Hugging Face's logo

uisikdag
/
vit-base-patch16-224-oxford-pets-classification

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Model card Files
xet
 Metrics Community
uisikdag commited on
Commit
2afbd91
·
verified ·
1 Parent(s): 1647ae9

Model save

Browse files
Files changed (14) hide show
  1. README.md +64 -0
  2. config.json +102 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +36 -0
  5. runs/May17_08-48-54_umit-ubuntu/events.out.tfevents.1715925001.umit-ubuntu +3 -0
  6. runs/May18_13-17-14_umit-ubuntu/events.out.tfevents.1716027438.umit-ubuntu +3 -0
  7. runs/May18_13-29-30_umit-ubuntu/events.out.tfevents.1716028175.umit-ubuntu +3 -0
  8. runs/May18_13-32-55_umit-ubuntu/events.out.tfevents.1716028376.umit-ubuntu +3 -0
  9. runs/May18_13-34-21_umit-ubuntu/events.out.tfevents.1716028462.umit-ubuntu +3 -0
  10. runs/May18_13-35-20_umit-ubuntu/events.out.tfevents.1716028521.umit-ubuntu +3 -0
  11. runs/May18_13-38-21_umit-ubuntu/events.out.tfevents.1716028702.umit-ubuntu +3 -0
  12. runs/May18_15-05-00_umit-ubuntu/events.out.tfevents.1716033905.umit-ubuntu +3 -0
  13. runs/May18_15-05-00_umit-ubuntu/events.out.tfevents.1716034099.umit-ubuntu +3 -0
  14. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/vit-base-patch16-224
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: vit-base-oxford-iiit-pets
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # vit-base-oxford-iiit-pets
17
+
18
+ This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.1992
21
+ - Accuracy: 0.9350
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.0003
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 5
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | 0.3808 | 1.0 | 370 | 0.2939 | 0.9229 |
53
+ | 0.2337 | 2.0 | 740 | 0.2166 | 0.9432 |
54
+ | 0.1762 | 3.0 | 1110 | 0.2010 | 0.9459 |
55
+ | 0.1414 | 4.0 | 1480 | 0.1922 | 0.9513 |
56
+ | 0.136 | 5.0 | 1850 | 0.1895 | 0.9499 |
57
+
58
+
59
+ ### Framework versions
60
+
61
+ - Transformers 4.41.0.dev0
62
+ - Pytorch 2.1.2+cu121
63
+ - Datasets 2.19.1
64
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/vit-base-patch16-224",
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": "Siamese",
13
+ "1": "Birman",
14
+ "2": "shiba inu",
15
+ "3": "staffordshire bull terrier",
16
+ "4": "basset hound",
17
+ "5": "Bombay",
18
+ "6": "japanese chin",
19
+ "7": "chihuahua",
20
+ "8": "german shorthaired",
21
+ "9": "pomeranian",
22
+ "10": "beagle",
23
+ "11": "english cocker spaniel",
24
+ "12": "american pit bull terrier",
25
+ "13": "Ragdoll",
26
+ "14": "Persian",
27
+ "15": "Egyptian Mau",
28
+ "16": "miniature pinscher",
29
+ "17": "Sphynx",
30
+ "18": "Maine Coon",
31
+ "19": "keeshond",
32
+ "20": "yorkshire terrier",
33
+ "21": "havanese",
34
+ "22": "leonberger",
35
+ "23": "wheaten terrier",
36
+ "24": "american bulldog",
37
+ "25": "english setter",
38
+ "26": "boxer",
39
+ "27": "newfoundland",
40
+ "28": "Bengal",
41
+ "29": "samoyed",
42
+ "30": "British Shorthair",
43
+ "31": "great pyrenees",
44
+ "32": "Abyssinian",
45
+ "33": "pug",
46
+ "34": "saint bernard",
47
+ "35": "Russian Blue",
48
+ "36": "scottish terrier"
49
+ },
50
+ "image_size": 224,
51
+ "initializer_range": 0.02,
52
+ "intermediate_size": 3072,
53
+ "label2id": {
54
+ "Abyssinian": 32,
55
+ "Bengal": 28,
56
+ "Birman": 1,
57
+ "Bombay": 5,
58
+ "British Shorthair": 30,
59
+ "Egyptian Mau": 15,
60
+ "Maine Coon": 18,
61
+ "Persian": 14,
62
+ "Ragdoll": 13,
63
+ "Russian Blue": 35,
64
+ "Siamese": 0,
65
+ "Sphynx": 17,
66
+ "american bulldog": 24,
67
+ "american pit bull terrier": 12,
68
+ "basset hound": 4,
69
+ "beagle": 10,
70
+ "boxer": 26,
71
