Mazen Amria
commited on
Commit
·
317fdb7
1
Parent(s):
b95932e
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- cifar100
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: swin-small-finetuned-cifar100
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Image Classification
|
| 14 |
+
type: image-classification
|
| 15 |
+
dataset:
|
| 16 |
+
name: cifar100
|
| 17 |
+
type: cifar100
|
| 18 |
+
args: cifar100
|
| 19 |
+
metrics:
|
| 20 |
+
- name: Accuracy
|
| 21 |
+
type: accuracy
|
| 22 |
+
value: 0.8938
|
| 23 |
+
---
|
| 24 |
+
|
| 25 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 26 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 27 |
+
|
| 28 |
+
# swin-small-finetuned-cifar100
|
| 29 |
+
|
| 30 |
+
This model is a fine-tuned version of [microsoft/swin-small-patch4-window7-224](https://huggingface.co/microsoft/swin-small-patch4-window7-224) on the cifar100 dataset.
|
| 31 |
+
It achieves the following results on the evaluation set:
|
| 32 |
+
- Loss: 0.6281
|
| 33 |
+
- Accuracy: 0.8938
|
| 34 |
+
|
| 35 |
+
## Model description
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Intended uses & limitations
|
| 40 |
+
|
| 41 |
+
More information needed
|
| 42 |
+
|
| 43 |
+
## Training and evaluation data
|
| 44 |
+
|
| 45 |
+
More information needed
|
| 46 |
+
|
| 47 |
+
## Training procedure
|
| 48 |
+
|
| 49 |
+
### Training hyperparameters
|
| 50 |
+
|
| 51 |
+
The following hyperparameters were used during training:
|
| 52 |
+
- learning_rate: 4e-05
|
| 53 |
+
- train_batch_size: 16
|
| 54 |
+
- eval_batch_size: 16
|
| 55 |
+
- seed: 42
|
| 56 |
+
- gradient_accumulation_steps: 4
|
| 57 |
+
- total_train_batch_size: 64
|
| 58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 59 |
+
- lr_scheduler_type: linear
|
| 60 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 61 |
+
- num_epochs: 20
|
| 62 |
+
|
| 63 |
+
### Training results
|
| 64 |
+
|
| 65 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 66 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 67 |
+
| 0.72 | 1.0 | 781 | 0.6691 | 0.8077 |
|
| 68 |
+
| 0.6944 | 2.0 | 1562 | 0.4797 | 0.8495 |
|
| 69 |
+
| 0.2794 | 3.0 | 2343 | 0.4338 | 0.869 |
|
| 70 |
+
| 0.2569 | 4.0 | 3124 | 0.4263 | 0.879 |
|
| 71 |
+
| 0.1417 | 5.0 | 3905 | 0.4385 | 0.8819 |
|
| 72 |
+
| 0.0961 | 6.0 | 4686 | 0.4720 | 0.8854 |
|
| 73 |
+
| 0.0584 | 7.0 | 5467 | 0.4941 | 0.885 |
|
| 74 |
+
| 0.0351 | 8.0 | 6248 | 0.5253 | 0.885 |
|
| 75 |
+
| 0.0107 | 9.0 | 7029 | 0.5598 | 0.8887 |
|
| 76 |
+
| 0.0118 | 10.0 | 7810 | 0.5998 | 0.8858 |
|
| 77 |
+
| 0.0097 | 11.0 | 8591 | 0.5957 | 0.8941 |
|
| 78 |
+
| 0.0044 | 12.0 | 9372 | 0.6237 | 0.8912 |
|
| 79 |
+
| 0.0013 | 13.0 | 10153 | 0.6286 | 0.8929 |
|
| 80 |
+
| 0.0102 | 14.0 | 10934 | 0.6281 | 0.8938 |
|
| 81 |
+
|
| 82 |
+
|
| 83 |
+
### Framework versions
|
| 84 |
+
|
| 85 |
+
- Transformers 4.20.1
|
| 86 |
+
- Pytorch 1.11.0
|
| 87 |
+
- Datasets 2.1.0
|
| 88 |
+
- Tokenizers 0.12.1
|