pierreguillou commited on
Commit
4ada266
1 Parent(s): 5ea0281

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +35 -2
README.md CHANGED
@@ -45,6 +45,9 @@ model-index:
45
  - name: f1
46
  type: f1
47
  value: 0.8634
 
 
 
48
  ---
49
 
50
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -59,7 +62,29 @@ It achieves the following results on the evaluation set:
59
  - Precision: 0.8634
60
  - Recall: 0.8634
61
  - F1: 0.8634
62
- - Accuracy: 0.8634
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
 
64
  ## References
65
 
@@ -175,4 +200,12 @@ The following hyperparameters were used during training:
175
  - Transformers 4.26.1
176
  - Pytorch 1.13.1+cu116
177
  - Datasets 2.9.0
178
- - Tokenizers 0.13.2
 
 
 
 
 
 
 
 
45
  - name: f1
46
  type: f1
47
  value: 0.8634
48
+ - name: accuracy
49
+ type: accuracy
50
+ value: 0.6815
51
  ---
52
 
53
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
62
  - Precision: 0.8634
63
  - Recall: 0.8634
64
  - F1: 0.8634
65
+ - Token Accuracy: 0.8634
66
+ - Paragraph Accuracy: 0.6815
67
+
68
+ ## Accuracy at paragraph level
69
+
70
+ - Paragraph Accuracy: 68.15%
71
+ - Accuracy by label
72
+ - Caption: 22.82%
73
+ - Footnote: 0.0%
74
+ - Formula: 97.33%
75
+ - List-item: 8.42%
76
+ - Page-footer: 98.77%
77
+ - Page-header: 77.81%
78
+ - Picture: 39.16%
79
+ - Section-header: 76.17%
80
+ - Table: 37.7%
81
+ - Text: 86.78%
82
+ - Title: 0.0%
83
+
84
+ ![Paragraphs labels vs accuracy (%) of the dataset DocLayNet base of test (model: LayoutXLM base finetuned on DocLayNet base))](https://huggingface.co/pierreguillou/layout-xlm-base-finetuned-with-DocLayNet-base-at-paragraphlevel-ml512/resolve/main/docs/paragraphs_labels_accuracy_DocLayNet_base_test_LayoutXLM_base_paragraph_level_512.png)
85
+
86
+ ![Confusion matrix of the labeled blocks of the dataset DocLayNet base of test (model: LayoutXLM base finetuned on DocLayNet base)](https://huggingface.co/pierreguillou/layout-xlm-base-finetuned-with-DocLayNet-base-at-paragraphlevel-ml512/resolve/main/docs/confusion_matrix_labeled_paragraphs_DocLayNet_base_test_LayoutXLM_base_paragraph_level_512.png)
87
+
88
 
89
  ## References
90
 
200
  - Transformers 4.26.1
201
  - Pytorch 1.13.1+cu116
202
  - Datasets 2.9.0
203
+ - Tokenizers 0.13.2
204
+
205
+ ## Other models
206
+ - Line level
207
+ - [Document Understanding model (finetuned LiLT base at line level on DocLayNet base)](https://huggingface.co/pierreguillou/lilt-xlm-roberta-base-finetuned-with-DocLayNet-base-at-linelevel-ml384) (line accuracy: xxxx)
208
+ - [Document Understanding model (finetuned LayoutXLM base at line level on DocLayNet base)](https://huggingface.co/pierreguillou/layout-xlm-base-finetuned-with-DocLayNet-base-at-linelevel-ml384) (line accuracy: xxx)
209
+ - Paragraph level
210
+ - [Document Understanding model (finetuned LiLT base at paragraph level on DocLayNet base)](https://huggingface.co/pierreguillou/lilt-xlm-roberta-base-finetuned-with-DocLayNet-base-at-paragraphlevel-ml512) (paragraph accuracy: 68.15%)
211
+ - [Document Understanding model (finetuned LayoutXLM base at paragraph level on DocLayNet base)](https://huggingface.co/pierreguillou/layout-xlm-base-finetuned-with-DocLayNet-base-at-paragraphlevel-ml512) (paragraph accuracy: 86.55%)