Hugging Face's logo

PawanKrGunjan
/
license_plate_recognizer

Image-to-Text
Transformers
Safetensors
English
vision-encoder-decoder
image-text-to-text
license-plate-recognition
ocr
Eval Results
Inference Endpoints
Model card Files Community
PawanKrGunjan commited on
Commit
2384a40
•
1 Parent(s): e9bc296

End of training

Browse files
Files changed (2) hide show
  1. README.md +25 -37
  2. model.safetensors +1 -1
README.md CHANGED
@@ -5,27 +5,18 @@ tags:
5
  model-index:
6
  - name: license_plate_recognizer
7
  results: []
8
- license: mit
9
- datasets:
10
- - PawanKrGunjan/license_plates
11
- language:
12
- - en
13
- metrics:
14
- - cer
15
- library_name: transformers
16
- pipeline_tag: image-to-text
17
  ---
18
 
19
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
20
  should probably proofread and complete it, then remove this comment. -->
21
 
22
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/pawankrgunjan/huggingface/runs/ajvl0e6b)
23
  # license_plate_recognizer
24
 
25
  This model is a fine-tuned version of [microsoft/trocr-base-handwritten](https://huggingface.co/microsoft/trocr-base-handwritten) on an unknown dataset.
26
  It achieves the following results on the evaluation set:
27
- - Loss: 0.0097
28
- - Cer: 0.0036
29
 
30
  ## Model description
31
 
@@ -50,35 +41,32 @@ The following hyperparameters were used during training:
50
  - seed: 42
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
- - num_epochs: 23
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Cer |
58
  |:-------------:|:-----:|:----:|:---------------:|:------:|
59
- | 0.1485 | 1.0 | 397 | 0.0528 | 0.0182 |
60
- | 0.0843 | 2.0 | 794 | 0.0371 | 0.0089 |
61
- | 0.0552 | 3.0 | 1191 | 0.0417 | 0.0129 |
62
- | 0.0812 | 4.0 | 1588 | 0.0386 | 0.0115 |
63
- | 0.0315 | 5.0 | 1985 | 0.0198 | 0.0053 |
64
- | 0.0178 | 6.0 | 2382 | 0.0263 | 0.0084 |
65
- | 0.0341 | 7.0 | 2779 | 0.0179 | 0.0067 |
66
- | 0.0143 | 8.0 | 3176 | 0.0149 | 0.0080 |
67
- | 0.0047 | 9.0 | 3573 | 0.0055 | 0.0027 |
68
- | 0.0163 | 10.0 | 3970 | 0.0062 | 0.0022 |
69
- | 0.0045 | 11.0 | 4367 | 0.0049 | 0.0027 |
70
- | 0.0115 | 12.0 | 4764 | 0.0077 | 0.0053 |
71
- | 0.0014 | 13.0 | 5161 | 0.0031 | 0.0022 |
72
- | 0.0081 | 14.0 | 5558 | 0.0052 | 0.0031 |
73
- | 0.0001 | 15.0 | 5955 | 0.0056 | 0.0035 |
74
- | 0.0005 | 16.0 | 6352 | 0.0057 | 0.0027 |
75
- | 0.0009 | 17.0 | 6749 | 0.0053 | 0.0022 |
76
- | 0.0003 | 18.0 | 7146 | 0.0067 | 0.0027 |
77
- | 0.0001 | 19.0 | 7543 | 0.0044 | 0.0018 |
78
- | 0.0001 | 20.0 | 7940 | 0.0052 | 0.0018 |
79
- | 0.0 | 21.0 | 8337 | 0.0050 | 0.0018 |
80
- | 0.0 | 22.0 | 8734 | 0.0051 | 0.0018 |
81
- | 0.0 | 23.0 | 9131 | 0.0051 | 0.0018 |
82
 
83
 
84
  ### Framework versions
@@ -86,4 +74,4 @@ The following hyperparameters were used during training:
86
  - Transformers 4.42.3
87
  - Pytorch 2.1.2
88
  - Datasets 2.20.0
89
- - Tokenizers 0.19.1
 
5
  model-index:
6
  - name: license_plate_recognizer
7
  results: []
 
 
 
 
 
 
 
 
 
8
  ---
9
 
10
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
  should probably proofread and complete it, then remove this comment. -->
12
 
13
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/pawankrgunjan/huggingface/runs/3caod3mu)
14
  # license_plate_recognizer
15
 
16
  This model is a fine-tuned version of [microsoft/trocr-base-handwritten](https://huggingface.co/microsoft/trocr-base-handwritten) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.0098
19
+ - Cer: 0.0053
20
 
21
  ## Model description
22
 
 
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
+ - num_epochs: 20
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Cer |
49
  |:-------------:|:-----:|:----:|:---------------:|:------:|
50
+ | 0.1379 | 1.0 | 397 | 0.0408 | 0.0124 |
51
+ | 0.0817 | 2.0 | 794 | 0.0313 | 0.0093 |
52
+ | 0.0641 | 3.0 | 1191 | 0.0253 | 0.0089 |
53
+ | 0.0431 | 4.0 | 1588 | 0.0221 | 0.0089 |
54
+ | 0.0246 | 5.0 | 1985 | 0.0233 | 0.0067 |
55
+ | 0.0192 | 6.0 | 2382 | 0.0193 | 0.0053 |
56
+ | 0.0205 | 7.0 | 2779 | 0.0221 | 0.0062 |
57
+ | 0.0158 | 8.0 | 3176 | 0.0134 | 0.0062 |
58
+ | 0.0074 | 9.0 | 3573 | 0.0086 | 0.0040 |
59
+ | 0.0074 | 10.0 | 3970 | 0.0056 | 0.0027 |
60
+ | 0.0036 | 11.0 | 4367 | 0.0033 | 0.0018 |
61
+ | 0.0079 | 12.0 | 4764 | 0.0075 | 0.0049 |
62
+ | 0.002 | 13.0 | 5161 | 0.0039 | 0.0027 |
63
+ | 0.0004 | 14.0 | 5558 | 0.0028 | 0.0022 |
64
+ | 0.0001 | 15.0 | 5955 | 0.0039 | 0.0027 |
65
+ | 0.0001 | 16.0 | 6352 | 0.0047 | 0.0035 |
66
+ | 0.0011 | 17.0 | 6749 | 0.0041 | 0.0027 |
67
+ | 0.0001 | 18.0 | 7146 | 0.0053 | 0.0018 |
68
+ | 0.0001 | 19.0 | 7543 | 0.0047 | 0.0018 |
69
+ | 0.0001 | 20.0 | 7940 | 0.0047 | 0.0018 |
 
 
 
70
 
71
 
72
  ### Framework versions
 
74
  - Transformers 4.42.3
75
  - Pytorch 2.1.2
76
  - Datasets 2.20.0
77
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3796b50b66a532aa2f2351fc62bd7f940913fbb4585c7e09c4b0e0b727d17cbe
3
  size 1335747032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:235e4c31c949bead52427e313a95567390534992261bd7a276229ddf209f315f
3
  size 1335747032