Hugging Face's logo

Netnoy17
/
Chess_Images

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Netnoy17 commited on
Commit
9c52212
•
1 Parent(s): bba7636

End of training

Browse files
Files changed (6) hide show
  1. README.md +127 -0
  2. config.json +40 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +22 -0
  5. runs/Apr04_16-43-59_9661203133a4/events.out.tfevents.1712249040.9661203133a4.161.0 +3 -0
  6. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/vit-base-patch16-224-in21k
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: Chess_Images
12
+ results:
13
+ - task:
14
+ name: Image Classification
15
+ type: image-classification
16
+ dataset:
17
+ name: imagefolder
18
+ type: imagefolder
19
+ config: default
20
+ split: train
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.9666666666666667
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # Chess_Images
32
+
33
+ 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.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.3882
36
+ - Accuracy: 0.9667
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 5e-05
56
+ - train_batch_size: 16
57
+ - eval_batch_size: 16
58
+ - seed: 42
59
+ - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 64
61
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
+ - lr_scheduler_type: linear
63
+ - lr_scheduler_warmup_ratio: 0.1
64
+ - num_epochs: 50
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 1.0 | 2 | 1.7939 | 0.2 |
71
+ | No log | 2.0 | 4 | 1.7836 | 0.1333 |
72
+ | No log | 3.0 | 6 | 1.7646 | 0.0667 |
73
+ | No log | 4.0 | 8 | 1.6917 | 0.1333 |
74
+ | 1.7382 | 5.0 | 10 | 1.6700 | 0.3333 |
75
+ | 1.7382 | 6.0 | 12 | 1.5990 | 0.5 |
76
+ | 1.7382 | 7.0 | 14 | 1.5424 | 0.4667 |
77
+ | 1.7382 | 8.0 | 16 | 1.4673 | 0.6 |
78
+ | 1.7382 | 9.0 | 18 | 1.4155 | 0.7333 |
79
+ | 1.3754 | 10.0 | 20 | 1.3015 | 0.7 |
80
+ | 1.3754 | 11.0 | 22 | 1.3055 | 0.6667 |
81
+ | 1.3754 | 12.0 | 24 | 1.2209 | 0.7 |
82
+ | 1.3754 | 13.0 | 26 | 1.0965 | 0.8 |
83
+ | 1.3754 | 14.0 | 28 | 1.0976 | 0.7667 |
84
+ | 0.9947 | 15.0 | 30 | 1.0388 | 0.8667 |
85
+ | 0.9947 | 16.0 | 32 | 1.0757 | 0.7 |
86
+ | 0.9947 | 17.0 | 34 | 0.9617 | 0.8 |
87
+ | 0.9947 | 18.0 | 36 | 0.8713 | 0.8667 |
88
+ | 0.9947 | 19.0 | 38 | 0.8803 | 0.8667 |
89
+ | 0.7399 | 20.0 | 40 | 0.8257 | 0.8667 |
90
+ | 0.7399 | 21.0 | 42 | 0.8740 | 0.8333 |
91
+ | 0.7399 | 22.0 | 44 | 0.7554 | 0.9667 |
92
+ | 0.7399 | 23.0 | 46 | 0.7581 | 0.8667 |
93
+ | 0.7399 | 24.0 | 48 | 0.7983 | 0.8333 |
94
+ | 0.5797 | 25.0 | 50 | 0.7052 | 0.9333 |
95
+ | 0.5797 | 26.0 | 52 | 0.7930 | 0.8667 |
96
+ | 0.5797 | 27.0 | 54 | 0.7511 | 0.8333 |
97
+ | 0.5797 | 28.0 | 56 | 0.5578 | 0.9667 |
98
+ | 0.5797 | 29.0 | 58 | 0.5771 | 0.9667 |
99
+ | 0.4642 | 30.0 | 60 | 0.5641 | 0.9667 |
100
+ | 0.4642 | 31.0 | 62 | 0.5368 | 0.9667 |
101
+ | 0.4642 | 32.0 | 64 | 0.5313 | 0.9333 |
102
+ | 0.4642 | 33.0 | 66 | 0.5521 | 0.9 |
103
+ | 0.4642 | 34.0 | 68 | 0.5530 | 0.9333 |
104
+ | 0.3813 | 35.0 | 70 | 0.5416 | 0.9 |
105
+ | 0.3813 | 36.0 | 72 | 0.4796 | 0.9 |
106
+ | 0.3813 | 37.0 | 74 | 0.4627 | 0.9667 |
107
+ | 0.3813 | 38.0 | 76 | 0.4788 | 0.9667 |
108
+ | 0.3813 | 39.0 | 78 | 0.5044 | 0.9 |
109
+ | 0.3555 | 40.0 | 80 | 0.5886 | 0.8667 |
110
+ | 0.3555 | 41.0 | 82 | 0.4892 | 0.9 |
111
+ | 0.3555 | 42.0 | 84 | 0.5306 | 0.8333 |
112
+ | 0.3555 | 43.0 | 86 | 0.5294 | 0.8333 |
113
+ | 0.3555 | 44.0 | 88 | 0.5260 | 0.8667 |
114
+ | 0.3441 | 45.0 | 90 | 0.4445 | 0.9667 |
115
+ | 0.3441 | 46.0 | 92 | 0.4579 | 0.9 |
116
+ | 0.3441 | 47.0 | 94 | 0.4390 | 0.9333 |
117
+ | 0.3441 | 48.0 | 96 | 0.4139 | 0.9667 |
118
+ | 0.3441 | 49.0 | 98 | 0.4820 | 0.9667 |
119
+ | 0.3155 | 50.0 | 100 | 0.3882 | 0.9667 |
120
+
121
+
122
+ ### Framework versions
123
+
124
+ - Transformers 4.38.2
125
+ - Pytorch 2.2.1+cu121
126
+ - Datasets 2.18.0
127
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "Black king",
13
+ "1": "Black knight",
14
+ "2": "Black queen",
15
+ "3": "White king",
16
+ "4": "White knight",
17
+ "5": "White queen"
18
+ },
19
+ "image_size": 224,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "Black king": "0",
24
+ "Black knight": "1",
25
+ "Black queen": "2",
26
+ "White king": "3",
27
+ "White knight": "4",
28
+ "White queen": "5"
29
+ },
30
+ "layer_norm_eps": 1e-12,
31
+ "model_type": "vit",
32
+ "num_attention_heads": 12,
33
+ "num_channels": 3,
34
+ "num_hidden_layers": 12,
35
+ "patch_size": 16,
36
+ "problem_type": "single_label_classification",
37
+ "qkv_bias": true,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.38.2"
40
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5707881086dd888b634f50070c2fcceae507926135b7b812e02d476ba8b9924c
3
+ size 343236280
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
+ }
runs/Apr04_16-43-59_9661203133a4/events.out.tfevents.1712249040.9661203133a4.161.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69f6cac504aafb64c61a3d2427a134964da119726bd3c2f2c416cc5bf04ab181
3
+ size 23030
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e948f170379585625c6489fddfde5049016a7f7c8726763701243de816466c8d
3
+ size 4920