Model save
Browse files- README.md +107 -0
- pytorch_model.bin +1 -1
README.md
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: microsoft/swin-tiny-patch4-window7-224
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- imagefolder
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: swin-tiny-patch4-window7-224-finetuned-200k
|
| 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: train
|
| 21 |
+
args: default
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Accuracy
|
| 24 |
+
type: accuracy
|
| 25 |
+
value: 0.796086508753862
|
| 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 |
+
# swin-tiny-patch4-window7-224-finetuned-200k
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.4347
|
| 36 |
+
- Accuracy: 0.7961
|
| 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: 128
|
| 57 |
+
- eval_batch_size: 128
|
| 58 |
+
- seed: 42
|
| 59 |
+
- gradient_accumulation_steps: 4
|
| 60 |
+
- total_train_batch_size: 512
|
| 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: 30
|
| 65 |
+
|
| 66 |
+
### Training results
|
| 67 |
+
|
| 68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
+
| 0.634 | 0.99 | 36 | 0.6243 | 0.6262 |
|
| 71 |
+
| 0.5551 | 1.99 | 72 | 0.5186 | 0.7250 |
|
| 72 |
+
| 0.5183 | 2.98 | 108 | 0.4826 | 0.7673 |
|
| 73 |
+
| 0.4854 | 4.0 | 145 | 0.5640 | 0.7261 |
|
| 74 |
+
| 0.4645 | 4.99 | 181 | 0.4598 | 0.7817 |
|
| 75 |
+
| 0.4655 | 5.99 | 217 | 0.4787 | 0.7786 |
|
| 76 |
+
| 0.4582 | 6.98 | 253 | 0.4483 | 0.7899 |
|
| 77 |
+
| 0.4415 | 8.0 | 290 | 0.4709 | 0.7765 |
|
| 78 |
+
| 0.4546 | 8.99 | 326 | 0.4717 | 0.7817 |
|
| 79 |
+
| 0.4566 | 9.99 | 362 | 0.4538 | 0.7951 |
|
| 80 |
+
| 0.4675 | 10.98 | 398 | 0.4491 | 0.7817 |
|
| 81 |
+
| 0.4449 | 12.0 | 435 | 0.4992 | 0.7652 |
|
| 82 |
+
| 0.4349 | 12.99 | 471 | 0.4627 | 0.7817 |
|
| 83 |
+
| 0.4253 | 13.99 | 507 | 0.4492 | 0.7858 |
|
| 84 |
+
| 0.4278 | 14.98 | 543 | 0.4442 | 0.7951 |
|
| 85 |
+
| 0.4567 | 16.0 | 580 | 0.4362 | 0.7899 |
|
| 86 |
+
| 0.4205 | 16.99 | 616 | 0.4550 | 0.7889 |
|
| 87 |
+
| 0.4233 | 17.99 | 652 | 0.4336 | 0.7909 |
|
| 88 |
+
| 0.4014 | 18.98 | 688 | 0.4565 | 0.7889 |
|
| 89 |
+
| 0.4176 | 20.0 | 725 | 0.4323 | 0.7940 |
|
| 90 |
+
| 0.411 | 20.99 | 761 | 0.4348 | 0.7951 |
|
| 91 |
+
| 0.4128 | 21.99 | 797 | 0.4378 | 0.7971 |
|
| 92 |
+
| 0.4045 | 22.98 | 833 | 0.4317 | 0.7951 |
|
| 93 |
+
| 0.4001 | 24.0 | 870 | 0.4452 | 0.7868 |
|
| 94 |
+
| 0.4061 | 24.99 | 906 | 0.4286 | 0.7920 |
|
| 95 |
+
| 0.4033 | 25.99 | 942 | 0.4306 | 0.7951 |
|
| 96 |
+
| 0.3953 | 26.98 | 978 | 0.4320 | 0.7920 |
|
| 97 |
+
| 0.3924 | 28.0 | 1015 | 0.4338 | 0.7940 |
|
| 98 |
+
| 0.4056 | 28.99 | 1051 | 0.4329 | 0.7930 |
|
| 99 |
+
| 0.4032 | 29.79 | 1080 | 0.4347 | 0.7961 |
|
| 100 |
+
|
| 101 |
+
|
| 102 |
+
### Framework versions
|
| 103 |
+
|
| 104 |
+
- Transformers 4.33.3
|
| 105 |
+
- Pytorch 2.0.1+cu117
|
| 106 |
+
- Datasets 2.14.5
|
| 107 |
+
- 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 110394865
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be2717dc47c05c4e22048c801af87487ec78c77778c96f2ca5060a148c349c31
|
| 3 |
size 110394865
|