ToletiSri commited on
Commit
0be40dc
·
1 Parent(s): c7b08d2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +39 -0
README.md CHANGED
@@ -10,4 +10,43 @@ pinned: false
10
  license: mit
11
  ---
12
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
10
  license: mit
11
  ---
12
 
13
+ # The School of AI - ERA(Extensive & Reimagined AI Program) - Assignment 12
14
+
15
+ This folder consists of Assignment-12 from ERA course offered by - TSAI(The school of AI).
16
+ Follow https://theschoolof.ai/ for more updates on TSAI
17
+
18
+ For more details on the assignment, refer to github link:
19
+ https://github.com/ToletiSri/TSAI_ERA_Assignments/tree/main/S12
20
+
21
+ As part of the assignment, we have trained a custom resnet model on CIFAR-10 dataset, using pytorch lightning.
22
+ We have then saved the trained model to file - saved_model.pth. The saved model is uploaded and used in the current Space.
23
+
24
+ As part of the app, we provide provide the following features to the user:
25
+ - ask the user whether he/she wants to see GradCAM images and how many, and from which layer, allow opacity change as well
26
+ - allow users to upload new images, as well as provide 10 example images
27
+ - ask how many top classes are to be shown (make sure the user cannot enter more than 10)
28
+
29
+ The custom resnet model used, has the following model architecture
30
+
31
+ -----------------------------------------------------------
32
+ # | Name | Type | Params
33
+ -------------------------------------------------------------
34
+ 0 | loss_criteria | CrossEntropyLoss | 0
35
+ 1 | accuracy | MulticlassAccuracy | 0
36
+ 2 | convblockPreparation | Sequential | 1.9 K
37
+ 3 | convblockL1X1 | Sequential | 74.0 K
38
+ 4 | convblockL1R1 | Sequential | 295 K
39
+ 5 | convblockL2X1 | Sequential | 295 K
40
+ 6 | convblockL3X1 | Sequential | 1.2 M
41
+ 7 | convblockL3R1 | Sequential | 4.7 M
42
+ 8 | FinalBlock | Sequential | 0
43
+ 9 | FC | Sequential | 5.1 K
44
+ 10 | dropout | Dropout | 0
45
+ -------------------------------------------------------------
46
+ 6.6 M Trainable params
47
+ 0 Non-trainable params
48
+ 6.6 M Total params
49
+ 26.293 Total estimated model params size (MB)
50
+
51
+
52
  Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference