Hugging Face's logo

dennisjooo
/
emotion_classification

Image Classification
Transformers
PyTorch
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
9
dennisjooo commited on
Commit
2409a1c
•
1 Parent(s): fd26a5f

End of training

Browse files
Files changed (2) hide show
  1. README.md +64 -71
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -4,127 +4,120 @@ base_model: google/vit-base-patch16-224-in21k
4
  tags:
5
  - generated_from_trainer
6
  datasets:
7
- - FastJobs/Visual_Emotional_Analysis
8
  metrics:
9
  - accuracy
10
  - precision
11
  - f1
12
  model-index:
13
- - name: emo-vit-base-patch16-224-in21k
14
  results:
15
  - task:
16
  name: Image Classification
17
  type: image-classification
18
  dataset:
19
- name: FastJobs/Visual_Emotional_Analysis
20
- type: FastJobs/Visual_Emotional_Analysis
21
  config: default
22
  split: train
23
  args: default
24
  metrics:
25
  - name: Accuracy
26
  type: accuracy
27
- value: 0.61875
28
  - name: Precision
29
  type: precision
30
- value: 0.6229001976284585
31
  - name: F1
32
  type: f1
33
- value: 0.6163114517061885
34
  ---
35
 
36
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
37
  should probably proofread and complete it, then remove this comment. -->
38
 
39
- # emo-vit-base-patch16-224-in21k
40
 
41
- This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k)
42
- on the [FastJobs/Visual_Emotional_Analysis](https://huggingface.co/datasets/FastJobs/Visual_Emotional_Analysis) dataset.
43
  It achieves the following results on the evaluation set:
44
- - Loss: 1.2392
45
- - Accuracy: 0.6188
46
- - Precision: 0.6229
47
- - F1: 0.6163
48
 
 
49
 
50
- ## Training and evaluation data
51
-
52
- ### Data Split
53
 
54
- Used a 4:1 ratio for training and development sets and a seed of 42.
55
 
56
- ### Pre-processing Augmentation
57
 
58
- The main pre-processing phase for both training and evaluation includes:
59
- - Resizing to (224, 224, 3)
60
- - Normalizing images using a mean and standard deviation of [0.5, 0.5, 0.5]
61
 
62
- Other than the aforementioned pre-processing, the training set was augmented using:
63
- - Random horizontal & vertical flip
64
- - Color jitter
65
- - Random resized crop
66
 
67
  ## Training procedure
68
 
69
  ### Training hyperparameters
70
 
71
  The following hyperparameters were used during training:
72
- - learning_rate: 0.0003
73
  - train_batch_size: 64
74
  - eval_batch_size: 64
75
  - seed: 42
76
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
77
  - lr_scheduler_type: cosine_with_restarts
78
- - lr_scheduler_warmup_steps: 10
79
  - num_epochs: 100
80
 