+ "chihuahua": 7,
72
+ "english cocker spaniel": 11,
73
+ "english setter": 25,
74
+ "german shorthaired": 8,
75
+ "great pyrenees": 31,
76
+ "havanese": 21,
77
+ "japanese chin": 6,
78
+ "keeshond": 19,
79
+ "leonberger": 22,
80
+ "miniature pinscher": 16,
81
+ "newfoundland": 27,
82
+ "pomeranian": 9,
83
+ "pug": 33,
84
+ "saint bernard": 34,
85
+ "samoyed": 29,
86
+ "scottish terrier": 36,
87
+ "shiba inu": 2,
88
+ "staffordshire bull terrier": 3,
89
+ "wheaten terrier": 23,
90
+ "yorkshire terrier": 20
91
+ },
92
+ "layer_norm_eps": 1e-12,
93
+ "model_type": "vit",
94
+ "num_attention_heads": 12,
95
+ "num_channels": 3,
96
+ "num_hidden_layers": 12,
97
+ "patch_size": 16,
98
+ "problem_type": "single_label_classification",
99
+ "qkv_bias": true,
100
+ "torch_dtype": "float32",
101
+ "transformers_version": "4.41.0.dev0"
102
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba0905fdb77a3ed3d7656df9a7d03edd7cd724f43aadae06594073f5b0ef712c
3
+ size 343331644
preprocessor_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_processor_keys": [
3
+ "images",
4
+ "do_resize",
5
+ "size",
6
+ "resample",
7
+ "do_rescale",
8
+ "rescale_factor",
9
+ "do_normalize",
10
+ "image_mean",
11
+ "image_std",
12
+ "return_tensors",
13
+ "data_format",
14
+ "input_data_format"
15
+ ],
16
+ "do_normalize": true,
17
+ "do_rescale": true,
18
+ "do_resize": true,
19
+ "image_mean": [
20
+ 0.5,
21
+ 0.5,
22
+ 0.5
23
+ ],
24
+ "image_processor_type": "ViTImageProcessor",
25
+ "image_std": [
26
+ 0.5,
27
+ 0.5,
28
+ 0.5
29
+ ],
30
+ "resample": 2,
31
+ "rescale_factor": 0.00392156862745098,
32
+ "size": {
33
+ "height": 224,
34
+ "width": 224
35
+ }
36
+ }
runs/May17_08-48-54_umit-ubuntu/events.out.tfevents.1715925001.umit-ubuntu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffdf59074ff83e10157afc00d4eb34780dd4fc85f023aee7673cc233def3b04f
3
+ size 13016
runs/May18_13-17-14_umit-ubuntu/events.out.tfevents.1716027438.umit-ubuntu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d505f0926e4bba5a5731f505ce863c5b68ba280f84bd5f776dcd35fceaf0dfa3
3
+ size 6528
runs/May18_13-29-30_umit-ubuntu/events.out.tfevents.1716028175.umit-ubuntu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cc79717bcd31c6adc04c51cfbdefaafa0e88bbee71b63ecb267c2b6017b2abc
3
+ size 6528
runs/May18_13-32-55_umit-ubuntu/events.out.tfevents.1716028376.umit-ubuntu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b14fa7d9f4e682be13925db972a38f85dc45667cec67f678c8de0ab86c33c7f6
3
+ size 6528
runs/May18_13-34-21_umit-ubuntu/events.out.tfevents.1716028462.umit-ubuntu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8ab04c515af494f2d6b5b04a1fe3c49b76225783bf759ab7700912dd8d795d9
3
+ size 6528
runs/May18_13-35-20_umit-ubuntu/events.out.tfevents.1716028521.umit-ubuntu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7fc3aee8eca52d8407ea07007e2bf8611e07619e71820828149cf373b32c5c3
3
+ size 6528
runs/May18_13-38-21_umit-ubuntu/events.out.tfevents.1716028702.umit-ubuntu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17f000bc7dce3c2001273c2e5907e304b513723d4f88199704509ea91972d84e
3
+ size 6528
runs/May18_15-05-00_umit-ubuntu/events.out.tfevents.1716033905.umit-ubuntu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18c6d86adde82da12fbbc1cfcfddb5d32d8dcd215761dc14e8bf3bb1b604274b
3
+ size 12291
runs/May18_15-05-00_umit-ubuntu/events.out.tfevents.1716034099.umit-ubuntu ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea0f974e649eca8fd9ec3476d27dfff96d09d93ad0737efda7d0e441820dbdbf
3
+ size 40
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b2e4420c51fa75bf230317e358106c6969fb1bbe7b23284c33f325456edead0
3
+ size 5112