Commit
•
f9c5d00
1
Parent(s):
4529342
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: swinv2-tiny-patch4-window8-256-finetuned_swinv2tiny-autotags-256
|
| 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: 0.965482233502538
|
| 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 |
+
# swinv2-tiny-patch4-window8-256-finetuned_swinv2tiny-autotags-256
|
| 31 |
+
|
| 32 |
+
This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
|
| 33 |
+
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 0.1115
|
| 35 |
+
- Accuracy: 0.9655
|
| 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: 5e-05
|
| 55 |
+
- train_batch_size: 16
|
| 56 |
+
- eval_batch_size: 16
|
| 57 |
+
- seed: 42
|
| 58 |
+
- gradient_accumulation_steps: 4
|
| 59 |
+
- total_train_batch_size: 64
|
| 60 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 61 |
+
- lr_scheduler_type: linear
|
| 62 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 63 |
+
- num_epochs: 15
|
| 64 |
+
|
| 65 |
+
### Training results
|
| 66 |
+
|
| 67 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 68 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 69 |
+
| 1.6169 | 0.99 | 61 | 1.1018 | 0.6701 |
|
| 70 |
+
| 0.7747 | 1.99 | 122 | 0.4571 | 0.8670 |
|
| 71 |
+
| 0.6088 | 2.99 | 183 | 0.3002 | 0.9198 |
|
| 72 |
+
| 0.3908 | 3.99 | 244 | 0.2334 | 0.9299 |
|
| 73 |
+
| 0.399 | 4.99 | 305 | 0.2138 | 0.9320 |
|
| 74 |
+
| 0.2969 | 5.99 | 366 | 0.1650 | 0.9492 |
|
| 75 |
+
| 0.2743 | 6.99 | 427 | 0.1514 | 0.9533 |
|
| 76 |
+
| 0.2947 | 7.99 | 488 | 0.1428 | 0.9513 |
|
| 77 |
+
| 0.2304 | 8.99 | 549 | 0.1541 | 0.9523 |
|
| 78 |
+
| 0.1957 | 9.99 | 610 | 0.1256 | 0.9604 |
|
| 79 |
+
| 0.1645 | 10.99 | 671 | 0.1138 | 0.9645 |
|
| 80 |
+
| 0.2317 | 11.99 | 732 | 0.1140 | 0.9655 |
|
| 81 |
+
| 0.1001 | 12.99 | 793 | 0.1068 | 0.9706 |
|
| 82 |
+
| 0.1564 | 13.99 | 854 | 0.1119 | 0.9675 |
|
| 83 |
+
| 0.1386 | 14.99 | 915 | 0.1115 | 0.9655 |
|
| 84 |
+
|
| 85 |
+
|
| 86 |
+
### Framework versions
|
| 87 |
+
|
| 88 |
+
- Transformers 4.25.1
|
| 89 |
+
- Pytorch 1.10.2+cu113
|
| 90 |
+
- Datasets 2.10.1
|
| 91 |
+
- Tokenizers 0.13.2
|