Hugging Face's logo

aditnnda
/
felidae_klasifikasi_fix

Image Classification
Transformers
TensorFlow
vit
generated_from_keras_callback
Inference Endpoints
Model card Files Community
aditnnda commited on
Commit
5a304cb
•
1 Parent(s): 98d983b

End of training

Browse files
Files changed (4) hide show
  1. README.md +105 -0
  2. config.json +36 -0
  3. preprocessor_config.json +22 -0
  4. tf_model.h5 +3 -0
README.md ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/vit-base-patch16-224-in21k
4
+ tags:
5
+ - generated_from_keras_callback
6
+ model-index:
7
+ - name: aditnnda/felidae_klasifikasi_fix
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information Keras had access to. You should
12
+ probably proofread and complete it, then remove this comment. -->
13
+
14
+ # aditnnda/felidae_klasifikasi_fix
15
+
16
+ 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.
17
+ It achieves the following results on the evaluation set:
18
+ - Train Loss: 0.2941
19
+ - Train Accuracy: 0.9180
20
+ - Validation Loss: 0.2691
21
+ - Validation Accuracy: 0.9180
22
+ - Epoch: 49
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 9100, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
42
+ - training_precision: float32
43
+
44
+ ### Training results
45
+
46
+ | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
47
+ |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
48
+ | 1.5677 | 0.6885 | 1.4799 | 0.6885 | 0 |
49
+ | 1.4926 | 0.9180 | 1.3584 | 0.9180 | 1 |
50
+ | 1.3957 | 0.9016 | 1.2332 | 0.9016 | 2 |
51
+ | 1.3151 | 0.8361 | 1.1098 | 0.8361 | 3 |
52
+ | 1.1756 | 0.8525 | 0.9886 | 0.8525 | 4 |
53
+ | 1.1173 | 0.8852 | 0.8775 | 0.8852 | 5 |
54
+ | 1.0196 | 0.9016 | 0.8042 | 0.9016 | 6 |
55
+ | 0.9451 | 0.9344 | 0.6991 | 0.9344 | 7 |
56
+ | 0.9189 | 0.9508 | 0.6396 | 0.9508 | 8 |
57
+ | 0.8269 | 0.9672 | 0.5717 | 0.9672 | 9 |
58
+ | 0.7581 | 0.9836 | 0.5063 | 0.9836 | 10 |
59
+ | 0.7328 | 0.9672 | 0.4772 | 0.9672 | 11 |
60
+ | 0.6639 | 0.9508 | 0.4691 | 0.9508 | 12 |
61
+ | 0.7082 | 0.9180 | 0.4597 | 0.9180 | 13 |
62
+ | 0.6607 | 0.9672 | 0.4006 | 0.9672 | 14 |
63
+ | 0.7278 | 0.9508 | 0.3966 | 0.9508 | 15 |
64
+ | 0.6285 | 0.9508 | 0.3669 | 0.9508 | 16 |
65
+ | 0.5902 | 0.9836 | 0.3321 | 0.9836 | 17 |
66
+ | 0.5963 | 0.9344 | 0.3899 | 0.9344 | 18 |
67
+ | 0.6273 | 0.9344 | 0.3246 | 0.9344 | 19 |
68
+ | 0.5917 | 0.9016 | 0.4248 | 0.9016 | 20 |
69
+ | 0.5190 | 0.9180 | 0.3575 | 0.9180 | 21 |
70
+ | 0.4991 | 0.9508 | 0.3060 | 0.9508 | 22 |
71
+ | 0.4861 | 0.9344 | 0.3244 | 0.9344 | 23 |
72
+ | 0.4650 | 0.9344 | 0.3014 | 0.9344 | 24 |
73
+ | 0.5044 | 0.9508 | 0.2727 | 0.9508 | 25 |
74
+ | 0.4232 | 0.9672 | 0.2439 | 0.9672 | 26 |
75
+ | 0.4247 | 0.9672 | 0.2233 | 0.9672 | 27 |
76
+ | 0.4732 | 0.9508 | 0.2857 | 0.9508 | 28 |
77
+ | 0.4222 | 1.0 | 0.1937 | 1.0 | 29 |
78
+ | 0.4165 | 0.9836 | 0.1996 | 0.9836 | 30 |
79
+ | 0.3979 | 0.9508 | 0.2074 | 0.9508 | 31 |
80
+ | 0.3691 | 0.9344 | 0.2627 | 0.9344 | 32 |
81
+ | 0.3094 | 0.9344 | 0.2641 | 0.9344 | 33 |
82
+ | 0.3726 | 0.9508 | 0.2224 | 0.9508 | 34 |
83
+ | 0.3503 | 0.9508 | 0.2241 | 0.9508 | 35 |
84
+ | 0.3832 | 0.9344 | 0.2274 | 0.9344 | 36 |
85
+ | 0.3765 | 0.9508 | 0.2421 | 0.9508 | 37 |
86
+ | 0.3927 | 0.9508 | 0.1979 | 0.9508 | 38 |
87
+ | 0.2968 | 0.9672 | 0.1857 | 0.9672 | 39 |
88
+ | 0.3489 | 0.9508 | 0.2158 | 0.9508 | 40 |
89
+ | 0.4102 | 0.9672 | 0.1951 | 0.9672 | 41 |
90
+ | 0.3842 | 0.9672 | 0.1971 | 0.9672 | 42 |
91
+ | 0.3417 | 0.8852 | 0.3686 | 0.8852 | 43 |
92
+ | 0.3219 | 0.9344 | 0.2255 | 0.9344 | 44 |
93
+ | 0.3671 | 0.9672 | 0.1570 | 0.9672 | 45 |
94
+ | 0.3948 | 0.9344 | 0.2217 | 0.9344 | 46 |
95
+ | 0.3201 | 0.9672 | 0.1993 | 0.9672 | 47 |
96
+ | 0.3612 | 0.9508 | 0.1936 | 0.9508 | 48 |
97
+ | 0.2941 | 0.9180 | 0.2691 | 0.9180 | 49 |
98
+
99
+
100
+ ### Framework versions
101
+
102
+ - Transformers 4.35.1
103
+ - TensorFlow 2.14.0
104
+ - Datasets 2.14.6
105
+ - Tokenizers 0.14.1
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "Cheetah",
13
+ "1": "Leopard",
14
+ "2": "Lion",
15
+ "3": "Puma",
16
+ "4": "Tiger"
17
+ },
18
+ "image_size": 224,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "Cheetah": "0",
23
+ "Leopard": "1",
24
+ "Lion": "2",
25
+ "Puma": "3",
26
+ "Tiger": "4"
27
+ },
28
+ "layer_norm_eps": 1e-12,
29
+ "model_type": "vit",
30
+ "num_attention_heads": 12,
31
+ "num_channels": 3,
32
+ "num_hidden_layers": 12,
33
+ "patch_size": 16,
34
+ "qkv_bias": true,
35
+ "transformers_version": "4.35.1"
36
+ }
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:d15156f1f69175c6cc7cad8337520955f7153f228a126c22712be4e85d976dd1
3
+ size 343495352