Hugging Face's logo

carlosleao
/
vit-Facial-Expression-Recognition

Image Classification
Transformers
Safetensors
vit
Generated from Trainer
Inference Endpoints
Model card Files Community
carlosleao commited on
Commit
fdc1f3b
•
1 Parent(s): 0766113

facial-expression-recognition-ferplus

Browse files
Files changed (4) hide show
  1. README.md +36 -17
  2. all_results.json +6 -6
  3. eval_results.json +6 -6
  4. model.safetensors +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [carlosleao/vit-Facial-Expression-Recognition](https://huggingface.co/carlosleao/vit-Facial-Expression-Recognition) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.5831
21
- - Accuracy: 0.4234
22
 
23
  ## Model description
24
 
@@ -52,25 +52,44 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-------:|:----:|:---------------:|:--------:|
55
- | 1.7711 | 2.0833 | 100 | 1.7038 | 0.3915 |
56
- | 1.5964 | 4.1667 | 200 | 1.5836 | 0.3957 |
57
- | 1.5002 | 6.25 | 300 | 1.5438 | 0.4113 |
58
- | 1.3591 | 8.3333 | 400 | 1.5690 | 0.4016 |
59
- | 1.1821 | 10.4167 | 500 | 1.5831 | 0.4234 |
60
- | 0.9323 | 12.5 | 600 | 1.7256 | 0.3960 |
61
- | 0.7237 | 14.5833 | 700 | 1.8623 | 0.3954 |
62
- | 0.5376 | 16.6667 | 800 | 2.0238 | 0.3742 |
63
- | 0.363 | 18.75 | 900 | 2.1839 | 0.3462 |
64
- | 0.238 | 20.8333 | 1000 | 2.2616 | 0.3602 |
65
- | 0.1686 | 22.9167 | 1100 | 2.3515 | 0.3758 |
66
- | 0.0952 | 25.0 | 1200 | 2.4730 | 0.3836 |
67
- | 0.0526 | 27.0833 | 1300 | 2.5531 | 0.3898 |
68
- | 0.0399 | 29.1667 | 1400 | 2.5901 | 0.3778 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
 
70
 
71
  ### Framework versions
72
 
73
  - Transformers 4.45.2
74
  - Pytorch 2.5.0+cu124
75
- - Datasets 3.0.2
76
  - Tokenizers 0.20.1
 
17
 
18
  This model is a fine-tuned version of [carlosleao/vit-Facial-Expression-Recognition](https://huggingface.co/carlosleao/vit-Facial-Expression-Recognition) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 2.2687
21
+ - Accuracy: 0.4177
22
 
23
  ## Model description
24
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-------:|:----:|:---------------:|:--------:|
55
+ | 0.9372 | 0.8959 | 100 | 1.5720 | 0.4417 |
56
+ | 0.9147 | 1.7917 | 200 | 1.6084 | 0.4364 |
57
+ | 0.8393 | 2.6876 | 300 | 1.7268 | 0.4169 |
58
+ | 0.7882 | 3.5834 | 400 | 1.7604 | 0.4227 |
59
+ | 0.6916 | 4.4793 | 500 | 1.8619 | 0.4124 |
60
+ | 0.6367 | 5.3751 | 600 | 1.9493 | 0.4261 |
61
+ | 0.5848 | 6.2710 | 700 | 2.0511 | 0.4046 |
62
+ | 0.5183 | 7.1669 | 800 | 2.1316 | 0.4230 |
63
+ | 0.4788 | 8.0627 | 900 | 2.2210 | 0.4026 |
64
+ | 0.4586 | 8.9586 | 1000 | 2.2687 | 0.4177 |
65
+ | 0.4079 | 9.8544 | 1100 | 2.4038 | 0.3747 |
66
+ | 0.3797 | 10.7503 | 1200 | 2.3664 | 0.4046 |
67
+ | 0.2957 | 11.6461 | 1300 | 2.4534 | 0.4068 |
68
+ | 0.2622 | 12.5420 | 1400 | 2.5413 | 0.3956 |
69
+ | 0.2202 | 13.4378 | 1500 | 2.5601 | 0.4127 |
70
+ | 0.2112 | 14.3337 | 1600 | 2.6560 | 0.3920 |
71
+ | 0.1769 | 15.2296 | 1700 | 2.8006 | 0.3909 |
72
+ | 0.161 | 16.1254 | 1800 | 2.8011 | 0.3928 |
73
+ | 0.155 | 17.0213 | 1900 | 2.9518 | 0.3856 |
74
+ | 0.1309 | 17.9171 | 2000 | 2.9363 | 0.3727 |
75
+ | 0.1001 | 18.8130 | 2100 | 2.9187 | 0.3998 |
76
+ | 0.0816 | 19.7088 | 2200 | 3.0563 | 0.3842 |
77
+ | 0.0672 | 20.6047 | 2300 | 2.9358 | 0.4205 |
78
+ | 0.0567 | 21.5006 | 2400 | 3.1118 | 0.3970 |
79
+ | 0.0524 | 22.3964 | 2500 | 3.2147 | 0.4054 |
80
+ | 0.0413 | 23.2923 | 2600 | 3.1928 | 0.3951 |
81
+ | 0.0368 | 24.1881 | 2700 | 3.1599 | 0.4141 |
82
+ | 0.0275 | 25.0840 | 2800 | 3.1720 | 0.4166 |
83
+ | 0.029 | 25.9798 | 2900 | 3.1924 | 0.4012 |
84
+ | 0.0231 | 26.8757 | 3000 | 3.2031 | 0.4088 |
85
+ | 0.0226 | 27.7716 | 3100 | 3.2125 | 0.4113 |
86
+ | 0.0205 | 28.6674 | 3200 | 3.2122 | 0.4118 |
87
+ | 0.0197 | 29.5633 | 3300 | 3.2126 | 0.4116 |
88
 
89
 
90
  ### Framework versions
91
 
92
  - Transformers 4.45.2
93
  - Pytorch 2.5.0+cu124
94
+ - Datasets 3.0.1
95
  - Tokenizers 0.20.1
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 30.0,
3
- "eval_accuracy": 0.42340286831812257,
4
- "eval_loss": 1.5831071138381958,
5
- "eval_runtime": 26.0496,
6
- "eval_samples_per_second": 117.775,
7
- "eval_steps_per_second": 3.685
8
  }
 
1
  {
2
+ "epoch": 29.83202687569989,
3
+ "eval_accuracy": 0.4177144453758033,
4
+ "eval_loss": 2.268655300140381,
5
+ "eval_runtime": 162.2,
6
+ "eval_samples_per_second": 22.065,
7
+ "eval_steps_per_second": 0.691
8
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 30.0,
3
- "eval_accuracy": 0.42340286831812257,
4
- "eval_loss": 1.5831071138381958,
5
- "eval_runtime": 26.0496,
6
- "eval_samples_per_second": 117.775,
7
- "eval_steps_per_second": 3.685
8
  }
 
1
  {
2
+ "epoch": 29.83202687569989,
3
+ "eval_accuracy": 0.4177144453758033,
4
+ "eval_loss": 2.268655300140381,
5
+ "eval_runtime": 162.2,
6
+ "eval_samples_per_second": 22.065,
7
+ "eval_steps_per_second": 0.691
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4632e07e9f89c723617648395314d40fbcbf1b4d139fa7b6a023a2945490cd53
3
  size 343242432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:652bcae054795a1b1e6282fce1d6a4105f7e41ee5977c190647a41885cfab240
3
  size 343242432