Hugging Face's logo

handi88
/
FastJobs-Visual_Emotions_Analysis

Generated from Trainer
Eval Results
Model card Files Community
handi88 commited on
Commit
c8f01ed
•
1 Parent(s): bd55a30

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +157 -0
README.md ADDED
@@ -0,0 +1,157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ 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: emotion_classification
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: FastJobs--Visual_Emotional_Analysis
22
+ split: train
23
+ args: FastJobs--Visual_Emotional_Analysis
24
+ metrics:
25
+ - name: Accuracy
26
+ type: accuracy
27
+ value: 0.66875
28
+ - name: Precision
29
+ type: precision
30
+ value: 0.7104119480438352
31
+ - name: F1
32
+ type: f1
33
+ value: 0.6712765732314218
34
+ ---
35
+ # Emotion Classification
36
+
37
+ This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k)
38
+ on the [FastJobs/Visual_Emotional_Analysis](https://huggingface.co/datasets/FastJobs/Visual_Emotional_Analysis) dataset.
39
+
40
+ In theory, the accuracy for a random guess on this dataset is 0.125 (8 labels and you need to choose one).
41
+
42
+ It achieves the following results on the evaluation set:
43
+ - Loss: 1.0511
44
+ - Accuracy: 0.6687
45
+ - Precision: 0.7104
46
+ - F1: 0.6713
47
+
48
+ ## Model description
49
+
50
+ The Vision Transformer base version trained on ImageNet-21K released by Google.
51
+ Further details can be found on their [repo](https://huggingface.co/google/vit-base-patch16-224-in21k).
52
+
53
+ ## Training and evaluation data
54
+
55
+ ### Data Split
56
+
57
+ Trained on [FastJobs/Visual_Emotional_Analysis](https://huggingface.co/datasets/FastJobs/Visual_Emotional_Analysis) dataset.
58
+ Used a 4:1 ratio for training and development sets and a random seed of 42.
59
+ Also used a seed of 42 for batching the data, completely unrelated lol.
60
+
61
+ ### Pre-processing Augmentation
62
+
63
+ The main pre-processing phase for both training and evaluation includes:
64
+ - Bilinear interpolation to resize the image to (224, 224, 3) because it uses ImageNet images to train the original model
65
+ - Normalizing images using a mean and standard deviation of [0.5, 0.5, 0.5] just like the original model
66
+
67
+ Other than the aforementioned pre-processing, the training set was augmented using:
68
+ - Random horizontal & vertical flip
69
+ - Color jitter
70
+ - Random resized crop
71
+
72
+ ## Training procedure
73
+
74
+ ### Training hyperparameters
75
+
76
+ The following hyperparameters were used during training:
77
+ - learning_rate: 5e-05
78
+ - train_batch_size: 64
79
+ - eval_batch_size: 64
80
+ - seed: 42
81
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
82
+ - lr_scheduler_type: cosine_with_restarts
83
+ - lr_scheduler_warmup_steps: 150
84
+ - num_epochs: 300
85
+
86
+ ### Training results
87
+
88
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | F1 |
89
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|
90
+ | 2.079 | 1.0 | 10 | 2.0895 | 0.0563 | 0.0604 | 0.0521 |
91
+ | 2.0789 | 2.0 | 20 | 2.0851 | 0.0563 | 0.0602 | 0.0529 |
92
+ | 2.0717 | 3.0 | 30 | 2.0773 | 0.0813 | 0.0858 | 0.0783 |
93
+ | 2.0613 | 4.0 | 40 | 2.0658 | 0.125 | 0.1997 | 0.1333 |
94
+ | 2.0445 | 5.0 | 50 | 2.0483 | 0.1875 | 0.2569 | 0.1934 |
95
+ | 2.0176 | 6.0 | 60 | 2.0206 | 0.2313 | 0.2692 | 0.2384 |
96
+ | 1.9894 | 7.0 | 70 | 1.9763 | 0.3063 | 0.3033 | 0.2983 |
97
+ | 1.9232 | 8.0 | 80 | 1.8912 | 0.3625 | 0.3307 | 0.3194 |
98
+ | 1.8256 | 9.0 | 90 | 1.7775 | 0.4062 | 0.3531 | 0.3600 |
