usamaaleem99tech commited on
Commit
9bc5971
1 Parent(s): 5ccdc3d

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +86 -0
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - imagefolder
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: segformer-class-classWeights-augmentation
11
+ results:
12
+ - task:
13
+ name: Image Classification
14
+ type: image-classification
15
+ dataset:
16
+ name: imagefolder
17
+ type: imagefolder
18
+ config: default
19
+ split: train
20
+ args: default
21
+ metrics:
22
+ - name: Accuracy
23
+ type: accuracy
24
+ value: 0.9545454545454546
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # segformer-class-classWeights-augmentation
31
+
32
+ This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.0927
35
+ - Accuracy: 0.9545
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 5e-05
55
+ - train_batch_size: 10
56
+ - eval_batch_size: 10
57
+ - seed: 42
58
+ - gradient_accumulation_steps: 4
59
+ - total_train_batch_size: 40
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - lr_scheduler_warmup_ratio: 0.1
63
+ - num_epochs: 10
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | No log | 0.96 | 6 | 0.9944 | 0.4773 |
70
+ | 1.0159 | 1.92 | 12 | 0.6948 | 0.75 |
71
+ | 1.0159 | 2.88 | 18 | 0.3417 | 0.9318 |
72
+ | 0.5444 | 4.0 | 25 | 0.2642 | 0.9091 |
73
+ | 0.2331 | 4.96 | 31 | 0.0986 | 0.9545 |
74
+ | 0.2331 | 5.92 | 37 | 0.1735 | 0.9545 |
75
+ | 0.2596 | 6.88 | 43 | 0.1091 | 0.9545 |
76
+ | 0.1737 | 8.0 | 50 | 0.0685 | 0.9545 |
77
+ | 0.1737 | 8.96 | 56 | 0.0995 | 0.9545 |
78
+ | 0.1716 | 9.6 | 60 | 0.0927 | 0.9545 |
79
+
80
+
81
+ ### Framework versions
82
+
83
+ - Transformers 4.30.2
84
+ - Pytorch 2.0.1+cu118
85
+ - Datasets 2.13.1
86
+ - Tokenizers 0.13.3