81
  ### Training results
82
 
83
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | F1 |
84
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|
85
- | 2.0652 | 1.0 | 10 | 1.9712 | 0.35 | 0.3441 | 0.3294 |
86
- | 1.9006 | 2.0 | 20 | 1.6055 | 0.425 | 0.3497 | 0.3578 |
87
- | 1.6274 | 3.0 | 30 | 1.4991 | 0.4875 | 0.5747 | 0.4621 |
88
- | 1.4742 | 4.0 | 40 | 1.4417 | 0.4313 | 0.4744 | 0.4037 |
89
- | 1.3546 | 5.0 | 50 | 1.3699 | 0.4125 | 0.3896 | 0.3387 |
90
- | 1.2574 | 6.0 | 60 | 1.2200 | 0.5125 | 0.5072 | 0.4783 |
91
- | 1.183 | 7.0 | 70 | 1.1368 | 0.5375 | 0.5802 | 0.5341 |
92
- | 1.0869 | 8.0 | 80 | 1.1332 | 0.5687 | 0.6024 | 0.5622 |
93
- | 1.002 | 9.0 | 90 | 1.1178 | 0.55 | 0.5663 | 0.5423 |
94
- | 0.9453 | 10.0 | 100 | 1.1601 | 0.5563 | 0.5994 | 0.5515 |
95
- | 0.9495 | 11.0 | 110 | 1.1202 | 0.525 | 0.5695 | 0.5266 |
96
- | 0.7805 | 12.0 | 120 | 1.1620 | 0.5375 | 0.5577 | 0.5323 |
97
- | 0.7487 | 13.0 | 130 | 1.2094 | 0.5687 | 0.6218 | 0.5716 |
98
- | 0.6805 | 14.0 | 140 | 1.2662 | 0.5437 | 0.5875 | 0.5345 |
99
- | 0.6491 | 15.0 | 150 | 1.1673 | 0.5625 | 0.5707 | 0.5511 |
100
- | 0.6168 | 16.0 | 160 | 1.2981 | 0.475 | 0.5388 | 0.4846 |
101
- | 0.5512 | 17.0 | 170 | 1.2624 | 0.575 | 0.6110 | 0.5726 |
102
- | 0.5532 | 18.0 | 180 | 1.2392 | 0.6188 | 0.6229 | 0.6163 |
103
- | 0.4931 | 19.0 | 190 | 1.4012 | 0.5375 | 0.5542 | 0.5277 |
104
- | 0.4919 | 20.0 | 200 | 1.2323 | 0.5813 | 0.5825 | 0.5758 |
105
- | 0.4243 | 21.0 | 210 | 1.3046 | 0.5875 | 0.5967 | 0.5750 |
106
- | 0.3971 | 22.0 | 220 | 1.3169 | 0.5687 | 0.5812 | 0.5610 |
107
- | 0.3534 | 23.0 | 230 | 1.4052 | 0.5625 | 0.6240 | 0.5527 |
108
- | 0.3456 | 24.0 | 240 | 1.3372 | 0.5875 | 0.5998 | 0.5838 |
109
- | 0.3381 | 25.0 | 250 | 1.4000 | 0.55 | 0.5589 | 0.5468 |
110
- | 0.3786 | 26.0 | 260 | 1.3531 | 0.5687 | 0.6269 | 0.5764 |
111
- | 0.3614 | 27.0 | 270 | 1.3696 | 0.5687 | 0.6019 | 0.5704 |
112
- | 0.312 | 28.0 | 280 | 1.3523 | 0.6125 | 0.6351 | 0.6148 |
113
- | 0.2643 | 29.0 | 290 | 1.4510 | 0.5813 | 0.6286 | 0.5825 |
114
- | 0.3553 | 30.0 | 300 | 1.5255 | 0.6062 | 0.6560 | 0.6113 |
115
- | 0.2807 | 31.0 | 310 | 1.5901 | 0.5813 | 0.5921 | 0.5655 |
116
- | 0.3252 | 32.0 | 320 | 1.5669 | 0.575 | 0.5764 | 0.5639 |
117
- | 0.3796 | 33.0 | 330 | 1.6251 | 0.5375 | 0.5776 | 0.5431 |
118
- | 0.2635 | 34.0 | 340 | 1.7397 | 0.4938 | 0.5513 | 0.4944 |
119
- | 0.2583 | 35.0 | 350 | 1.4806 | 0.6 | 0.6566 | 0.6099 |
120
- | 0.3006 | 36.0 | 360 | 1.4808 | 0.5813 | 0.6310 | 0.5863 |
121
- | 0.3082 | 37.0 | 370 | 1.7077 | 0.5188 | 0.5680 | 0.5156 |
122
- | 0.3346 | 38.0 | 380 | 1.6861 | 0.575 | 0.6725 | 0.5638 |
123
- | 0.291 | 39.0 | 390 | 1.5484 | 0.5625 | 0.5631 | 0.5535 |
124
- | 0.2313 | 40.0 | 400 | 1.4933 | 0.5563 | 0.5564 | 0.5526 |
125
- | 0.2163 | 41.0 | 410 | 1.5836 | 0.5938 | 0.6046 | 0.5929 |
126
- | 0.2201 | 42.0 | 420 | 1.6363 | 0.5687 | 0.5954 | 0.5672 |
127
- | 0.2077 | 43.0 | 430 | 1.6746 | 0.5687 | 0.5623 | 0.5622 |
128
 
