Commit
•
6dcb75b
1
Parent(s):
579406e
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-large-patch4-window12to16-192to256-22kto1k-ft-finetuned-eurosat-50
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Image Classification
|
| 14 |
+
type: image-classification
|
| 15 |
+
dataset:
|
| 16 |
+
name: imagefolder
|
| 17 |
+
type: imagefolder
|
| 18 |
+
config: Skin_Cancer
|
| 19 |
+
split: train
|
| 20 |
+
args: Skin_Cancer
|
| 21 |
+
metrics:
|
| 22 |
+
- name: Accuracy
|
| 23 |
+
type: accuracy
|
| 24 |
+
value: 0.8338983050847457
|
| 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-large-patch4-window12to16-192to256-22kto1k-ft-finetuned-eurosat-50
|
| 31 |
+
|
| 32 |
+
This model is a fine-tuned version of [microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft](https://huggingface.co/microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft) on the imagefolder dataset.
|
| 33 |
+
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 0.5108
|
| 35 |
+
- Accuracy: 0.8339
|
| 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: 3e-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: 0.005
|
| 63 |
+
- num_epochs: 30
|
| 64 |
+
|
| 65 |
+
### Training results
|
| 66 |
+
|
| 67 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 68 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 69 |
+
| No log | 0.97 | 18 | 1.3358 | 0.5017 |
|
| 70 |
+
| 1.7327 | 2.0 | 37 | 0.9711 | 0.6102 |
|
| 71 |
+
| 1.1314 | 2.97 | 55 | 0.6877 | 0.7254 |
|
| 72 |
+
| 0.7956 | 4.0 | 74 | 0.6924 | 0.7458 |
|
| 73 |
+
| 0.6511 | 4.97 | 92 | 0.7236 | 0.6915 |
|
| 74 |
+
| 0.5609 | 6.0 | 111 | 0.5625 | 0.8169 |
|
| 75 |
+
| 0.4585 | 6.97 | 129 | 0.5356 | 0.8102 |
|
| 76 |
+
| 0.3988 | 8.0 | 148 | 0.8137 | 0.7186 |
|
| 77 |
+
| 0.35 | 8.97 | 166 | 0.5569 | 0.8136 |
|
| 78 |
+
| 0.3431 | 10.0 | 185 | 0.6979 | 0.7729 |
|
| 79 |
+
| 0.2888 | 10.97 | 203 | 0.5444 | 0.8 |
|
| 80 |
+
| 0.2553 | 12.0 | 222 | 0.6462 | 0.7729 |
|
| 81 |
+
| 0.2263 | 12.97 | 240 | 0.5093 | 0.8373 |
|
| 82 |
+
| 0.2263 | 14.0 | 259 | 0.5331 | 0.8169 |
|
| 83 |
+
| 0.2323 | 14.97 | 277 | 0.5521 | 0.8203 |
|
| 84 |
+
| 0.1601 | 16.0 | 296 | 0.5984 | 0.7831 |
|
| 85 |
+
| 0.1645 | 16.97 | 314 | 0.6850 | 0.7932 |
|
| 86 |
+
| 0.202 | 18.0 | 333 | 0.5786 | 0.8 |
|
| 87 |
+
| 0.1762 | 18.97 | 351 | 0.5961 | 0.8305 |
|
| 88 |
+
| 0.1546 | 20.0 | 370 | 0.6169 | 0.8373 |
|
| 89 |
+
| 0.1583 | 20.97 | 388 | 0.4907 | 0.8373 |
|
| 90 |
+
| 0.1168 | 22.0 | 407 | 0.4846 | 0.8508 |
|
| 91 |
+
| 0.1193 | 22.97 | 425 | 0.5030 | 0.8475 |
|
| 92 |
+
| 0.1275 | 24.0 | 444 | 0.5287 | 0.8373 |
|
| 93 |
+
| 0.1214 | 24.97 | 462 | 0.5240 | 0.8407 |
|
| 94 |
+
| 0.1107 | 26.0 | 481 | 0.5439 | 0.8407 |
|
| 95 |
+
| 0.1107 | 26.97 | 499 | 0.4901 | 0.8305 |
|
| 96 |
+
| 0.0921 | 28.0 | 518 | 0.5037 | 0.8407 |
|
| 97 |
+
| 0.1105 | 28.97 | 536 | 0.5105 | 0.8305 |
|
| 98 |
+
| 0.0883 | 29.19 | 540 | 0.5108 | 0.8339 |
|
| 99 |
+
|
| 100 |
+
|
| 101 |
+
### Framework versions
|
| 102 |
+
|
| 103 |
+
- Transformers 4.30.2
|
| 104 |
+
- Pytorch 2.0.1+cu118
|
| 105 |
+
- Datasets 2.13.1
|
| 106 |
+
- Tokenizers 0.13.3
|