Model save
Browse files- README.md +97 -0
- pytorch_model.bin +1 -1
README.md
ADDED
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/deit-tiny-patch16-224
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- imagefolder
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: deit-tiny-patch16-224-finetuned-piid
|
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: val
|
21 |
+
args: default
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.8082191780821918
|
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 |
+
# deit-tiny-patch16-224-finetuned-piid
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on the imagefolder dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.6114
|
36 |
+
- Accuracy: 0.8082
|
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: 5e-05
|
56 |
+
- train_batch_size: 8
|
57 |
+
- eval_batch_size: 8
|
58 |
+
- seed: 42
|
59 |
+
- gradient_accumulation_steps: 4
|
60 |
+
- total_train_batch_size: 32
|
61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
+
- lr_scheduler_type: linear
|
63 |
+
- lr_scheduler_warmup_ratio: 0.1
|
64 |
+
- num_epochs: 20
|
65 |
+
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
70 |
+
| 1.2298 | 0.98 | 20 | 1.1138 | 0.4703 |
|
71 |
+
| 0.7642 | 2.0 | 41 | 0.9123 | 0.5982 |
|
72 |
+
| 0.6167 | 2.98 | 61 | 0.6736 | 0.6849 |
|
73 |
+
| 0.5628 | 4.0 | 82 | 0.6615 | 0.7032 |
|
74 |
+
| 0.5616 | 4.98 | 102 | 0.5985 | 0.7352 |
|
75 |
+
| 0.4742 | 6.0 | 123 | 0.4981 | 0.7854 |
|
76 |
+
| 0.3434 | 6.98 | 143 | 0.5729 | 0.7489 |
|
77 |
+
| 0.3691 | 8.0 | 164 | 0.5779 | 0.7397 |
|
78 |
+
| 0.3375 | 8.98 | 184 | 0.5417 | 0.7580 |
|
79 |
+
| 0.3192 | 10.0 | 205 | 0.5554 | 0.7534 |
|
80 |
+
| 0.2795 | 10.98 | 225 | 0.5656 | 0.7763 |
|
81 |
+
| 0.242 | 12.0 | 246 | 0.5319 | 0.7991 |
|
82 |
+
| 0.2557 | 12.98 | 266 | 0.5154 | 0.8128 |
|
83 |
+
| 0.2465 | 14.0 | 287 | 0.5763 | 0.7991 |
|
84 |
+
| 0.221 | 14.98 | 307 | 0.5683 | 0.8037 |
|
85 |
+
| 0.2058 | 16.0 | 328 | 0.5852 | 0.8128 |
|
86 |
+
| 0.1809 | 16.98 | 348 | 0.6282 | 0.8082 |
|
87 |
+
| 0.1638 | 18.0 | 369 | 0.6289 | 0.7945 |
|
88 |
+
| 0.155 | 18.98 | 389 | 0.6134 | 0.8037 |
|
89 |
+
| 0.2094 | 19.51 | 400 | 0.6114 | 0.8082 |
|
90 |
+
|
91 |
+
|
92 |
+
### Framework versions
|
93 |
+
|
94 |
+
- Transformers 4.33.3
|
95 |
+
- Pytorch 2.0.1+cu118
|
96 |
+
- Datasets 2.14.5
|
97 |
+
- Tokenizers 0.13.3
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 22168173
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64b53c4ed6b3caf8ad2de44180c3903aa929c546a730cb604db52162ce1c1d27
|
3 |
size 22168173
|