129
 
130
  ### Framework versions
 
4
  tags:
5
  - generated_from_trainer
6
  datasets:
7
+ - imagefolder
8
  metrics:
9
  - accuracy
10
  - precision
11
  - f1
12
  model-index:
13
+ - name: emotion_classification
14
  results:
15
  - task:
16
  name: Image Classification
17
  type: image-classification
18
  dataset:
19
+ name: imagefolder
20
+ type: imagefolder
21
  config: default
22
  split: train
23
  args: default
24
  metrics:
25
  - name: Accuracy
26
  type: accuracy
27
+ value: 0.63125
28
  - name: Precision
29
  type: precision
30
+ value: 0.6430986797647803
31
  - name: F1
32
  type: f1
33
+ value: 0.6224944698106615
34
  ---
35
 
36
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
37
  should probably proofread and complete it, then remove this comment. -->
38
 
39
+ # emotion_classification
40
 
41
+ This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
 
42
  It achieves the following results on the evaluation set:
43
+ - Loss: 1.1031
44
+ - Accuracy: 0.6312
45
+ - Precision: 0.6431
46
+ - F1: 0.6225
47
 
48
+ ## Model description
49
 
50
+ More information needed
 
 
51
 
52
+ ## Intended uses & limitations
53
 
54
+ More information needed
55
 
56
+ ## Training and evaluation data
 
 
57
 
58
+ More information needed
 
 
 
59
 
60
  ## Training procedure
61
 
62
  ### Training hyperparameters
63
 
64
  The following hyperparameters were used during training:
65
+ - learning_rate: 0.0002
66
  - train_batch_size: 64
67
  - eval_batch_size: 64
68
  - seed: 42
69
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
70
  - lr_scheduler_type: cosine_with_restarts
71
+ - lr_scheduler_warmup_steps: 20
72
  - num_epochs: 100
73
 
