Awsaf

> > > Could you please provide links to the description of Mosaic Augmentation? I think it was even mentioned in YOLOv4 paper. Here are some references: https://www.kaggle.com/nvnnghia/awesome-augmentation https://github.com/klauspa/Yolov4-tensorflow

> cc. @awsaf49 > Cutmix is available officially in `keras`, [HERE](https://github.com/keras-team/keras-cv/blob/master/keras_cv/layers/preprocessing/cut_mix.py). The Mosaic one will be soon. Thank you 😀

@younesbelkada Did you try finetuning it on **kitti** dataset as well?

@younesbelkada Thanks for your reply. The issue with **kitti** is that it doesn't come with **dense/interpolated** depth map like **nyuv2** dataset. Hence, I'm having doubts if they trained model with...

I am wondering the same thing.

@hamelsmu could you please have a look?

cc: @fchollet kindly need your review on this, specifically I'm not sure how this layer will fit to current keras v3. For now, I'm keeping everything in `layers/preprocessing/audio_preprocessing.py`. Also, while...

Visual results seem fine,  ```py import librosa import matplotlib.pyplot as plt import librosa.display num_mel_bins = 256 fft_stride = 128 num_fft_bins = 1024 fmin = 512 fmax = 8000 y,...

> Looking good! Please add a set of unit tests as well. Thanks. I will add the unit test soon.

@fchollet, while performing correctness tests, I noticed that the result from `keras` matches with `torchaudio` but doesn't match with `librosa`, even when the parameters are the same. However, visually, they...