update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- imagefolder
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
+
- f1
|
12 |
+
model-index:
|
13 |
+
- name: finetuned-affecthq
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
name: Image Classification
|
17 |
+
type: image-classification
|
18 |
+
dataset:
|
19 |
+
name: imagefolder
|
20 |
+
type: imagefolder
|
21 |
+
config: default
|
22 |
+
split: train
|
23 |
+
args: default
|
24 |
+
metrics:
|
25 |
+
- name: Accuracy
|
26 |
+
type: accuracy
|
27 |
+
value: 0.7179302910528207
|
28 |
+
- name: Precision
|
29 |
+
type: precision
|
30 |
+
value: 0.7173911115103917
|
31 |
+
- name: Recall
|
32 |
+
type: recall
|
33 |
+
value: 0.7179302910528207
|
34 |
+
- name: F1
|
35 |
+
type: f1
|
36 |
+
value: 0.7166821507529032
|
37 |
+
---
|
38 |
+
|
39 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
40 |
+
should probably proofread and complete it, then remove this comment. -->
|
41 |
+
|
42 |
+
# finetuned-affecthq
|
43 |
+
|
44 |
+
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.
|
45 |
+
It achieves the following results on the evaluation set:
|
46 |
+
- Loss: 0.8116
|
47 |
+
- Accuracy: 0.7179
|
48 |
+
- Precision: 0.7174
|
49 |
+
- Recall: 0.7179
|
50 |
+
- F1: 0.7167
|
51 |
+
|
52 |
+
## Model description
|
53 |
+
|
54 |
+
More information needed
|
55 |
+
|
56 |
+
## Intended uses & limitations
|
57 |
+
|
58 |
+
More information needed
|
59 |
+
|
60 |
+
## Training and evaluation data
|
61 |
+
|
62 |
+
More information needed
|
63 |
+
|
64 |
+
## Training procedure
|
65 |
+
|
66 |
+
### Training hyperparameters
|
67 |
+
|
68 |
+
The following hyperparameters were used during training:
|
69 |
+
- learning_rate: 1e-05
|
70 |
+
- train_batch_size: 32
|
71 |
+
- eval_batch_size: 32
|
72 |
+
- seed: 17
|
73 |
+
- gradient_accumulation_steps: 4
|
74 |
+
- total_train_batch_size: 128
|
75 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
76 |
+
- lr_scheduler_type: linear
|
77 |
+
- lr_scheduler_warmup_ratio: 0.1
|
78 |
+
- num_epochs: 10
|
79 |
+
|
80 |
+
### Training results
|
81 |
+
|
82 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|
83 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
|
84 |
+
| 1.5413 | 1.0 | 174 | 1.4810 | 0.4898 | 0.4867 | 0.4898 | 0.4409 |
|
85 |
+
| 1.0367 | 2.0 | 348 | 1.0571 | 0.6155 | 0.6172 | 0.6155 | 0.6041 |
|
86 |
+
| 0.9534 | 3.0 | 522 | 0.9673 | 0.6475 | 0.6476 | 0.6475 | 0.6375 |
|
87 |
+
| 0.8532 | 4.0 | 696 | 0.9056 | 0.6748 | 0.6710 | 0.6748 | 0.6704 |
|
88 |
+
| 0.8211 | 5.0 | 870 | 0.8707 | 0.6903 | 0.6912 | 0.6903 | 0.6836 |
|
89 |
+
| 0.7797 | 6.0 | 1044 | 0.8472 | 0.7050 | 0.7050 | 0.7050 | 0.7019 |
|
90 |
+
| 0.7816 | 7.0 | 1218 | 0.8298 | 0.7111 | 0.7099 | 0.7111 | 0.7096 |
|
91 |
+
| 0.7135 | 8.0 | 1392 | 0.8186 | 0.7111 | 0.7116 | 0.7111 | 0.7105 |
|
92 |
+
| 0.6697 | 9.0 | 1566 | 0.8143 | 0.7140 | 0.7124 | 0.7140 | 0.7126 |
|
93 |
+
| 0.6765 | 10.0 | 1740 | 0.8116 | 0.7179 | 0.7174 | 0.7179 | 0.7167 |
|
94 |
+
|
95 |
+
|
96 |
+
### Framework versions
|
97 |
+
|
98 |
+
- Transformers 4.27.0.dev0
|
99 |
+
- Pytorch 1.13.1+cu116
|
100 |
+
- Datasets 2.9.0
|
101 |
+
- Tokenizers 0.13.2
|