74
  ### Training results
75
 
76
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | F1 |
77
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|
78
+ | 2.0742 | 1.0 | 10 | 2.0533 | 0.1938 | 0.1942 | 0.1858 |
79
+ | 2.0081 | 2.0 | 20 | 1.8908 | 0.3438 | 0.3701 | 0.3368 |
80
+ | 1.7211 | 3.0 | 30 | 1.5199 | 0.5312 | 0.4821 | 0.4844 |
81
+ | 1.5641 | 4.0 | 40 | 1.4248 | 0.4875 | 0.5314 | 0.4532 |
82
+ | 1.3979 | 5.0 | 50 | 1.2973 | 0.5375 | 0.5162 | 0.5023 |
83
+ | 1.2997 | 6.0 | 60 | 1.2016 | 0.525 | 0.4828 | 0.4826 |
84
+ | 1.2348 | 7.0 | 70 | 1.1670 | 0.5875 | 0.6375 | 0.5941 |
85
+ | 1.1481 | 8.0 | 80 | 1.1292 | 0.6 | 0.6111 | 0.5961 |
86
+ | 1.079 | 9.0 | 90 | 1.1782 | 0.5188 | 0.5265 | 0.5005 |
87
+ | 0.9909 | 10.0 | 100 | 1.1115 | 0.5813 | 0.5892 | 0.5668 |
88
+ | 0.9662 | 11.0 | 110 | 1.1047 | 0.5938 | 0.6336 | 0.5723 |
89
+ | 0.8149 | 12.0 | 120 | 1.0944 | 0.5563 | 0.5648 | 0.5499 |
90
+ | 0.7661 | 13.0 | 130 | 1.0932 | 0.5625 | 0.5738 | 0.5499 |
91
+ | 0.7067 | 14.0 | 140 | 1.0787 | 0.6062 | 0.6318 | 0.6045 |
92
+ | 0.6708 | 15.0 | 150 | 1.1140 | 0.6188 | 0.6463 | 0.6134 |
93
+ | 0.6268 | 16.0 | 160 | 1.0875 | 0.5813 | 0.6016 | 0.5815 |
94
+ | 0.5473 | 17.0 | 170 | 1.1483 | 0.5938 | 0.6027 | 0.5844 |
95
+ | 0.5228 | 18.0 | 180 | 1.1031 | 0.6312 | 0.6431 | 0.6225 |
96
+ | 0.4805 | 19.0 | 190 | 1.1747 | 0.5813 | 0.6057 | 0.5848 |
97
+ | 0.4995 | 20.0 | 200 | 1.1865 | 0.6062 | 0.6062 | 0.5980 |
98
+ | 0.456 | 21.0 | 210 | 1.2619 | 0.6 | 0.6020 | 0.5843 |
99
+ | 0.4697 | 22.0 | 220 | 1.2476 | 0.5625 | 0.5804 | 0.5647 |
100
+ | 0.3656 | 23.0 | 230 | 1.3106 | 0.6125 | 0.6645 | 0.6130 |
101
+ | 0.394 | 24.0 | 240 | 1.3398 | 0.5437 | 0.5627 | 0.5460 |
102
+ | 0.35 | 25.0 | 250 | 1.3391 | 0.5938 | 0.5940 | 0.5860 |
103
+ | 0.3508 | 26.0 | 260 | 1.2846 | 0.575 | 0.6070 | 0.5821 |
104
+ | 0.3106 | 27.0 | 270 | 1.3495 | 0.575 | 0.6258 | 0.5663 |
105
+ | 0.3265 | 28.0 | 280 | 1.4450 | 0.5375 | 0.6512 | 0.5248 |
106
+ | 0.2806 | 29.0 | 290 | 1.5145 | 0.5188 | 0.5840 | 0.5151 |
107
+ | 0.3276 | 30.0 | 300 | 1.5207 | 0.5188 | 0.5741 | 0.5164 |
108
+ | 0.2932 | 31.0 | 310 | 1.3179 | 0.6312 | 0.6421 | 0.6298 |
109
+ | 0.3542 | 32.0 | 320 | 1.3720 | 0.5875 | 0.6157 | 0.5780 |
110
+ | 0.3321 | 33.0 | 330 | 1.4787 | 0.5625 | 0.6088 | 0.5714 |
111
+ | 0.2641 | 34.0 | 340 | 1.5468 | 0.5375 | 0.5817 | 0.5385 |
112
+ | 0.2432 | 35.0 | 350 | 1.4893 | 0.5687 | 0.6012 | 0.5538 |
113
+ | 0.275 | 36.0 | 360 | 1.4775 | 0.575 | 0.5827 | 0.5710 |
114
+ | 0.239 | 37.0 | 370 | 1.4812 | 0.575 | 0.6100 | 0.5739 |
115
+ | 0.2658 | 38.0 | 380 | 1.7335 | 0.5563 | 0.6547 | 0.5436 |
116
+ | 0.3026 | 39.0 | 390 | 1.5692 | 0.5875 | 0.6401 | 0.5854 |
117
+ | 0.1867 | 40.0 | 400 | 1.4908 | 0.5687 | 0.5921 | 0.5741 |
118
+ | 0.1931 | 41.0 | 410 | 1.6608 | 0.5375 | 0.5834 | 0.5396 |
119
+ | 0.2416 | 42.0 | 420 | 1.5172 | 0.5938 | 0.6259 | 0.5935 |
120
+ | 0.1943 | 43.0 | 430 | 1.5260 | 0.5437 | 0.5775 | 0.5498 |
121
 
122
 
123
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20e97cb19753fa8cd2e82b55fb7716057dc65e1428de206641a4fcb97dfca8c4
3
  size 343287149
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:748f0dd2bd7134254a547fcf47842053881f8de66aa2463ddb1a3233e0d0afb4
3
  size 343287149