microsoft / EdgeML

This repository provides code for machine learning algorithms for edge devices developed at Microsoft Research India.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

i want to use Bosani with anaconda spyder

musaosman78 opened this issue · comments

hi,
i have a problem when i am trying to use the Bosani module in my spyder

File "", line 1, in
import helpermethods

ModuleNotFoundError: No module named 'helpermethods'
also if i want this model in my own dataset how can i use
thanks in advance

Hi @musaosman78,

  1. helpermethods.py is in the same location as bonsai_example.py here: https://github.com/microsoft/EdgeML/tree/master/examples/pytorch/Bonsai
    Can you please share detailed setup information and trace so that I can help you?

  2. bonsai_example.py assumes that data is in a specific format. It is assumed that train and test data is contained in two files, train.npy and test.npy. Each containing a 2D numpy array of dimension [numberOfExamples, numberOfFeatures + 1]. The first column of each matrix is assumed to contain label information. For an N-Class problem, we assume the labels are integers
    from 0 through N-1.
    So either you can convert your dataset to the above format or else modify the preProcessData function here accordingly.

Thanks SachinG007 , another question how to plot the accuracy and the loss function

Hi @musaosman78,
The line here gives you the training loss and training accuracy after every epoch. You can dump these values in a list and plot them later. You can also use tensorboardX for monitoring the same values while the training is ongoing.