Circle6173/check_ocr

README.md

@@ -0,0 +1,99 @@
+---
+license: cc-by-nc-sa-4.0
+base_model: microsoft/layoutlmv3-base
+tags:
+- generated_from_trainer
+datasets:
+- data_loader
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: models
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: data_loader
+      type: data_loader
+      config: default
+      split: test
+      args: default
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.8940149625935162
+    - name: Recall
+      type: recall
+      value: 0.9168797953964194
+    - name: F1
+      type: f1
+      value: 0.9053030303030304
+    - name: Accuracy
+      type: accuracy
+      value: 0.9743718592964824
+---
+
+<!-- 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. -->
+
+# models
+
+This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the data_loader dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1595
+- Precision: 0.8940
+- Recall: 0.9169
+- F1: 0.9053
+- Accuracy: 0.9744
+
+## 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: 1e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 1000
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 2.5   | 100  | 0.1926          | 0.7730    | 0.8274 | 0.7993 | 0.9452   |
+| No log        | 5.0   | 200  | 0.1342          | 0.8285    | 0.8708 | 0.8491 | 0.9583   |
+| No log        | 7.5   | 300  | 0.1217          | 0.8758    | 0.9015 | 0.8885 | 0.9693   |
+| No log        | 10.0  | 400  | 0.1157          | 0.9082    | 0.9233 | 0.9157 | 0.9769   |
+| 0.15          | 12.5  | 500  | 0.1310          | 0.9011    | 0.9092 | 0.9052 | 0.9744   |
+| 0.15          | 15.0  | 600  | 0.1583          | 0.8682    | 0.9015 | 0.8846 | 0.9693   |
+| 0.15          | 17.5  | 700  | 0.1628          | 0.8867    | 0.9105 | 0.8984 | 0.9724   |
+| 0.15          | 20.0  | 800  | 0.1594          | 0.8945    | 0.9220 | 0.9081 | 0.9749   |
+| 0.15          | 22.5  | 900  | 0.1579          | 0.8940    | 0.9169 | 0.9053 | 0.9744   |
+| 0.0047        | 25.0  | 1000 | 0.1595          | 0.8940    | 0.9169 | 0.9053 | 0.9744   |
+
+
+### Framework versions
+
+- Transformers 4.40.0.dev0
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "microsoft/layoutlmv3-base",
+  "architectures": [
+    "LayoutLMv3ForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "coordinate_size": 128,
+  "eos_token_id": 2,
+  "has_relative_attention_bias": true,
+  "has_spatial_attention_bias": true,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Check Number",
+    "1": "Check Number Title",
+    "2": "Invoice Number",
+    "3": "Invoice Number Title",
+    "4": "Line Amount",
+    "5": "Total Amount",
+    "6": "Check Date Title",
+    "7": "Check Date",
+    "8": "Ignore"
+  },
+  "initializer_range": 0.02,
+  "input_size": 224,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Check Date": 7,
+    "Check Date Title": 6,
+    "Check Number": 0,
+    "Check Number Title": 1,
+    "Ignore": 8,
+    "Invoice Number": 2,
+    "Invoice Number Title": 3,
+    "Line Amount": 4,
+    "Total Amount": 5
+  },
+  "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": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "patch_size": 16,
+  "rel_2d_pos_bins": 64,
+  "rel_pos_bins": 32,
+  "second_input_size": 112,
+  "shape_size": 128,
+  "text_embed": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0.dev0",
+  "type_vocab_size": 1,
+  "visual_embed": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40e6e9a46725aa8a0b8dd9621e9f028e0e5e3e5ea67e3b9e0f3b9f9b58552d7e
+size 501361684

preprocessor_config.json

@@ -0,0 +1,43 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "apply_ocr",
+    "ocr_lang",
+    "tesseract_config",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "apply_ocr": false,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "LayoutLMv3ImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "ocr_lang": null,
+  "processor_class": "LayoutLMv3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  },
+  "tesseract_config": ""
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,79 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "apply_ocr": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "cls_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "only_label_first_subword": true,
+  "pad_token": "<pad>",
+  "pad_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "pad_token_label": -100,
+  "processor_class": "LayoutLMv3Processor",
+  "sep_token": "</s>",
+  "sep_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "tokenizer_class": "LayoutLMv3Tokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ec9674ff1a12dd5c8bb77c57991f7f11def008c903672dbbf3c9acc5fad285b
+size 4856