99
+ | 1.732 | 10.0 | 100 | 1.6580 | 0.4688 | 0.4158 | 0.4133 |
100
+ | 1.6406 | 11.0 | 110 | 1.5597 | 0.5 | 0.4358 | 0.4370 |
101
+ | 1.5584 | 12.0 | 120 | 1.4855 | 0.5125 | 0.4792 | 0.4784 |
102
+ | 1.4898 | 13.0 | 130 | 1.4248 | 0.5437 | 0.5011 | 0.5098 |
103
+ | 1.4216 | 14.0 | 140 | 1.3692 | 0.5687 | 0.5255 | 0.5289 |
104
+ | 1.3701 | 15.0 | 150 | 1.3158 | 0.5687 | 0.5346 | 0.5360 |
105
+ | 1.3438 | 16.0 | 160 | 1.2842 | 0.5437 | 0.5451 | 0.5098 |
106
+ | 1.2799 | 17.0 | 170 | 1.2620 | 0.5625 | 0.5169 | 0.5194 |
107
+ | 1.2481 | 18.0 | 180 | 1.2321 | 0.5938 | 0.6003 | 0.5811 |
108
+ | 1.1993 | 19.0 | 190 | 1.2108 | 0.5687 | 0.5640 | 0.5412 |
109
+ | 1.1599 | 20.0 | 200 | 1.1853 | 0.55 | 0.5434 | 0.5259 |
110
+ | 1.1087 | 21.0 | 210 | 1.1839 | 0.5563 | 0.5670 | 0.5380 |
111
+ | 1.0757 | 22.0 | 220 | 1.1905 | 0.55 | 0.5682 | 0.5308 |
112
+ | 0.9985 | 23.0 | 230 | 1.1509 | 0.6375 | 0.6714 | 0.6287 |
113
+ | 0.9776 | 24.0 | 240 | 1.1048 | 0.6188 | 0.6222 | 0.6127 |
114
+ | 0.9331 | 25.0 | 250 | 1.1196 | 0.6125 | 0.6345 | 0.6072 |
115
+ | 0.8887 | 26.0 | 260 | 1.1424 | 0.5938 | 0.6174 | 0.5867 |
116
+ | 0.879 | 27.0 | 270 | 1.1232 | 0.6062 | 0.6342 | 0.5978 |
117
+ | 0.8369 | 28.0 | 280 | 1.1172 | 0.6 | 0.6480 | 0.5865 |
118
+ | 0.7864 | 29.0 | 290 | 1.1285 | 0.5938 | 0.6819 | 0.5763 |
119
+ | 0.7775 | 30.0 | 300 | 1.0511 | 0.6687 | 0.7104 | 0.6713 |
120
+ | 0.7281 | 31.0 | 310 | 1.0295 | 0.6562 | 0.6596 | 0.6514 |
121
+ | 0.7348 | 32.0 | 320 | 1.0398 | 0.6375 | 0.6353 | 0.6319 |
122
+ | 0.6896 | 33.0 | 330 | 1.0729 | 0.6062 | 0.6205 | 0.6062 |
123
+ | 0.613 | 34.0 | 340 | 1.0505 | 0.6438 | 0.6595 | 0.6421 |
124
+ | 0.6034 | 35.0 | 350 | 1.0827 | 0.6375 | 0.6593 | 0.6376 |
125
+ | 0.6236 | 36.0 | 360 | 1.1271 | 0.6125 | 0.6238 | 0.6087 |
126
+ | 0.5607 | 37.0 | 370 | 1.0985 | 0.6062 | 0.6254 | 0.6015 |
127
+ | 0.5835 | 38.0 | 380 | 1.0791 | 0.6375 | 0.6624 | 0.6370 |
128
+ | 0.5889 | 39.0 | 390 | 1.1300 | 0.6062 | 0.6529 | 0.6092 |
129
+ | 0.5137 | 40.0 | 400 | 1.1062 | 0.625 | 0.6457 | 0.6226 |
130
+ | 0.4804 | 41.0 | 410 | 1.1452 | 0.6188 | 0.6403 | 0.6158 |
131
+ | 0.4811 | 42.0 | 420 | 1.1271 | 0.6375 | 0.6478 | 0.6347 |
132
+ | 0.5179 | 43.0 | 430 | 1.1942 | 0.5875 | 0.6185 | 0.5874 |
133
+ | 0.4744 | 44.0 | 440 | 1.1515 | 0.6125 | 0.6329 | 0.6160 |
134
+ | 0.4327 | 45.0 | 450 | 1.1321 | 0.6375 | 0.6669 | 0.6412 |
135
+ | 0.4565 | 46.0 | 460 | 1.1742 | 0.625 | 0.6478 | 0.6251 |
136
+ | 0.4006 | 47.0 | 470 | 1.1675 | 0.6062 | 0.6361 | 0.6079 |
137
+ | 0.4541 | 48.0 | 480 | 1.1542 | 0.6125 | 0.6404 | 0.6152 |
138
+ | 0.3689 | 49.0 | 490 | 1.2190 | 0.5875 | 0.6134 | 0.5896 |
139
+ | 0.3794 | 50.0 | 500 | 1.2002 | 0.6062 | 0.6155 | 0.6005 |
140
+ | 0.429 | 51.0 | 510 | 1.2904 | 0.575 | 0.6207 | 0.5849 |
141
+ | 0.431 | 52.0 | 520 | 1.2416 | 0.5875 | 0.6028 | 0.5794 |
142
+ | 0.3813 | 53.0 | 530 | 1.2073 | 0.6125 | 0.6449 | 0.6142 |
143
+ | 0.365 | 54.0 | 540 | 1.2083 | 0.6062 | 0.6454 | 0.6075 |
144
+ | 0.3714 | 55.0 | 550 | 1.1627 | 0.6375 | 0.6576 | 0.6390 |
145
+ | 0.3393 | 56.0 | 560 | 1.1620 | 0.6438 | 0.6505 | 0.6389 |
146
+ | 0.3676 | 57.0 | 570 | 1.1501 | 0.625 | 0.6294 | 0.6258 |
147
+ | 0.3371 | 58.0 | 580 | 1.2779 | 0.5875 | 0.6000 | 0.5792 |
148
+ | 0.3325 | 59.0 | 590 | 1.2719 | 0.575 | 0.5843 | 0.5651 |
149
+ | 0.3509 | 60.0 | 600 | 1.2956 | 0.6 | 0.6422 | 0.6059 |
150
+
151
+
152
+ ### Framework versions
153
+
154
+ - Transformers 4.33.0
155
+ - Pytorch 2.0.0
156
+ - Datasets 2.1.0
157
+ - Tokenizers 0.13.3