Commit
•
4ec1261
1
Parent(s):
fbea6b5
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: finetuned-ConvNext-Indian-food
|
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: 0.9309245483528161
|
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 |
+
# finetuned-ConvNext-Indian-food
|
31 |
+
|
32 |
+
This model is a fine-tuned version of [facebook/convnext-tiny-224](https://huggingface.co/facebook/convnext-tiny-224) on the imagefolder dataset.
|
33 |
+
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.3046
|
35 |
+
- Accuracy: 0.9309
|
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: 0.0002
|
55 |
+
- train_batch_size: 16
|
56 |
+
- eval_batch_size: 8
|
57 |
+
- seed: 42
|
58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
+
- lr_scheduler_type: linear
|
60 |
+
- num_epochs: 10
|
61 |
+
- mixed_precision_training: Native AMP
|
62 |
+
|
63 |
+
### Training results
|
64 |
+
|
65 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
66 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
67 |
+
| 1.3145 | 0.3 | 100 | 1.0460 | 0.8151 |
|
68 |
+
| 0.6694 | 0.6 | 200 | 0.5439 | 0.8757 |
|
69 |
+
| 0.5057 | 0.9 | 300 | 0.4398 | 0.8831 |
|
70 |
+
| 0.4381 | 1.2 | 400 | 0.4286 | 0.8820 |
|
71 |
+
| 0.4376 | 1.5 | 500 | 0.3400 | 0.9044 |
|
72 |
+
| 0.2499 | 1.8 | 600 | 0.3312 | 0.9065 |
|
73 |
+
| 0.2802 | 2.1 | 700 | 0.3338 | 0.9033 |
|
74 |
+
| 0.3014 | 2.4 | 800 | 0.3572 | 0.8948 |
|
75 |
+
| 0.2508 | 2.7 | 900 | 0.3432 | 0.9022 |
|
76 |
+
| 0.2012 | 3.0 | 1000 | 0.3060 | 0.9086 |
|
77 |
+
| 0.2634 | 3.3 | 1100 | 0.3451 | 0.9086 |
|
78 |
+
| 0.2483 | 3.6 | 1200 | 0.3550 | 0.9044 |
|
79 |
+
| 0.2273 | 3.9 | 1300 | 0.2977 | 0.9107 |
|
80 |
+
| 0.1214 | 4.2 | 1400 | 0.3265 | 0.9160 |
|
81 |
+
| 0.2048 | 4.5 | 1500 | 0.3126 | 0.9214 |
|
82 |
+
| 0.0997 | 4.8 | 1600 | 0.3164 | 0.9160 |
|
83 |
+
| 0.1145 | 5.11 | 1700 | 0.3055 | 0.9139 |
|
84 |
+
| 0.1578 | 5.41 | 1800 | 0.3195 | 0.9171 |
|
85 |
+
| 0.0615 | 5.71 | 1900 | 0.3401 | 0.9107 |
|
86 |
+
| 0.1537 | 6.01 | 2000 | 0.3428 | 0.9097 |
|
87 |
+
| 0.1278 | 6.31 | 2100 | 0.3058 | 0.9192 |
|
88 |
+
| 0.1274 | 6.61 | 2200 | 0.3189 | 0.9192 |
|
89 |
+
| 0.0877 | 6.91 | 2300 | 0.3370 | 0.9182 |
|
90 |
+
| 0.1058 | 7.21 | 2400 | 0.3225 | 0.9192 |
|
91 |
+
| 0.1742 | 7.51 | 2500 | 0.3341 | 0.9214 |
|
92 |
+
| 0.0949 | 7.81 | 2600 | 0.3126 | 0.9256 |
|
93 |
+
| 0.1732 | 8.11 | 2700 | 0.3078 | 0.9235 |
|
94 |
+
| 0.0894 | 8.41 | 2800 | 0.3098 | 0.9267 |
|
95 |
+
| 0.1257 | 8.71 | 2900 | 0.3030 | 0.9320 |
|
96 |
+
| 0.1747 | 9.01 | 3000 | 0.3106 | 0.9256 |
|
97 |
+
| 0.2119 | 9.31 | 3100 | 0.3037 | 0.9299 |
|
98 |
+
| 0.1074 | 9.61 | 3200 | 0.3049 | 0.9277 |
|
99 |
+
| 0.1275 | 9.91 | 3300 | 0.3046 | 0.9309 |
|
100 |
+
|
101 |
+
|
102 |
+
### Framework versions
|
103 |
+
|
104 |
+
- Transformers 4.22.2
|
105 |
+
- Pytorch 1.12.1+cu113
|
106 |
+
- Datasets 2.5.1
|
107 |
+
- Tokenizers 0.12.1
|