# 13th place solution [public LB] - brief summary

The second year to take part in freesound audio tagging, thanks for the organization for the interesting and close to reality audio competition. Thanks for
[@daisukelab](/daisukelab)
[@mhiro2](/mhiro2)
[@ceshine](/ceshine)
[@jihangz](/jihangz)
, and many kagglers for the starter kernels and discussions.
Earlier single model kernel without cv is as below:
[https://www.kaggle.com/sailorwei/fat2019-2d-cnn-with-mixup-lb-0-673](https://www.kaggle.com/sailorwei/fat2019-2d-cnn-with-mixup-lb-0-673)
Discussion about single model LB:
[https://www.kaggle.com/c/freesound-audio-tagging-2019/discussion/91881#latest-547036](https://www.kaggle.com/c/freesound-audio-tagging-2019/discussion/91881#latest-547036)
[https://github.com/sailor88128/dcase2019-task2](https://github.com/sailor88128/dcase2019-task2)
Final submission:
- On curated dataset, 5 fold cv, inception V3, single model LB is 0.691 and 5 model average is 0.713;
- On curated dataset and noisy dataset, with specific loss function, 5 fold cv, 8 layer cnn, 5 model average 0.678;
- Geometric average of these two models, 0.73+.
Techniques we ever used:
1. PCEN spectragram, didnot try many parameters, not sure if it work for this competition; 
2. mixup, about 0.01 increase in LB;
3. SpecAugment shows no increase, while RandomResizedCrop cannot be explained for audio with a better lb increase;
4. CV and tta,  about 0.05 increase for the primary single model;
5. Mixmatch, got a much lower LB with the same model, need to check the code then; 
6. Schedule of lr, cycliclr and cosineannealing do not show much difference.
Others:
1. While lots of kagglers said shallow cnn works well, we didnot get effective shallow cnn. We ever tried alexnet or vgg, all with low local lwlrap :(
2. Different cnns were used at first, but we didnot save them well for the final model ensemble;
3. Dataset with noisy label are not well used. We just used a weight loss function to train the noisy labeled data together with curated data set. The mixmatch we realize for the task maybe wrong in detail and should be checked.