update model card README.md
Browse files
README.md
CHANGED
|
@@ -5,24 +5,9 @@ tags:
|
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- imagefolder
|
| 8 |
-
metrics:
|
| 9 |
-
- accuracy
|
| 10 |
model-index:
|
| 11 |
- name: attraction-classifier
|
| 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: 0.8389955686853766
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -31,9 +16,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 31 |
# attraction-classifier
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
|
| 34 |
-
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.3983
|
| 36 |
-
- Accuracy: 0.8390
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
@@ -55,7 +37,7 @@ The following hyperparameters were used during training:
|
|
| 55 |
- learning_rate: 5e-05
|
| 56 |
- train_batch_size: 16
|
| 57 |
- eval_batch_size: 16
|
| 58 |
-
- seed:
|
| 59 |
- gradient_accumulation_steps: 4
|
| 60 |
- total_train_batch_size: 64
|
| 61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
@@ -63,25 +45,9 @@ The following hyperparameters were used during training:
|
|
| 63 |
- lr_scheduler_warmup_ratio: 0.1
|
| 64 |
- num_epochs: 10
|
| 65 |
|
| 66 |
-
### Training results
|
| 67 |
-
|
| 68 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
-
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
-
| 0.5745 | 0.99 | 42 | 0.5208 | 0.7829 |
|
| 71 |
-
| 0.4617 | 2.0 | 85 | 0.4346 | 0.8065 |
|
| 72 |
-
| 0.4245 | 2.99 | 127 | 0.4151 | 0.8346 |
|
| 73 |
-
| 0.3512 | 4.0 | 170 | 0.3854 | 0.8508 |
|
| 74 |
-
| 0.3146 | 4.99 | 212 | 0.4062 | 0.8360 |
|
| 75 |
-
| 0.3235 | 6.0 | 255 | 0.3864 | 0.8390 |
|
| 76 |
-
| 0.2699 | 6.99 | 297 | 0.4094 | 0.8508 |
|
| 77 |
-
| 0.3049 | 8.0 | 340 | 0.3735 | 0.8567 |
|
| 78 |
-
| 0.2459 | 8.99 | 382 | 0.4037 | 0.8360 |
|
| 79 |
-
| 0.2277 | 9.88 | 420 | 0.3983 | 0.8390 |
|
| 80 |
-
|
| 81 |
-
|
| 82 |
### Framework versions
|
| 83 |
|
| 84 |
-
- Transformers 4.
|
| 85 |
-
- Pytorch 2.
|
| 86 |
-
- Datasets 2.
|
| 87 |
-
- Tokenizers 0.
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- imagefolder
|
|
|
|
|
|
|
| 8 |
model-index:
|
| 9 |
- name: attraction-classifier
|
| 10 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 16 |
# attraction-classifier
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 37 |
- learning_rate: 5e-05
|
| 38 |
- train_batch_size: 16
|
| 39 |
- eval_batch_size: 16
|
| 40 |
+
- seed: 69
|
| 41 |
- gradient_accumulation_steps: 4
|
| 42 |
- total_train_batch_size: 64
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
|
|
| 45 |
- lr_scheduler_warmup_ratio: 0.1
|
| 46 |
- num_epochs: 10
|
| 47 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
### Framework versions
|
| 49 |
|
| 50 |
+
- Transformers 4.31.0
|
| 51 |
+
- Pytorch 2.0.1+cu117
|
| 52 |
+
- Datasets 2.12.0
|
| 53 |
+
- Tokenizers 0.13.3
|