Update README.md
Browse files
README.md
CHANGED
@@ -1,6 +1,3 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
---
|
4 |
# Description
|
5 |
This model is a convolutional neural network built with transfer learning using the pre-trained model 'VGG16.' The 'block5_conv1' layer is retrained, and a final dense layer with 128 neurons is added.
|
6 |
|
@@ -20,7 +17,7 @@ class_9: cell contains the number 9
|
|
20 |
The dataset is constructed with balanced classes using images from the famous "MNIST digits classification" dataset, as well as images of numbers written digitally.
|
21 |
|
22 |
# Dataset schema
|
23 |
-
After applying data augmentation to the dataset, the total number of images is as follows:
|
24 |
- Training images: 5600
|
25 |
- Validation images: 2400
|
26 |
- Test images: 200
|
@@ -30,10 +27,14 @@ Test Accuracy: 0.9810
|
|
30 |
# Other validations:
|
31 |
An initial validation is performed. It remains pending to increase the size of the validations to understand the reliability of the mode
|
32 |
|
33 |
-
|
|
|
|
|
|
|
34 |
|
35 |
The results of the inference are as follows:
|
36 |
-
|
37 |
-
|
|
|
38 |
|
39 |
|
|
|
|
|
|
|
|
|
1 |
# Description
|
2 |
This model is a convolutional neural network built with transfer learning using the pre-trained model 'VGG16.' The 'block5_conv1' layer is retrained, and a final dense layer with 128 neurons is added.
|
3 |
|
|
|
17 |
The dataset is constructed with balanced classes using images from the famous "MNIST digits classification" dataset, as well as images of numbers written digitally.
|
18 |
|
19 |
# Dataset schema
|
20 |
+
The image size it is 28x28. After applying data augmentation to the dataset, the total number of images is as follows:
|
21 |
- Training images: 5600
|
22 |
- Validation images: 2400
|
23 |
- Test images: 200
|
|
|
27 |
# Other validations:
|
28 |
An initial validation is performed. It remains pending to increase the size of the validations to understand the reliability of the mode
|
29 |
|
30 |
+
<div style="text-align: center;">
|
31 |
+
<img src="https://i.imgur.com/kdj9udt.jpg" width="300">
|
32 |
+
</div>
|
33 |
+
</div>
|
34 |
|
35 |
The results of the inference are as follows:
|
36 |
+
<div style="text-align: center;">
|
37 |
+
<img src="https://i.imgur.com/U2MJzH6.jpg" width="500">
|
38 |
+
</div>
|
39 |
|
40 |
|