EdgeML
EdgeML copied to clipboard
This repository provides code for machine learning algorithms for edge devices developed at Microsoft Research India.
Hi @harsha-simhadri , this is a quick implementation of the script `process_google.py`. Also, I have checked SRNN and the accuracy is in the .ipynb of the PR. Solves issue #122
- The median heuristic function [utils.medianHeuristic](https://github.com/microsoft/EdgeML/blob/master/tf/edgeml/utils.py#L12) is missing in the pytorch branch. Please copy it to `edgeml_pytorch.utils`. - It is being called from [here](https://github.com/microsoft/EdgeML/blob/0b33f1d959b8312615fac9bc941a28a16ce2cf95/pytorch/examples/ProtoNN/helpermethods.py#L49) when you run the example. That...
[fastTrainer](https://github.com/microsoft/EdgeML/blob/harsha/reorg/edgeml_pytorch/trainer/fastTrainer.py). and [fastcell_example](https://github.com/microsoft/EdgeML/blob/harsha/reorg/examples/pytorch/FastCells/fastcell_example.py) of the harsha/reorg branch seem to be out of date and need to be updated or removed. @harsha-simhadri I think thes file needs to be removed once...
The script [process_google.py](https://github.com/microsoft/EdgeML/blob/master/pytorch/examples/SRNN/process_google.py) reads all the .wav in a numpy array which might cause a memory error on many systems. Either use of disk storage through `numpy.memmap` or storing array...
There are important files that Microsoft projects should all have that are not present in this repository. A pull request has been opened to add the missing file(s). When the...
Please accept this contribution adding the standard Microsoft SECURITY.MD :lock: file to help the community understand the security policy and how to safely report security issues. GitHub uses the presence...
- Added `regression` capability for `pytorch` implementation of Bonsai - Similar to `tf` implementation, you can train model specifically for regression using `-regression True` flag - Tested on [boston-housing](https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/regression.html#housing) and...
Each class is divided into 1300 images for training and 50 images for validation.The data sets I found online only have 1300 training sets per class, how do I get...
Bumps [scipy](https://github.com/scipy/scipy) from 1.3.0 to 1.10.0. Release notes Sourced from scipy's releases. SciPy 1.10.0 Release Notes SciPy 1.10.0 is the culmination of 6 months of hard work. It contains many...