Mohammed Innat commited on
Commit
3c519a5
1 Parent(s): 0f09377

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +24 -5
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- title: Demo
3
  emoji: 🔥
4
  colorFrom: purple
5
  colorTo: yellow
@@ -9,8 +9,27 @@ app_file: app.py
9
  pinned: false
10
  ---
11
 
12
- ## Visual Interpretation of a Hybrid Model
13
 
14
- Building a hybrid model with *EfficientNet* and *Swin Transformer*, we have tried to inspect the visual interpretations of a CNN and Transformer blocks of a hybrid model (CNN + Swin Transformer) with the GradCAM technique. As a result, it appears that the transformer blocks are capable of globally refining feature activation across the relevant object, as opposed to the CNN, which is more focused on operating locally. However, the approach that will be shown here, is experimental. The workflow probably can generate a more meaningful modeling approach. The model is trained on [tf_flowers](https://www.tensorflow.org/datasets/catalog/tf_flowers) dataset, a multi-class classification problem.
15
-
16
- ![]('./Presentation2.png')
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ title: HybridModel-GradCAM
3
  emoji: 🔥
4
  colorFrom: purple
5
  colorTo: yellow
 
9
  pinned: false
10
  ---
11
 
 
12
 
13
+ <table class="tfo-notebook-buttons" align="center">
14
+
15
+ <td>
16
+ <a target="_blank" href="https://colab.research.google.com/drive/1usxq9yhZthyapAnzFfFObQ7RjXPicAop?usp=sharing"><img src="https://www.tensorflow.org/images/colab_logo_32px.png" />Run in Google Colab</a>
17
+ </td>
18
+
19
+ <td>
20
+ <a target="_blank" href="https://github.com/innat/Hybrid-EfficientNet-Swin-Transformer"><img src="https://www.tensorflow.org/images/GitHub-Mark-32px.png" />View source on GitHub</a>
21
+ </td>
22
+
23
+ <td>
24
+ <a target="_blank" href="https://deepnote.com/workspace/mohammed-innat-36e929bc-ce23-4d95-9ddc-a9c6662eb7d6/project/Notebooks-32e94ef4-8ce0-4cc4-8042-49862519f3f2/%2F%5BDeepnote%5D_HENetSwinT.ipynb"><img src="https://bit.ly/3NYODoU" />Run in Deepnote</a>
25
+ </td>
26
+
27
+ <td>
28
+ <a target="_blank" href="https://www.kaggle.com/code/ipythonx/tf-hybrid-efficientnet-swin-transformer-gradcam"><img src="https://bit.ly/3HqRDIf" />Run in Kaggle</a>
29
+ </td>
30
+
31
+ <td>
32
+ <a target="_blank" href="https://github.com/tensorflow/similarity/blob/master/examples/unsupervised_hello_world.ipynb"><img src="https://bit.ly/3mOOoRo" />Try on Gradio</a>
33
+ </td>
34
+
35
+ </table>