
+For details about usage command and descriptions of parameters, please refer to the [Document](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/module_usage/layout_detection.html#iii-quick-integration).
+
+### Pipeline Usage
+
+The ability of a single model is limited. But the pipeline consists of several models can provide more capacity to resolve difficult problems in real-world scenarios.
+
+#### PP-StructureV3
+
+Layout analysis is a technique used to extract structured information from document images. PP-StructureV3 includes the following six modules:
+* Layout Detection Module
+* General OCR Sub-pipeline
+* Document Image Preprocessing Sub-pipeline （Optional）
+* Table Recognition Sub-pipeline （Optional）
+* Seal Recognition Sub-pipeline （Optional）
+* Formula Recognition Sub-pipeline （Optional）
+
+You can quickly experience the PP-StructureV3 pipeline with a single command.
+
+```bash
+paddleocr pp_structurev3 -i https://cdn-uploads.huggingface.co/production/uploads/63d7b8ee07cd1aa3c49a2026/KP10tiSZfAjMuwZUSLtRp.png
+```
+
+You can experience the inference of the pipeline with just a few lines of code. Taking the PP-StructureV3 pipeline as an example:
+
+```python
+from paddleocr import PPStructureV3
+
+pipeline = PPStructureV3()
+# ocr = PPStructureV3(use_doc_orientation_classify=True) # Use use_doc_orientation_classify to enable/disable document orientation classification model
+# ocr = PPStructureV3(use_doc_unwarping=True) # Use use_doc_unwarping to enable/disable document unwarping module
+# ocr = PPStructureV3(use_textline_orientation=True) # Use use_textline_orientation to enable/disable textline orientation classification model
+# ocr = PPStructureV3(device="gpu") # Use device to specify GPU for model inference
+output = pipeline.predict("./KP10tiSZfAjMuwZUSLtRp.png")
+for res in output:
+    res.print() ## Print the structured prediction output
+    res.save_to_json(save_path="output") ## Save the current image's structured result in JSON format
+    res.save_to_markdown(save_path="output") ## Save the current image's result in Markdown format
+```
+
+The default model used in pipeline is `PP-DocLayout_plus-L`.
+For details about usage command and descriptions of parameters, please refer to the [Document](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/pipeline_usage/PP-StructureV3.html#2-quick-start).
+
+## Links
+
+[PaddleOCR Repo](https://github.com/paddlepaddle/paddleocr)
+
+[PaddleOCR Documentation](https://paddlepaddle.github.io/PaddleOCR/latest/en/index.html)
+

Structure/PP-DocLayout_plus-L/config.json

@@ -0,0 +1,227 @@
+{
+    "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": {
+                    "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": {
+                    "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
+                        ]
+                    ]
+                }
+            }
+        }
+    }
+}

Structure/PP-DocLayout_plus-L/inference.pdiparams

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24ca3e2e442164505e250deef59f7ee9a54ea12dd32875c9cd6155d959dc97da
+size 129307978

Structure/PP-DocLayout_plus-L/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

Structure/doclayout_yolo_docstructbench_imgsz1280_2501.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b152460888dc30be6db7f5dfab28bde3dcc999e5202f46187a764a1699c80be
+size 39772550

Structure/layout_zh.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5acc32e5087ebb2601cf1221c7bdba960c086e1e4b009b15ce8b21c8e935fe3
+size 40654210