Hugging Face's logo

Spaces:
gputrain
/
UrbanSounds8K
Runtime error

App Files Community
gputrain commited on
Commit
02c67bc
•
1 Parent(s): 16b6f95

update text

Browse files
Files changed (1) hide show
  1. article.md +2 -3
article.md CHANGED
@@ -10,15 +10,14 @@ Files are converted to melspectrograms that perform better in general for visual
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 |
17
- | epoch | train_loss | valid_loss | accuracy | time |
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)
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 |
 
17
  | 0 | 0.600056 | 0.309964 | 0.892325 | 00:40 |
18
  |1 | 0.260431 | 0.200901 | 0.945017 | 00:39 |
19
  | 2 | 0.090158 | 0.164748 | 0.950745 | 00:40 |
20
+
21
  ## Classical Approaches
22
 
23
  [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)