paul
commited on
Commit
•
5c234a3
1
Parent(s):
56b615b
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: swin-base-patch4-window7-224-in22k-finetuned-memes
|
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: 0.8562596599690881
|
28 |
+
- name: Precision
|
29 |
+
type: precision
|
30 |
+
value: 0.8545652818321074
|
31 |
+
- name: Recall
|
32 |
+
type: recall
|
33 |
+
value: 0.8562596599690881
|
34 |
+
- name: F1
|
35 |
+
type: f1
|
36 |
+
value: 0.8552274649509984
|
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 |
+
# swin-base-patch4-window7-224-in22k-finetuned-memes
|
43 |
+
|
44 |
+
This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224-in22k](https://huggingface.co/microsoft/swin-base-patch4-window7-224-in22k) on the imagefolder dataset.
|
45 |
+
It achieves the following results on the evaluation set:
|
46 |
+
- Loss: 0.7094
|
47 |
+
- Accuracy: 0.8563
|
48 |
+
- Precision: 0.8546
|
49 |
+
- Recall: 0.8563
|
50 |
+
- F1: 0.8552
|
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: 0.00012
|
70 |
+
- train_batch_size: 64
|
71 |
+
- eval_batch_size: 64
|
72 |
+
- seed: 42
|
73 |
+
- gradient_accumulation_steps: 4
|
74 |
+
- total_train_batch_size: 256
|
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: 20
|
79 |
+
|
80 |
+
### Training results
|
81 |
+
|
82 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|
83 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
|
84 |
+
| 1.1655 | 0.99 | 20 | 0.8573 | 0.6955 | 0.6953 | 0.6955 | 0.6683 |
|
85 |
+
| 0.5506 | 1.99 | 40 | 0.5327 | 0.8083 | 0.8050 | 0.8083 | 0.7963 |
|
86 |
+
| 0.3573 | 2.99 | 60 | 0.4497 | 0.8338 | 0.8339 | 0.8338 | 0.8317 |
|
87 |
+
| 0.2083 | 3.99 | 80 | 0.4561 | 0.8354 | 0.8450 | 0.8354 | 0.8368 |
|
88 |
+
| 0.1545 | 4.99 | 100 | 0.4605 | 0.8423 | 0.8458 | 0.8423 | 0.8430 |
|
89 |
+
| 0.1014 | 5.99 | 120 | 0.4924 | 0.8524 | 0.8571 | 0.8524 | 0.8538 |
|
90 |
+
| 0.0854 | 6.99 | 140 | 0.5759 | 0.8393 | 0.8452 | 0.8393 | 0.8400 |
|
91 |
+
| 0.1012 | 7.99 | 160 | 0.5142 | 0.8362 | 0.8378 | 0.8362 | 0.8361 |
|
92 |
+
| 0.077 | 8.99 | 180 | 0.5647 | 0.8331 | 0.8538 | 0.8331 | 0.8407 |
|
93 |
+
| 0.0667 | 9.99 | 200 | 0.5294 | 0.8462 | 0.8509 | 0.8462 | 0.8483 |
|
94 |
+
| 0.0666 | 10.99 | 220 | 0.6038 | 0.8385 | 0.8415 | 0.8385 | 0.8396 |
|
95 |
+
| 0.0574 | 11.99 | 240 | 0.6384 | 0.8408 | 0.8431 | 0.8408 | 0.8411 |
|
96 |
+
| 0.0488 | 12.99 | 260 | 0.6305 | 0.8516 | 0.8561 | 0.8516 | 0.8532 |
|
97 |
+
| 0.0524 | 13.99 | 280 | 0.6411 | 0.8509 | 0.8526 | 0.8509 | 0.8510 |
|
98 |
+
| 0.0511 | 14.99 | 300 | 0.6462 | 0.8547 | 0.8542 | 0.8547 | 0.8543 |
|
99 |
+
| 0.0495 | 15.99 | 320 | 0.6869 | 0.8532 | 0.8534 | 0.8532 | 0.8527 |
|
100 |
+
| 0.0412 | 16.99 | 340 | 0.6643 | 0.8578 | 0.8554 | 0.8578 | 0.8564 |
|
101 |
+
| 0.0411 | 17.99 | 360 | 0.7214 | 0.8570 | 0.8539 | 0.8570 | 0.8552 |
|
102 |
+
| 0.0434 | 18.99 | 380 | 0.7037 | 0.8524 | 0.8507 | 0.8524 | 0.8514 |
|
103 |
+
| 0.0394 | 19.99 | 400 | 0.7094 | 0.8563 | 0.8546 | 0.8563 | 0.8552 |
|
104 |
+
|
105 |
+
|
106 |
+
### Framework versions
|
107 |
+
|
108 |
+
- Transformers 4.24.0.dev0
|
109 |
+
- Pytorch 1.11.0+cu102
|
110 |
+
- Datasets 2.6.1.dev0
|
111 |
+
- Tokenizers 0.13.1
|