eslamxm commited on
Commit
51da4b1
1 Parent(s): 3c63b02

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +77 -0
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - image-classification
5
+ - generated_from_trainer
6
+ datasets:
7
+ - food101
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: vit-base-food101-demo-v5
12
+ results:
13
+ - task:
14
+ name: Image Classification
15
+ type: image-classification
16
+ dataset:
17
+ name: food101
18
+ type: food101
19
+ args: default
20
+ metrics:
21
+ - name: Accuracy
22
+ type: accuracy
23
+ value: 0.8558811881188119
24
+ ---
25
+
26
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
27
+ should probably proofread and complete it, then remove this comment. -->
28
+
29
+ # vit-base-food101-demo-v5
30
+
31
+ 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 food101 dataset.
32
+ It achieves the following results on the evaluation set:
33
+ - Loss: 0.5434
34
+ - Accuracy: 0.8559
35
+
36
+ ## Model description
37
+
38
+ More information needed
39
+
40
+ ## Intended uses & limitations
41
+
42
+ More information needed
43
+
44
+ ## Training and evaluation data
45
+
46
+ More information needed
47
+
48
+ ## Training procedure
49
+
50
+ ### Training hyperparameters
51
+
52
+ The following hyperparameters were used during training:
53
+ - learning_rate: 0.0002
54
+ - train_batch_size: 16
55
+ - eval_batch_size: 8
56
+ - seed: 42
57
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
58
+ - lr_scheduler_type: linear
59
+ - num_epochs: 4
60
+ - mixed_precision_training: Native AMP
61
+
62
+ ### Training results
63
+
64
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
66
+ | 1.6283 | 1.0 | 4735 | 0.9875 | 0.7409 |
67
+ | 0.9874 | 2.0 | 9470 | 0.7967 | 0.7894 |
68
+ | 0.7102 | 3.0 | 14205 | 0.6455 | 0.8255 |
69
+ | 0.4917 | 4.0 | 18940 | 0.5502 | 0.8524 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.19.2
75
+ - Pytorch 1.11.0+cu113
76
+ - Datasets 2.2.1
77
+ - Tokenizers 0.12.1