sergiocannata
commited on
Commit
•
3b26cfd
1
Parent(s):
7db9e88
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: vit-large-patch32-384-finetuned-melanoma
|
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: 0.8272727272727273
|
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 |
+
# vit-large-patch32-384-finetuned-melanoma
|
31 |
+
|
32 |
+
This model is a fine-tuned version of [google/vit-large-patch32-384](https://huggingface.co/google/vit-large-patch32-384) on the imagefolder dataset.
|
33 |
+
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 1.0767
|
35 |
+
- Accuracy: 0.8273
|
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: 1e-05
|
55 |
+
- train_batch_size: 1
|
56 |
+
- eval_batch_size: 1
|
57 |
+
- seed: 42
|
58 |
+
- gradient_accumulation_steps: 4
|
59 |
+
- total_train_batch_size: 4
|
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: 40
|
64 |
+
|
65 |
+
### Training results
|
66 |
+
|
67 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
68 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
69 |
+
| 1.0081 | 1.0 | 550 | 0.7650 | 0.68 |
|
70 |
+
| 0.7527 | 2.0 | 1100 | 0.6693 | 0.7364 |
|
71 |
+
| 0.6234 | 3.0 | 1650 | 0.6127 | 0.7709 |
|
72 |
+
| 2.6284 | 4.0 | 2200 | 0.6788 | 0.7655 |
|
73 |
+
| 0.1406 | 5.0 | 2750 | 0.6657 | 0.7836 |
|
74 |
+
| 0.317 | 6.0 | 3300 | 0.6936 | 0.78 |
|
75 |
+
| 2.5358 | 7.0 | 3850 | 0.7104 | 0.7909 |
|
76 |
+
| 1.5802 | 8.0 | 4400 | 0.6928 | 0.8 |
|
77 |
+
| 0.088 | 9.0 | 4950 | 0.8060 | 0.7982 |
|
78 |
+
| 0.0183 | 10.0 | 5500 | 0.7811 | 0.8091 |
|
79 |
+
| 0.0074 | 11.0 | 6050 | 0.7185 | 0.7945 |
|
80 |
+
| 0.0448 | 12.0 | 6600 | 0.8780 | 0.7909 |
|
81 |
+
| 0.4288 | 13.0 | 7150 | 0.8229 | 0.82 |
|
82 |
+
| 0.017 | 14.0 | 7700 | 0.7516 | 0.8182 |
|
83 |
+
| 0.0057 | 15.0 | 8250 | 0.7974 | 0.7964 |
|
84 |
+
| 1.7571 | 16.0 | 8800 | 0.7866 | 0.8218 |
|
85 |
+
| 1.3159 | 17.0 | 9350 | 0.8491 | 0.8073 |
|
86 |
+
| 1.649 | 18.0 | 9900 | 0.8432 | 0.7891 |
|
87 |
+
| 0.0014 | 19.0 | 10450 | 0.8870 | 0.82 |
|
88 |
+
| 0.002 | 20.0 | 11000 | 0.9460 | 0.8236 |
|
89 |
+
| 0.3717 | 21.0 | 11550 | 0.8866 | 0.8327 |
|
90 |
+
| 0.0025 | 22.0 | 12100 | 1.0287 | 0.8073 |
|
91 |
+
| 0.0094 | 23.0 | 12650 | 0.9696 | 0.8091 |
|
92 |
+
| 0.002 | 24.0 | 13200 | 0.9659 | 0.8018 |
|
93 |
+
| 0.1001 | 25.0 | 13750 | 0.9712 | 0.8327 |
|
94 |
+
| 0.2953 | 26.0 | 14300 | 1.0512 | 0.8236 |
|
95 |
+
| 0.0141 | 27.0 | 14850 | 1.0503 | 0.82 |
|
96 |
+
| 0.612 | 28.0 | 15400 | 1.2020 | 0.8109 |
|
97 |
+
| 0.0792 | 29.0 | 15950 | 1.0498 | 0.8364 |
|
98 |
+
| 0.0117 | 30.0 | 16500 | 1.0079 | 0.8327 |
|
99 |
+
| 0.0568 | 31.0 | 17050 | 1.0199 | 0.8255 |
|
100 |
+
| 0.0001 | 32.0 | 17600 | 1.0319 | 0.8291 |
|
101 |
+
| 0.075 | 33.0 | 18150 | 1.0427 | 0.8382 |
|
102 |
+
| 0.001 | 34.0 | 18700 | 1.1289 | 0.8382 |
|
103 |
+
| 0.0001 | 35.0 | 19250 | 1.0589 | 0.8364 |
|
104 |
+
| 0.0006 | 36.0 | 19800 | 1.0349 | 0.8236 |
|
105 |
+
| 0.0023 | 37.0 | 20350 | 1.1192 | 0.8273 |
|
106 |
+
| 0.0002 | 38.0 | 20900 | 1.0863 | 0.8273 |
|
107 |
+
| 0.2031 | 39.0 | 21450 | 1.0604 | 0.8255 |
|
108 |
+
| 0.0006 | 40.0 | 22000 | 1.0767 | 0.8273 |
|
109 |
+
|
110 |
+
|
111 |
+
### Framework versions
|
112 |
+
|
113 |
+
- Transformers 4.24.0
|
114 |
+
- Pytorch 1.12.1+cu113
|
115 |
+
- Datasets 2.7.0
|
116 |
+
- Tokenizers 0.13.2
|