update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,126 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: vit-base-patch16-224-Soybean_11-46
|
| 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: 0.9270833333333334
|
| 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 |
+
# vit-base-patch16-224-Soybean_11-46
|
| 31 |
+
|
| 32 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
|
| 33 |
+
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 0.2241
|
| 35 |
+
- Accuracy: 0.9271
|
| 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: 60
|
| 56 |
+
- eval_batch_size: 60
|
| 57 |
+
- seed: 42
|
| 58 |
+
- gradient_accumulation_steps: 4
|
| 59 |
+
- total_train_batch_size: 240
|
| 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: 50
|
| 64 |
+
|
| 65 |
+
### Training results
|
| 66 |
+
|
| 67 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 68 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 69 |
+
| 1.3661 | 1.0 | 11 | 1.3698 | 0.5069 |
|
| 70 |
+
| 0.9979 | 2.0 | 22 | 0.9817 | 0.6632 |
|
| 71 |
+
| 0.6746 | 3.0 | 33 | 0.7423 | 0.7396 |
|
| 72 |
+
| 0.6364 | 4.0 | 44 | 0.6075 | 0.7569 |
|
| 73 |
+
| 0.5425 | 5.0 | 55 | 0.5500 | 0.7951 |
|
| 74 |
+
| 0.5001 | 6.0 | 66 | 0.4883 | 0.8160 |
|
| 75 |
+
| 0.3519 | 7.0 | 77 | 0.4539 | 0.8264 |
|
| 76 |
+
| 0.4421 | 8.0 | 88 | 0.4483 | 0.8194 |
|
| 77 |
+
| 0.3207 | 9.0 | 99 | 0.3785 | 0.8438 |
|
| 78 |
+
| 0.3682 | 10.0 | 110 | 0.3385 | 0.8646 |
|
| 79 |
+
| 0.2642 | 11.0 | 121 | 0.3827 | 0.8403 |
|
| 80 |
+
| 0.3444 | 12.0 | 132 | 0.3462 | 0.8507 |
|
| 81 |
+
| 0.2423 | 13.0 | 143 | 0.3170 | 0.8681 |
|
| 82 |
+
| 0.3168 | 14.0 | 154 | 0.3168 | 0.8715 |
|
| 83 |
+
| 0.2781 | 15.0 | 165 | 0.3323 | 0.8333 |
|
| 84 |
+
| 0.2411 | 16.0 | 176 | 0.3200 | 0.8715 |
|
| 85 |
+
| 0.2276 | 17.0 | 187 | 0.3296 | 0.875 |
|
| 86 |
+
| 0.192 | 18.0 | 198 | 0.3119 | 0.8854 |
|
| 87 |
+
| 0.1612 | 19.0 | 209 | 0.3647 | 0.875 |
|
| 88 |
+
| 0.1084 | 20.0 | 220 | 0.2641 | 0.8993 |
|
| 89 |
+
| 0.2099 | 21.0 | 231 | 0.2807 | 0.8958 |
|
| 90 |
+
| 0.1666 | 22.0 | 242 | 0.2595 | 0.9097 |
|
| 91 |
+
| 0.1355 | 23.0 | 253 | 0.2735 | 0.8924 |
|
| 92 |
+
| 0.1165 | 24.0 | 264 | 0.3238 | 0.8785 |
|
| 93 |
+
| 0.112 | 25.0 | 275 | 0.3066 | 0.8889 |
|
| 94 |
+
| 0.1191 | 26.0 | 286 | 0.2427 | 0.9062 |
|
| 95 |
+
| 0.1293 | 27.0 | 297 | 0.2536 | 0.9201 |
|
| 96 |
+
| 0.2932 | 28.0 | 308 | 0.2707 | 0.8924 |
|
| 97 |
+
| 0.0918 | 29.0 | 319 | 0.2688 | 0.8924 |
|
| 98 |
+
| 0.1529 | 30.0 | 330 | 0.2715 | 0.8889 |
|
| 99 |
+
| 0.227 | 31.0 | 341 | 0.2664 | 0.9028 |
|
| 100 |
+
| 0.1044 | 32.0 | 352 | 0.2809 | 0.8993 |
|
| 101 |
+
| 0.0894 | 33.0 | 363 | 0.2863 | 0.8924 |
|
| 102 |
+
| 0.0566 | 34.0 | 374 | 0.2474 | 0.9201 |
|
| 103 |
+
| 0.0915 | 35.0 | 385 | 0.2428 | 0.9097 |
|
| 104 |
+
| 0.1136 | 36.0 | 396 | 0.2545 | 0.9097 |
|
| 105 |
+
| 0.0947 | 37.0 | 407 | 0.2599 | 0.9097 |
|
| 106 |
+
| 0.1012 | 38.0 | 418 | 0.2454 | 0.9167 |
|
| 107 |
+
| 0.0465 | 39.0 | 429 | 0.2435 | 0.9201 |
|
| 108 |
+
| 0.0299 | 40.0 | 440 | 0.2532 | 0.9062 |
|
| 109 |
+
| 0.0311 | 41.0 | 451 | 0.2298 | 0.9271 |
|
| 110 |
+
| 0.0796 | 42.0 | 462 | 0.2422 | 0.9167 |
|
| 111 |
+
| 0.058 | 43.0 | 473 | 0.2058 | 0.9306 |
|
| 112 |
+
| 0.0853 | 44.0 | 484 | 0.2266 | 0.9306 |
|
| 113 |
+
| 0.0868 | 45.0 | 495 | 0.2266 | 0.9236 |
|
| 114 |
+
| 0.0554 | 46.0 | 506 | 0.2163 | 0.9271 |
|
| 115 |
+
| 0.0508 | 47.0 | 517 | 0.2104 | 0.9306 |
|
| 116 |
+
| 0.0589 | 48.0 | 528 | 0.2172 | 0.9271 |
|
| 117 |
+
| 0.0369 | 49.0 | 539 | 0.2214 | 0.9271 |
|
| 118 |
+
| 0.0852 | 50.0 | 550 | 0.2241 | 0.9271 |
|
| 119 |
+
|
| 120 |
+
|
| 121 |
+
### Framework versions
|
| 122 |
+
|
| 123 |
+
- Transformers 4.30.0.dev0
|
| 124 |
+
- Pytorch 1.12.1
|
| 125 |
+
- Datasets 2.12.0
|
| 126 |
+
- Tokenizers 0.13.1
|