Upload folder using huggingface_hub

.gitattributes

@@ -25,7 +25,6 @@
 *.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

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,145 @@
+---
+license: cc-by-nc-sa-4.0
+tags:
+- generated_from_trainer
+datasets:
+- wild_receipt
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: OCR-LayoutLMv3-Invoice
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: wild_receipt
+      type: wild_receipt
+      config: WildReceipt
+      split: train
+      args: WildReceipt
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.8765398302764851
+    - name: Recall
+      type: recall
+      value: 0.8812439796339617
+    - name: F1
+      type: f1
+      value: 0.8788856103753516
+    - name: Accuracy
+      type: accuracy
+      value: 0.92678512668641
+---
+
+<!-- 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. -->
+
+# OCR-LayoutLMv3-Invoice
+
+This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the wild_receipt dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3159
+- Precision: 0.8765
+- Recall: 0.8812
+- F1: 0.8789
+- Accuracy: 0.9268
+
+## Model description
+
+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: 6000
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 0.16  | 100  | 1.5032          | 0.4934    | 0.1444 | 0.2234 | 0.6064   |
+| No log        | 0.32  | 200  | 1.0282          | 0.5884    | 0.4420 | 0.5048 | 0.7385   |
+| No log        | 0.47  | 300  | 0.7856          | 0.7448    | 0.6205 | 0.6770 | 0.8133   |
+| No log        | 0.63  | 400  | 0.6464          | 0.7736    | 0.6689 | 0.7174 | 0.8399   |
+| 1.1733        | 0.79  | 500  | 0.5672          | 0.7609    | 0.7303 | 0.7453 | 0.8557   |
+| 1.1733        | 0.95  | 600  | 0.5055          | 0.7658    | 0.7652 | 0.7655 | 0.8677   |
+| 1.1733        | 1.1   | 700  | 0.4735          | 0.7946    | 0.7848 | 0.7897 | 0.8784   |
+| 1.1733        | 1.26  | 800  | 0.4414          | 0.7962    | 0.7946 | 0.7954 | 0.8818   |
+| 1.1733        | 1.42  | 900  | 0.4094          | 0.8176    | 0.8064 | 0.8120 | 0.8894   |
+| 0.5047        | 1.58  | 1000 | 0.3971          | 0.8219    | 0.8248 | 0.8234 | 0.8961   |
+| 0.5047        | 1.74  | 1100 | 0.4082          | 0.7993    | 0.8362 | 0.8174 | 0.8927   |
+| 0.5047        | 1.89  | 1200 | 0.3797          | 0.8240    | 0.8317 | 0.8278 | 0.8962   |
+| 0.5047        | 2.05  | 1300 | 0.3597          | 0.8326    | 0.8331 | 0.8329 | 0.9020   |
+| 0.5047        | 2.21  | 1400 | 0.3544          | 0.8462    | 0.8283 | 0.8371 | 0.9020   |
+| 0.368         | 2.37  | 1500 | 0.3374          | 0.8428    | 0.8435 | 0.8432 | 0.9056   |
+| 0.368         | 2.52  | 1600 | 0.3364          | 0.8406    | 0.8522 | 0.8464 | 0.9089   |
+| 0.368         | 2.68  | 1700 | 0.3404          | 0.8467    | 0.8536 | 0.8501 | 0.9107   |
+| 0.368         | 2.84  | 1800 | 0.3319          | 0.8405    | 0.8501 | 0.8453 | 0.9090   |
+| 0.368         | 3.0   | 1900 | 0.3324          | 0.8584    | 0.8492 | 0.8538 | 0.9117   |
+| 0.2949        | 3.15  | 2000 | 0.3204          | 0.8691    | 0.8404 | 0.8545 | 0.9119   |
+| 0.2949        | 3.31  | 2100 | 0.3107          | 0.8599    | 0.8547 | 0.8573 | 0.9162   |
+| 0.2949        | 3.47  | 2200 | 0.3169          | 0.8680    | 0.8489 | 0.8584 | 0.9146   |
+| 0.2949        | 3.63  | 2300 | 0.3190          | 0.8683    | 0.8519 | 0.8600 | 0.9152   |
+| 0.2949        | 3.79  | 2400 | 0.2975          | 0.8631    | 0.8617 | 0.8624 | 0.9182   |
