Matt Le

Results 5 issues of Matt Le

Should we be normalizing the inputs prior to feeding them into the network [[1](https://stats.stackexchange.com/questions/211436/why-do-we-normalize-images-by-subtracting-the-datasets-image-mean-and-not-the-c)]? All of the PyTorch networks contained in the model zoo use the same mean and std...

This PR adds an example showing how to crop a raster image. Example is based on #11

### 🐛 Describe the bug If the input is a video, `torchaudio.info().num_frames` returns the incorrect result. For example: ```python import torchaudio from subprocess import check_call url = "https://download.pytorch.org/torchaudio/tutorial-assets/stream-api/NASAs_Most_Scientifically_Complex_Space_Observatory_Requires_Precision-MP4_small.mp4" check_call(["wget", url,...

Is there a way of getting the sample rate of the audio from a video? ```Python reader = AudioReader() reader.get_info() ``` Will print the sample rate to stdout, but is...

I'm seeing 270046 cumulative cases for "England, United Kingdom" in the jrc-covid-19-all-days-by-regions.csv file for 2020-08-11, but in the "jrc-covid-19-regions-20201108.csv" file, it says 16820, which is much more in line with...