Thomas Viehmann t-vi

🌍

Creating fun and friendly AIs

Principal Research Engineer at @Lightning-AI Mathematics and Inference at @MathInf I do a lot of @pytorch work

t-vi / benchmarking.py

Last active October 18, 2018 12:09

native batch norm

	import torch
	import pickle
	import math
	print ("git revision:", torch.__version__)
	with open('/tmp/1.0.0a0-058c128_timings.pkl', "rb") as f:
	reference_timings_dict = pickle.load(f)

	print ("""
	input shape = (bs, channels) + features
	mode = (training/eval)-(forward+backward)/forward

t-vi / speech_command_recognition_quantization-part1.ipynb

Last active June 21, 2021 17:10

Sorry, something went wrong. Reload?

Sorry, we cannot display this file.

Sorry, this file is invalid so it cannot be displayed.

t-vi / speech_command_recognition_quantization_full.ipynb

Created July 19, 2021 10:51

Code for Training an Edge Optimized Speech Recognition Model with PyTorch Lightning

Sorry, something went wrong. Reload?

Sorry, we cannot display this file.

Sorry, this file is invalid so it cannot be displayed.