Total runs:
105
Run Growth:
-49
Growth Rate:
-46.67%
Sponsored by
YouArt
keras-io / consistency_training_with_supervision_student_model
Model's Last Updated: July 05 2024
image-classification
Introduction of consistency_training_with_supervision_student_model
Model Details of consistency_training_with_supervision_student_model
Model description
Consistency training with supervision
In this example, we have trained an image classification model enforcing a sense of consistency inside it by doing the following:
- Train a standard image classification model.
- Train an equal or larger model on a noisy version of the dataset (augmented using RandAugment).
- To do this, we will first obtain predictions of the previous model on the clean images of the dataset.
- We will then use these predictions and train the second model to match these predictions on the noisy variant of the same images. This is identical to the workflow of Knowledge Distillation but since the student model is equal or larger in size this process is also referred to as Self-Training.
This overall training workflow finds its roots in works like FixMatch, Unsupervised Data Augmentation for Consistency Training, and Noisy Student Training. Since this training process encourages a model yield consistent predictions for clean as well as noisy images, it's often referred to as consistency training or training with consistency regularization. Although the example focuses on using consistency training to enhance the robustness of models to common corruptions this example can also serve a template for performing weakly supervised learning.
Full Credits to Sayak Paul for this work.
This repo contains only the Student Model of this training example.
Teacher Model Repo can be find at this Link .
Intended uses & limitations
More information needed
Training and evaluation data
Trained and evaluated on CIFAR-10 dataset.
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
| name | optimizer | average_period | start_averaging | training_precision |
|---|---|---|---|---|
| SWA | {'class_name': 'Adam', 'config': {'name': 'Adam', 'learning_rate': 3.9063e-06, 'decay': 0.5, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}} | 10 | 0 | float32 |
Model Plot
View Model Plot
Runs of keras-io consistency_training_with_supervision_student_model on huggingface.co
18
Total runs
0
24-hour runs
-2
3-day runs
-3
7-day runs
12
30-day runs
More Information About consistency_training_with_supervision_student_model huggingface.co Model
Url of consistency_training_with_supervision_student_model
consistency_training_with_supervision_student_model huggingface.co Url
Provider of consistency_training_with_supervision_student_model huggingface.co
Other API from keras-io
Updated:July 05 2024
Total runs:
104
Run Growth:
87
Growth Rate:
83.65%
Total runs:
69
Run Growth:
43
Growth Rate:
60.56%
Total runs:
56
Run Growth:
56
Growth Rate:
87.50%
Total runs:
44
Run Growth:
9
Growth Rate:
20.45%
Total runs:
42
Run Growth:
14
Growth Rate:
32.56%
Total runs:
42
Run Growth:
-35
Growth Rate:
-83.33%
Total runs:
42
Run Growth:
-20
Growth Rate:
-46.51%
Total runs:
40
Run Growth:
-16
Growth Rate:
-40.00%
Total runs:
39
Run Growth:
27
Growth Rate:
69.23%
Total runs:
39
Run Growth:
17
Growth Rate:
43.59%
Total runs:
38
Run Growth:
21
Growth Rate:
55.26%
Total runs:
34
Run Growth:
18
Growth Rate:
52.94%
Total runs:
33
Run Growth:
-9
Growth Rate:
-27.27%
Total runs:
33
Run Growth:
-2
Growth Rate:
-5.56%
Total runs:
33
Run Growth:
16
Growth Rate:
48.48%
Total runs:
30
Run Growth:
-10
Growth Rate:
-33.33%
Total runs:
30
Run Growth:
15
Growth Rate:
50.00%
Total runs:
28
Run Growth:
-13
Growth Rate:
-44.83%
Total runs:
27
Run Growth:
-4
Growth Rate:
-14.81%
Total runs:
27
Run Growth:
0
Growth Rate:
0.00%
Total runs:
25
Run Growth:
-7
Growth Rate:
-28.00%
Total runs:
20
Run Growth:
-1
Growth Rate:
-4.35%
Total runs:
23
Run Growth:
-14
Growth Rate:
-60.87%
Total runs:
22
Run Growth:
2
Growth Rate:
9.09%
Total runs:
24
Run Growth:
0
Growth Rate:
0.00%
Total runs:
21
Run Growth:
-41
Growth Rate:
-195.24%
Total runs:
20
Run Growth:
-5
Growth Rate:
-25.00%
Total runs:
19
Run Growth:
4
Growth Rate:
21.05%
Total runs:
18
Run Growth:
1
Growth Rate:
5.56%
Total runs:
16
Run Growth:
-5
Growth Rate:
-31.25%
Total runs:
16
Run Growth:
-2
Growth Rate:
-12.50%
Total runs:
16
Run Growth:
15
Growth Rate:
93.75%
Total runs:
15
Run Growth:
8
Growth Rate:
53.33%
Total runs:
14
Run Growth:
4
Growth Rate:
28.57%
Total runs:
13
Run Growth:
3
Growth Rate:
23.08%
Total runs:
12
Run Growth:
-1
Growth Rate:
-8.33%
Total runs:
12
Run Growth:
-11
Growth Rate:
-91.67%
Total runs:
12
Run Growth:
0
Growth Rate:
0.00%
Total runs:
12
Run Growth:
6
Growth Rate:
50.00%
Total runs:
11
Run Growth:
3
Growth Rate:
27.27%
Total runs:
11
Run Growth:
-1
Growth Rate:
-9.09%
Total runs:
10
Run Growth:
7
Growth Rate:
70.00%
Total runs:
10
Run Growth:
-14
Growth Rate:
-140.00%
Total runs:
10
Run Growth:
-10
Growth Rate:
-90.91%
Total runs:
8
Run Growth:
-19
Growth Rate:
-237.50%
Total runs:
8
Run Growth:
-2
Growth Rate:
-22.22%
Total runs:
7
Run Growth:
3
Growth Rate:
42.86%
Total runs:
5
Run Growth:
-3
Growth Rate:
-42.86%
Total runs:
5
Run Growth:
-5
Growth Rate:
-100.00%
Total runs:
4
Run Growth:
3
Growth Rate:
75.00%
Total runs:
4
Run Growth:
-1
Growth Rate:
-25.00%
Total runs:
3
Run Growth:
-16
Growth Rate:
-533.33%
Total runs:
3
Run Growth:
1
Growth Rate:
33.33%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%