+| 0.2438        | 3.94  | 2500 | 0.3040          | 0.8566    | 0.8640 | 0.8603 | 0.9171   |
+| 0.2438        | 4.1   | 2600 | 0.3045          | 0.8585    | 0.8642 | 0.8613 | 0.9181   |
+| 0.2438        | 4.26  | 2700 | 0.3139          | 0.8498    | 0.8748 | 0.8621 | 0.9160   |
+| 0.2438        | 4.42  | 2800 | 0.2985          | 0.8642    | 0.8672 | 0.8657 | 0.9214   |
+| 0.2438        | 4.57  | 2900 | 0.3047          | 0.8688    | 0.8694 | 0.8691 | 0.9214   |
+| 0.2028        | 4.73  | 3000 | 0.2986          | 0.8686    | 0.8695 | 0.8691 | 0.9207   |
+| 0.2028        | 4.89  | 3100 | 0.3135          | 0.8628    | 0.8755 | 0.8691 | 0.9197   |
+| 0.2028        | 5.05  | 3200 | 0.2927          | 0.8656    | 0.8755 | 0.8705 | 0.9217   |
+| 0.2028        | 5.21  | 3300 | 0.2992          | 0.8724    | 0.8697 | 0.8711 | 0.9228   |
+| 0.2028        | 5.36  | 3400 | 0.2975          | 0.8831    | 0.8639 | 0.8734 | 0.9244   |
+| 0.1814        | 5.52  | 3500 | 0.2897          | 0.8736    | 0.8788 | 0.8762 | 0.9250   |
+| 0.1814        | 5.68  | 3600 | 0.3118          | 0.8674    | 0.8751 | 0.8712 | 0.9216   |
+| 0.1814        | 5.84  | 3700 | 0.2974          | 0.8735    | 0.8779 | 0.8757 | 0.9237   |
+| 0.1814        | 5.99  | 3800 | 0.2957          | 0.8696    | 0.8815 | 0.8755 | 0.9240   |
+| 0.1814        | 6.15  | 3900 | 0.3120          | 0.8698    | 0.8817 | 0.8757 | 0.9250   |
+| 0.1602        | 6.31  | 4000 | 0.3080          | 0.8715    | 0.8800 | 0.8757 | 0.9238   |
+| 0.1602        | 6.47  | 4100 | 0.3031          | 0.8767    | 0.8788 | 0.8777 | 0.9261   |
+| 0.1602        | 6.62  | 4200 | 0.3146          | 0.8699    | 0.8784 | 0.8741 | 0.9227   |
+| 0.1602        | 6.78  | 4300 | 0.3085          | 0.8717    | 0.8788 | 0.8752 | 0.9248   |
+| 0.1602        | 6.94  | 4400 | 0.3023          | 0.8749    | 0.8756 | 0.8752 | 0.9250   |
+| 0.1383        | 7.1   | 4500 | 0.3025          | 0.8860    | 0.8735 | 0.8797 | 0.9252   |
+| 0.1383        | 7.26  | 4600 | 0.3026          | 0.8775    | 0.8810 | 0.8792 | 0.9272   |
+| 0.1383        | 7.41  | 4700 | 0.3146          | 0.8715    | 0.8832 | 0.8773 | 0.9251   |
+| 0.1383        | 7.57  | 4800 | 0.3113          | 0.8769    | 0.8803 | 0.8786 | 0.9275   |
+| 0.1383        | 7.73  | 4900 | 0.3073          | 0.8797    | 0.8786 | 0.8792 | 0.9261   |
+| 0.1306        | 7.89  | 5000 | 0.3163          | 0.8714    | 0.8828 | 0.8770 | 0.9248   |
+| 0.1306        | 8.04  | 5100 | 0.3163          | 0.8753    | 0.8810 | 0.8781 | 0.9250   |
+| 0.1306        | 8.2   | 5200 | 0.3132          | 0.8743    | 0.8804 | 0.8773 | 0.9257   |
+| 0.1306        | 8.36  | 5300 | 0.3119          | 0.8735    | 0.8837 | 0.8786 | 0.9264   |
+| 0.1306        | 8.52  | 5400 | 0.3145          | 0.8826    | 0.8779 | 0.8802 | 0.9272   |
+| 0.1174        | 8.68  | 5500 | 0.3166          | 0.8776    | 0.8811 | 0.8794 | 0.9261   |
+| 0.1174        | 8.83  | 5600 | 0.3146          | 0.8776    | 0.8814 | 0.8795 | 0.9260   |
+| 0.1174        | 8.99  | 5700 | 0.3135          | 0.8763    | 0.8826 | 0.8795 | 0.9271   |
+| 0.1174        | 9.15  | 5800 | 0.3154          | 0.8794    | 0.8818 | 0.8806 | 0.9275   |
+| 0.1174        | 9.31  | 5900 | 0.3152          | 0.8788    | 0.8817 | 0.8802 | 0.9274   |
+| 0.11          | 9.46  | 6000 | 0.3159          | 0.8765    | 0.8812 | 0.8789 | 0.9268   |
+
+
+### Framework versions
+
+- Transformers 4.25.0.dev0
+- Pytorch 1.12.1
+- Datasets 2.6.1
+- Tokenizers 0.13.1

