dhanesh123in
commited on
Commit
•
7172d85
1
Parent(s):
0933d36
Model save
Browse files
README.md
ADDED
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google/vit-base-patch16-224-in21k
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- imagefolder
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: image_classification_obipix_birdID
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Image Classification
|
15 |
+
type: image-classification
|
16 |
+
dataset:
|
17 |
+
name: imagefolder
|
18 |
+
type: imagefolder
|
19 |
+
config: default
|
20 |
+
split: train
|
21 |
+
args: default
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.9719696025912545
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# image_classification_obipix_birdID
|
32 |
+
|
33 |
+
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 imagefolder dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.1150
|
36 |
+
- Accuracy: 0.9720
|
37 |
+
|
38 |
+
## Model description
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Intended uses & limitations
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training and evaluation data
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training procedure
|
51 |
+
|
52 |
+
### Training hyperparameters
|
53 |
+
|
54 |
+
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 0.0002
|
56 |
+
- train_batch_size: 64
|
57 |
+
- eval_batch_size: 16
|
58 |
+
- seed: 42
|
59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
+
- lr_scheduler_type: linear
|
61 |
+
- num_epochs: 5
|
62 |
+
- mixed_precision_training: Native AMP
|
63 |
+
|
64 |
+
### Training results
|
65 |
+
|
66 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
67 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
68 |
+
| 6.9257 | 0.18 | 1000 | 5.3830 | 0.1638 |
|
69 |
+
| 3.9727 | 0.35 | 2000 | 2.7695 | 0.4797 |
|
70 |
+
| 2.057 | 0.53 | 3000 | 1.5070 | 0.6936 |
|
71 |
+
| 1.2103 | 0.7 | 4000 | 0.9727 | 0.7842 |
|
72 |
+
| 0.8513 | 0.88 | 5000 | 0.7101 | 0.8318 |
|
73 |
+
| 0.5836 | 1.06 | 6000 | 0.5797 | 0.8561 |
|
74 |
+
| 0.3545 | 1.23 | 7000 | 0.5066 | 0.8730 |
|
75 |
+
| 0.314 | 1.41 | 8000 | 0.4521 | 0.8818 |
|
76 |
+
| 0.2858 | 1.58 | 9000 | 0.3915 | 0.8960 |
|
77 |
+
| 0.2482 | 1.76 | 10000 | 0.3564 | 0.9056 |
|
78 |
+
| 0.2192 | 1.93 | 11000 | 0.3131 | 0.9148 |
|
79 |
+
| 0.1271 | 2.11 | 12000 | 0.2916 | 0.9207 |
|
80 |
+
| 0.0779 | 2.29 | 13000 | 0.2727 | 0.9260 |
|
81 |
+
| 0.0749 | 2.46 | 14000 | 0.2597 | 0.9309 |
|
82 |
+
| 0.0682 | 2.64 | 15000 | 0.2415 | 0.9355 |
|
83 |
+
| 0.0615 | 2.81 | 16000 | 0.2268 | 0.9385 |
|
84 |
+
| 0.0566 | 2.99 | 17000 | 0.2084 | 0.9440 |
|
85 |
+
| 0.0197 | 3.17 | 18000 | 0.1951 | 0.9475 |
|
86 |
+
| 0.0158 | 3.34 | 19000 | 0.1843 | 0.9513 |
|
87 |
+
| 0.0145 | 3.52 | 20000 | 0.1746 | 0.9541 |
|
88 |
+
| 0.0118 | 3.69 | 21000 | 0.1649 | 0.9573 |
|
89 |
+
| 0.0103 | 3.87 | 22000 | 0.1531 | 0.9599 |
|
90 |
+
| 0.006 | 4.05 | 23000 | 0.1379 | 0.9644 |
|
91 |
+
| 0.0016 | 4.22 | 24000 | 0.1316 | 0.9668 |
|
92 |
+
| 0.0013 | 4.4 | 25000 | 0.1265 | 0.9686 |
|
93 |
+
| 0.0014 | 4.57 | 26000 | 0.1232 | 0.9697 |
|
94 |
+
| 0.0009 | 4.75 | 27000 | 0.1189 | 0.9712 |
|
95 |
+
| 0.001 | 4.92 | 28000 | 0.1150 | 0.9720 |
|
96 |
+
|
97 |
+
|
98 |
+
### Framework versions
|
99 |
+
|
100 |
+
- Transformers 4.38.2
|
101 |
+
- Pytorch 2.2.1+cu121
|
102 |
+
- Datasets 2.18.0
|
103 |
+
- Tokenizers 0.15.0
|
runs/Mar18_12-43-54_user-desktop/events.out.tfevents.1710746066.user-desktop.44603.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d61fc19ff420bc3125ea689dd6a6f02197fe84287a5151cb737f118ae026f63
|
3 |
+
size 218706
|