Hugging Face's logo

Spaces:
gputrain
/
UrbanSounds8K
Runtime error

App Files Community
gputrain commited on
Commit
16b6f95
•
1 Parent(s): 888bf57

update

Browse files
Files changed (1) hide show
  1. article.md +2 -3
article.md CHANGED
@@ -1,5 +1,3 @@
1
- > Note: The examples provides may not work on Safari, tablets and iOS devices. Try an alternate approach.
2
-
3
  ## Dataset
4
 
5
  - [UrbanSound8K](https://urbansounddataset.weebly.com/urbansound8k.html)
@@ -12,6 +10,7 @@ Files are converted to melspectrograms that perform better in general for visual
12
 
13
  Using With Fast.ai and three epochs with minimal lines of code approaches 95% accuracy with a 20% validation of the entire dataset of 8732 labelled sound excerpts of 10 classes shown above. Fast.ai was used to train this classifier with a Resnet34 vision learner with three epochs.
14
 
 
15
  | epoch | train_loss | valid_loss | accuracy | time |
16
  |-------|------------|-------------|-------------|-------|
17
  |0 | 1.462791 | 0.710250 | 0.775487 | 01:12 |
@@ -19,7 +18,7 @@ Using With Fast.ai and three epochs with minimal lines of code approaches 95% ac
19
  | 0 | 0.600056 | 0.309964 | 0.892325 | 00:40 |
20
  |1 | 0.260431 | 0.200901 | 0.945017 | 00:39 |
21
  | 2 | 0.090158 | 0.164748 | 0.950745 | 00:40 |
22
-
23
  ## Classical Approaches
24
 
25
  [Classical approaches on this dataset as of 2019](https://www.researchgate.net/publication/335862311_Evaluation_of_Classical_Machine_Learning_Techniques_towards_Urban_Sound_Recognition_on_Embedded_Systems)
 
 
1
  ## Dataset
2
 
3
  - [UrbanSound8K](https://urbansounddataset.weebly.com/urbansound8k.html)
10
 
11
  Using With Fast.ai and three epochs with minimal lines of code approaches 95% accuracy with a 20% validation of the entire dataset of 8732 labelled sound excerpts of 10 classes shown above. Fast.ai was used to train this classifier with a Resnet34 vision learner with three epochs.
12
 
13
+ |-------|------------|-------------|-------------|-------|
14
  | epoch | train_loss | valid_loss | accuracy | time |
15
  |-------|------------|-------------|-------------|-------|
16
  |0 | 1.462791 | 0.710250 | 0.775487 | 01:12 |
18
  | 0 | 0.600056 | 0.309964 | 0.892325 | 00:40 |
19
  |1 | 0.260431 | 0.200901 | 0.945017 | 00:39 |
20
  | 2 | 0.090158 | 0.164748 | 0.950745 | 00:40 |
21
+ |-------|------------|-------------|-------------|-------|
22
  ## Classical Approaches
23
 
24
  [Classical approaches on this dataset as of 2019](https://www.researchgate.net/publication/335862311_Evaluation_of_Classical_Machine_Learning_Techniques_towards_Urban_Sound_Recognition_on_Embedded_Systems)