Commit
•
7692d15
1
Parent(s):
e4d9d4a
Model save
Browse files
README.md
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/convnextv2-nano-22k-384
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- imagefolder
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: convnext-nano-3e-4-augment
|
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: validation
|
21 |
+
args: default
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.9248508946322067
|
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 |
+
# convnext-nano-3e-4-augment
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [facebook/convnextv2-nano-22k-384](https://huggingface.co/facebook/convnextv2-nano-22k-384) on the imagefolder dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.2948
|
36 |
+
- Accuracy: 0.9249
|
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: 0.0003
|
56 |
+
- train_batch_size: 64
|
57 |
+
- eval_batch_size: 64
|
58 |
+
- seed: 42
|
59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
+
- lr_scheduler_type: cosine
|
61 |
+
- num_epochs: 10
|
62 |
+
|
63 |
+
### Training results
|
64 |
+
|
65 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
66 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
67 |
+
| 0.8119 | 1.0 | 275 | 0.5637 | 0.8270 |
|
68 |
+
| 0.5829 | 2.0 | 550 | 0.5016 | 0.8497 |
|
69 |
+
| 0.4623 | 3.0 | 825 | 0.4494 | 0.8755 |
|
70 |
+
| 0.359 | 4.0 | 1100 | 0.3809 | 0.8887 |
|
71 |
+
| 0.2881 | 5.0 | 1375 | 0.3742 | 0.8998 |
|
72 |
+
| 0.2302 | 6.0 | 1650 | 0.3402 | 0.9113 |
|
73 |
+
| 0.1827 | 7.0 | 1925 | 0.3150 | 0.9121 |
|
74 |
+
| 0.1466 | 8.0 | 2200 | 0.3012 | 0.9229 |
|
75 |
+
| 0.1223 | 9.0 | 2475 | 0.2996 | 0.9249 |
|
76 |
+
| 0.1332 | 10.0 | 2750 | 0.2948 | 0.9249 |
|
77 |
+
|
78 |
+
|
79 |
+
### Framework versions
|
80 |
+
|
81 |
+
- Transformers 4.39.3
|
82 |
+
- Pytorch 2.1.2
|
83 |
+
- Datasets 2.18.0
|
84 |
+
- Tokenizers 0.15.2
|