agusg6 commited on
Commit
0fda705
1 Parent(s): eff80d5

End of training

Browse files
Files changed (3) hide show
  1. README.md +11 -11
  2. config.json +1 -1
  3. tf_model.h5 +1 -1
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: google/vit-base-patch16-224-in21k
4
  tags:
5
  - generated_from_keras_callback
6
  model-index:
@@ -13,11 +13,11 @@ probably proofread and complete it, then remove this comment. -->
13
 
14
  # agusg6/food_classifier
15
 
16
- This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 0.8003
19
- - Validation Loss: 0.8361
20
- - Train Accuracy: 0.6188
21
  - Epoch: 4
22
 
23
  ## Model description
@@ -37,18 +37,18 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 4035, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
41
  - training_precision: float32
42
 
43
  ### Training results
44
 
45
  | Train Loss | Validation Loss | Train Accuracy | Epoch |
46
  |:----------:|:---------------:|:--------------:|:-----:|
47
- | 0.9397 | 0.8601 | 0.6337 | 0 |
48
- | 0.8864 | 0.8469 | 0.6436 | 1 |
49
- | 0.8482 | 0.8817 | 0.5842 | 2 |
50
- | 0.8441 | 0.8652 | 0.6139 | 3 |
51
- | 0.8003 | 0.8361 | 0.6188 | 4 |
52
 
53
 
54
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: agusg6/food_classifier
4
  tags:
5
  - generated_from_keras_callback
6
  model-index:
 
13
 
14
  # agusg6/food_classifier
15
 
16
+ This model is a fine-tuned version of [agusg6/food_classifier](https://huggingface.co/agusg6/food_classifier) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 0.8050
19
+ - Validation Loss: 0.8146
20
+ - Train Accuracy: 0.6475
21
  - Epoch: 4
22
 
23
  ## Model description
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 5545, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
41
  - training_precision: float32
42
 
43
  ### Training results
44
 
45
  | Train Loss | Validation Loss | Train Accuracy | Epoch |
46
  |:----------:|:---------------:|:--------------:|:-----:|
47
+ | 0.8657 | 0.8197 | 0.6403 | 0 |
48
+ | 0.8443 | 0.8155 | 0.6331 | 1 |
49
+ | 0.8306 | 0.8137 | 0.6511 | 2 |
50
+ | 0.8273 | 0.8319 | 0.6511 | 3 |
51
+ | 0.8050 | 0.8146 | 0.6475 | 4 |
52
 
53
 
54
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "google/vit-base-patch16-224-in21k",
3
  "architectures": [
4
  "ViTForImageClassification"
5
  ],
 
1
  {
2
+ "_name_or_path": "agusg6/food_classifier",
3
  "architectures": [
4
  "ViTForImageClassification"
5
  ],
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a39ed4e8611bce99075d1693721f4be401e06b03c4c38e5c53cd4f06ed9401b
3
  size 343489208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9f024374ec5e8a1fd3cc1ee1e84934ec09263ff0bb43f54f1a9df5fdc82757d
3
  size 343489208