config.json

@@ -0,0 +1,96 @@
+{
+  "_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": "Ignore",
+    "1": "Store_name_value",
+    "2": "Store_name_key",
+    "3": "Store_addr_value",
+    "4": "Store_addr_key",
+    "5": "Tel_value",
+    "6": "Tel_key",
+    "7": "Date_value",
+    "8": "Date_key",
+    "9": "Time_value",
+    "10": "Time_key",
+    "11": "Prod_item_value",
+    "12": "Prod_item_key",
+    "13": "Prod_quantity_value",
+    "14": "Prod_quantity_key",
+    "15": "Prod_price_value",
+    "16": "Prod_price_key",
+    "17": "Subtotal_value",
+    "18": "Subtotal_key",
+    "19": "Tax_value",
+    "20": "Tax_key",
+    "21": "Tips_value",
+    "22": "Tips_key",
+    "23": "Total_value",
+    "24": "Total_key",
+    "25": "Others"
+  },
+  "initializer_range": 0.02,
+  "input_size": 224,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Date_key": 8,
+    "Date_value": 7,
+    "Ignore": 0,
+    "Others": 25,
+    "Prod_item_key": 12,
+    "Prod_item_value": 11,
+    "Prod_price_key": 16,
+    "Prod_price_value": 15,
+    "Prod_quantity_key": 14,
+    "Prod_quantity_value": 13,
+    "Store_addr_key": 4,
+    "Store_addr_value": 3,
+    "Store_name_key": 2,
+    "Store_name_value": 1,
+    "Subtotal_key": 18,
+    "Subtotal_value": 17,
+    "Tax_key": 20,
+    "Tax_value": 19,
+    "Tel_key": 6,
+    "Tel_value": 5,
+    "Time_key": 10,
+    "Time_value": 9,
+    "Tips_key": 22,
+    "Tips_value": 21,
+    "Total_key": 24,
+    "Total_value": 23
+  },
+  "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": "4.25.0.dev0",
+  "type_vocab_size": 1,
+  "visual_embed": true,
+  "vocab_size": 50265
+}

logs/1667783647.4231527/events.out.tfevents.1667783647.132-145-141-187.64914.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaee60766e7c2c7b8902f0070d4aeced0fe89ff6780559175cf0a42245664e83
+size 5474

logs/events.out.tfevents.1667783647.132-145-141-187.64914.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a40298075d21e63e9f6f3e829a8f3e11957507c6c7801a4e24a3b6ebe066c479
+size 35877

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "apply_ocr": false,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "LayoutLMv3ImageProcessor",
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "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": ""
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d98a9eca6095013c09a7d570a4c3a4c36842d281ca410d72db88b1c34c4c6378
+size 503827343

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 +1,87 @@
+{
+  "add_prefix_space": true,
+  "apply_ocr": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "microsoft/layoutlmv3-base",
+  "only_label_first_subword": true,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "pad_token_label": -100,
+  "processor_class": "LayoutLMv3Processor",
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "special_tokens_map_file": null,
+  "tokenizer_class": "LayoutLMv3Tokenizer",
+  "trim_offsets": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27e0317d32dfe56fd0bcbaa84b940b5987f6cd84187347341f903da547986a8c
+size 3375