Hugging Face's logo

hasnanmr
/
vit-base-oxford-iiit-pets

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Model card Files Metrics Community
hasnanmr commited on
Commit
239dcd9
·
verified ·
1 Parent(s): 2d58d28

cutoutCLAHE

Browse files
Files changed (7) hide show
  1. README.md +84 -0
  2. config.json +34 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +23 -0
  5. runs/Mar01_07-11-34_a31d1e9f3617/events.out.tfevents.1740813097.a31d1e9f3617.1416.0 +3 -0
  6. runs/Mar01_07-11-34_a31d1e9f3617/events.out.tfevents.1740814008.a31d1e9f3617.1416.1 +3 -0
  7. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: google/vit-base-patch16-224
5
+ tags:
6
+ - image-classification
7
+ - generated_from_trainer
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: vit-base-oxford-iiit-pets
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # vit-base-oxford-iiit-pets
19
+
20
+ This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the cepha-cutoutCLAHE dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.6194
23
+ - Accuracy: 0.7639
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 0.0001
43
+ - train_batch_size: 16
44
+ - eval_batch_size: 8
45
+ - seed: 42
46
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
+ - lr_scheduler_type: linear
48
+ - num_epochs: 50
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
+ | 1.0901 | 1.0 | 32 | 0.9278 | 0.4931 |
55
+ | 0.5383 | 2.0 | 64 | 0.6985 | 0.6319 |
56
+ | 0.2707 | 3.0 | 96 | 0.6691 | 0.7222 |
57
+ | 0.0366 | 4.0 | 128 | 0.9557 | 0.6806 |
58
+ | 0.0066 | 5.0 | 160 | 0.8927 | 0.7083 |
59
+ | 0.0075 | 6.0 | 192 | 1.2046 | 0.7014 |
60
+ | 0.0013 | 7.0 | 224 | 1.2583 | 0.7083 |
61
+ | 0.0006 | 8.0 | 256 | 1.3180 | 0.6944 |
62
+ | 0.0004 | 9.0 | 288 | 1.3468 | 0.7014 |
63
+ | 0.0002 | 10.0 | 320 | 1.3582 | 0.6875 |
64
+ | 0.0002 | 11.0 | 352 | 1.3868 | 0.6875 |
65
+ | 0.0002 | 12.0 | 384 | 1.4094 | 0.6806 |
66
+ | 0.0002 | 13.0 | 416 | 1.4392 | 0.6806 |
67
+ | 0.0002 | 14.0 | 448 | 1.4536 | 0.6875 |
68
+ | 0.0001 | 15.0 | 480 | 1.4695 | 0.6875 |
69
+ | 0.0001 | 16.0 | 512 | 1.4850 | 0.6875 |
70
+ | 0.0001 | 17.0 | 544 | 1.5004 | 0.6875 |
71
+ | 0.0001 | 18.0 | 576 | 1.5110 | 0.6875 |
72
+ | 0.0001 | 19.0 | 608 | 1.5219 | 0.6875 |
73
+ | 0.0001 | 20.0 | 640 | 1.5340 | 0.6875 |
74
+ | 0.0001 | 21.0 | 672 | 1.5461 | 0.6875 |
75
+ | 0.0001 | 22.0 | 704 | 1.5541 | 0.6875 |
76
+ | 0.0001 | 23.0 | 736 | 1.5624 | 0.6875 |
77
+
78
+
79
+ ### Framework versions
80
+
81
+ - Transformers 4.48.3
82
+ - Pytorch 2.5.1+cu124
83
+ - Datasets 3.3.2
84
+ - Tokenizers 0.21.0
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2"
15
+ },
16
+ "image_size": 224,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "model_type": "vit",
26
+ "num_attention_heads": 12,
27
+ "num_channels": 3,
28
+ "num_hidden_layers": 12,
29
+ "patch_size": 16,
30
+ "problem_type": "single_label_classification",
31
+ "qkv_bias": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.48.3"
34
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf4c5b7b8455b12802d578120c826f58fe33b966a30e3d68147c70869b1791e4
3
+ size 343227052
preprocessor_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "ViTImageProcessor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "resample": 2,
18
+ "rescale_factor": 0.00392156862745098,
19
+ "size": {
20
+ "height": 224,
21
+ "width": 224
22
+ }
23
+ }
runs/Mar01_07-11-34_a31d1e9f3617/events.out.tfevents.1740813097.a31d1e9f3617.1416.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d4d447964bffb903274d9ebae123a855735fdb4c7e0c030d7b0d4eefb5777ee
3
+ size 20468
runs/Mar01_07-11-34_a31d1e9f3617/events.out.tfevents.1740814008.a31d1e9f3617.1416.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45c9bd027fe3504f2a493a55d0e73425bce05d2c35d581f5d967821882f4981a
3
+ size 411
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b46a07a017523cc983edbdab70879410d283e7091d11aad91980f1e1f2500f1
3
+ size 5368