ipartzix commited on
Commit
9f60e28
·
verified ·
1 Parent(s): fe5cfba

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LayoutLMv3ForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "coordinate_size": 128,
9
+ "dtype": "float32",
10
+ "eos_token_id": 2,
11
+ "has_relative_attention_bias": true,
12
+ "has_spatial_attention_bias": true,
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0.1,
15
+ "hidden_size": 768,
16
+ "id2label": {
17
+ "0": "Official",
18
+ "1": "Personal",
19
+ "2": "Utility",
20
+ "3": "General"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "input_size": 224,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "General": 3,
27
+ "Official": 0,
28
+ "Personal": 1,
29
+ "Utility": 2
30
+ },
31
+ "layer_norm_eps": 1e-05,
32
+ "max_2d_position_embeddings": 1024,
33
+ "max_position_embeddings": 514,
34
+ "max_rel_2d_pos": 256,
35
+ "max_rel_pos": 128,
36
+ "model_type": "layoutlmv3",
37
+ "num_attention_heads": 12,
38
+ "num_channels": 3,
39
+ "num_hidden_layers": 12,
40
+ "pad_token_id": 1,
41
+ "patch_size": 16,
42
+ "problem_type": "single_label_classification",
43
+ "rel_2d_pos_bins": 64,
44
+ "rel_pos_bins": 32,
45
+ "second_input_size": 112,
46
+ "shape_size": 128,
47
+ "text_embed": true,
48
+ "transformers_version": "5.16.1",
49
+ "type_vocab_size": 1,
50
+ "use_cache": false,
51
+ "visual_embed": true,
52
+ "vocab_size": 50265
53
+ }
labels.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "labels": [
3
+ "Official",
4
+ "Personal",
5
+ "Utility",
6
+ "General"
7
+ ],
8
+ "label2id": {
9
+ "Official": 0,
10
+ "Personal": 1,
11
+ "Utility": 2,
12
+ "General": 3
13
+ },
14
+ "id2label": {
15
+ "0": "Official",
16
+ "1": "Personal",
17
+ "2": "Utility",
18
+ "3": "General"
19
+ }
20
+ }
metadata.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model": "microsoft/layoutlmv3-base",
3
+ "architecture": "LayoutLMv3ForSequenceClassification",
4
+ "ocr_engine": "Tesseract",
5
+ "ocr_config": "--psm 3",
6
+ "ocr_cores": 4,
7
+ "labels": [
8
+ "Official",
9
+ "Personal",
10
+ "Utility",
11
+ "General"
12
+ ],
13
+ "split": {
14
+ "train": 0.7,
15
+ "validation": 0.2,
16
+ "test": 0.1
17
+ },
18
+ "original_train_images": 2858,
19
+ "total_training_samples_per_epoch": 2858,
20
+ "validation_images": 816,
21
+ "test_images": 409,
22
+ "skipped_corrupt_images": 0,
23
+ "corrupt_files": [],
24
+ "train_batch_size": 1,
25
+ "gradient_accumulation_steps": 8,
26
+ "training_precision": "float32",
27
+ "augmentation": "none",
28
+ "dataset_id": "ipartzix/doc-vault-4class-dataset",
29
+ "epochs_run": 10,
30
+ "saved_weight_dtype": "float32",
31
+ "seed": 42,
32
+ "best_checkpoint": "/kaggle/temp/checkpoints/checkpoint-2864",
33
+ "best_validation_macro_f1": 0.9467780332371768,
34
+ "test_accuracy": 0.9462102689486552,
35
+ "test_macro_f1": 0.9453807029757133
36
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7b10a2916417edf75b3dc5e71acb03619918a8939746e21e62642f893b80518
3
+ size 503708904
processor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "apply_ocr": false,
4
+ "do_normalize": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "LayoutLMv3ImageProcessor",
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "resample": 2,
19
+ "rescale_factor": 0.00392156862745098,
20
+ "size": {
21
+ "height": 224,
22
+ "width": 224
23
+ },
24
+ "tesseract_config": ""
25
+ },
26
+ "processor_class": "LayoutLMv3Processor"
27
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "apply_ocr": false,
4
+ "backend": "tokenizers",
5
+ "bos_token": "<s>",
6
+ "cls_token": "<s>",
7
+ "cls_token_box": [
8
+ 0,
9
+ 0,
10
+ 0,
11
+ 0
12
+ ],
13
+ "eos_token": "</s>",
14
+ "errors": "replace",
15
+ "is_local": false,
16
+ "local_files_only": false,
17
+ "mask_token": "<mask>",
18
+ "model_max_length": 512,
19
+ "only_label_first_subword": true,
20
+ "pad_token": "<pad>",
21
+ "pad_token_box": [
22
+ 0,
23
+ 0,
24
+ 0,
25
+ 0
26
+ ],
27
+ "pad_token_label": -100,
28
+ "processor_class": "LayoutLMv3Processor",
29
+ "sep_token": "</s>",
30
+ "sep_token_box": [
31
+ 0,
32
+ 0,
33
+ 0,
34
+ 0
35
+ ],
36
+ "tokenizer_class": "LayoutLMv3Tokenizer",
37
+ "unk_token": "<unk>"
38
+ }