Hugging Face's logo

CynthiaCR
/
emotions_classifier

Image Classification
Transformers
TensorFlow
vit
generated_from_keras_callback
Inference Endpoints
Model card Files Community
1
CynthiaCR commited on
Commit
f2dd93e
•
1 Parent(s): be32577

End of training

Browse files
Files changed (4) hide show
  1. README.md +103 -0
  2. config.json +42 -0
  3. preprocessor_config.json +22 -0
  4. tf_model.h5 +3 -0
README.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_keras_callback
5
+ model-index:
6
+ - name: CynthiaCR/emotions_classifier
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information Keras had access to. You should
11
+ probably proofread and complete it, then remove this comment. -->
12
+
13
+ # CynthiaCR/emotions_classifier
14
+
15
+ This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Train Loss: 2.0432
18
+ - Validation Loss: 2.0673
19
+ - Train Accuracy: 0.1375
20
+ - Epoch: 49
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0003, 'decay_steps': 32000, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
40
+ - training_precision: float32
41
+
42
+ ### Training results
43
+
44
+ | Train Loss | Validation Loss | Train Accuracy | Epoch |
45
+ |:----------:|:---------------:|:--------------:|:-----:|
46
+ | 2.0872 | 2.0954 | 0.1 | 0 |
47
+ | 2.0981 | 2.0914 | 0.1 | 1 |
48
+ | 2.0830 | 2.0902 | 0.1375 | 2 |
49
+ | 2.0908 | 2.0781 | 0.1437 | 3 |
50
+ | 2.0849 | 2.0887 | 0.1375 | 4 |
51
+ | 2.0826 | 2.0909 | 0.1125 | 5 |
52
+ | 2.0832 | 2.0876 | 0.1062 | 6 |
53
+ | 2.0835 | 2.0874 | 0.1125 | 7 |
54
+ | 2.0845 | 2.0856 | 0.1 | 8 |
55
+ | 2.0814 | 2.0876 | 0.1 | 9 |
56
+ | 2.0808 | 2.0851 | 0.1 | 10 |
57
+ | 2.0874 | 2.0849 | 0.1062 | 11 |
58
+ | 2.0837 | 2.0808 | 0.1187 | 12 |
59
+ | 2.0802 | 2.0855 | 0.1187 | 13 |
60
+ | 2.0840 | 2.0819 | 0.1125 | 14 |
61
+ | 2.0889 | 2.0876 | 0.1125 | 15 |
62
+ | 2.0859 | 2.0787 | 0.125 | 16 |
63
+ | 2.0853 | 2.0861 | 0.1062 | 17 |
64
+ | 2.0821 | 2.0830 | 0.1125 | 18 |
65
+ | 2.0813 | 2.0839 | 0.1 | 19 |
66
+ | 2.0814 | 2.0860 | 0.1187 | 20 |
67
+ | 2.0817 | 2.0831 | 0.1313 | 21 |
68
+ | 2.0805 | 2.0842 | 0.1125 | 22 |
69
+ | 2.0804 | 2.0844 | 0.0875 | 23 |
70
+ | 2.0800 | 2.0854 | 0.1375 | 24 |
71
+ | 2.0802 | 2.0890 | 0.1313 | 25 |
72
+ | 2.0788 | 2.0866 | 0.1125 | 26 |
73
+ | 2.0819 | 2.0852 | 0.1125 | 27 |
74
+ | 2.0790 | 2.0896 | 0.1062 | 28 |
75
+ | 2.0824 | 2.0850 | 0.1125 | 29 |
76
+ | 2.0808 | 2.0852 | 0.0813 | 30 |
77
+ | 2.0765 | 2.0840 | 0.125 | 31 |
78
+ | 2.0644 | 2.0726 | 0.1313 | 32 |
79
+ | 2.0571 | 2.0667 | 0.1313 | 33 |
80
+ | 2.0548 | 2.0885 | 0.1125 | 34 |
81
+ | 2.0496 | 2.0551 | 0.1562 | 35 |
82
+ | 2.0595 | 2.0664 | 0.125 | 36 |
83
+ | 2.0494 | 2.0584 | 0.1313 | 37 |
84
+ | 2.0529 | 2.0590 | 0.1375 | 38 |
85
+ | 2.0435 | 2.0654 | 0.1375 | 39 |
86
+ | 2.0465 | 2.1045 | 0.1125 | 40 |
87
+ | 2.0425 | 2.0551 | 0.125 | 41 |
88
+ | 2.0497 | 2.0704 | 0.1187 | 42 |
89
+ | 2.0442 | 2.0816 | 0.1187 | 43 |
90
+ | 2.0433 | 2.0590 | 0.1375 | 44 |
91
+ | 2.0464 | 2.0608 | 0.1313 | 45 |
92
+ | 2.0642 | 2.0706 | 0.1125 | 46 |
93
+ | 2.0511 | 2.0815 | 0.1313 | 47 |
94
+ | 2.0445 | 2.0983 | 0.1187 | 48 |
95
+ | 2.0432 | 2.0673 | 0.1375 | 49 |
96
+
97
+
98
+ ### Framework versions
99
+
100
+ - Transformers 4.29.1
101
+ - TensorFlow 2.12.0
102
+ - Datasets 2.12.0
103
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/vit-base-patch16-224-in21k",
3
+ "architectures": [
4
+ "ViTForImageClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "encoder_stride": 16,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.0,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "anger",
13
+ "1": "contempt",
14
+ "2": "disgust",
15
+ "3": "fear",
16
+ "4": "happy",
17
+ "5": "neutral",
18
+ "6": "sad",
19
+ "7": "surprise"
20
+ },
21
+ "image_size": 224,
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "anger": "0",
26
+ "contempt": "1",
27
+ "disgust": "2",
28
+ "fear": "3",
29
+ "happy": "4",
30
+ "neutral": "5",
31
+ "sad": "6",
32
+ "surprise": "7"
33
+ },
34
+ "layer_norm_eps": 1e-12,
35
+ "model_type": "vit",
36
+ "num_attention_heads": 12,
37
+ "num_channels": 3,
38
+ "num_hidden_layers": 12,
39
+ "patch_size": 16,
40
+ "qkv_bias": true,
41
+ "transformers_version": "4.29.1"
42
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_rescale": true,
4
+ "do_resize": true,
5
+ "image_mean": [
6
+ 0.5,
7
+ 0.5,
8
+ 0.5
9
+ ],
10
+ "image_processor_type": "ViTImageProcessor",
11
+ "image_std": [
12
+ 0.5,
13
+ 0.5,
14
+ 0.5
15
+ ],
16
+ "resample": 2,
17
+ "rescale_factor": 0.00392156862745098,
18
+ "size": {
19
+ "height": 224,
20
+ "width": 224
21
+ }
22
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47dd1dff47aa3833fe7ca300d23ef4f4288ec6dfd6983604adbfeb3cd0dfb547
3
+ size 343504568