You are required to train a neural net model for the handwritten data set. Python script will be used to evaluate each code.
Only use python version 3 (not 2) for coding.
Input to file:
Your code should accept command line parameters. It should take one image file name as
python3 [login to view URL] [login to view URL]
Input image file will have fixed 20x20 size in grayscale. In the given dataset images are saved in the form of rows of 400 length.
These rows can be converted into 20x20 grayscale images by using following python code.
(You may import packages form numpy and matplotlib)
[login to view URL](filename, [login to view URL](data).reshape(20,20).T,cmap="gray")
In the example above data is the row data of X. for example X, X so on, “filename”
is the name of the image file. It can be any name like “[login to view URL]”, “[login to view URL]” so on.
Output of file:
Output of your code should be the predicted digit. Only digit in one line must be written as
Testing your code:
Script will evaluate each code. I shall provide the input image (unseen) (size 20x20, gray
scale) to your code and will give +1 or 0 reward for each right and wrong prediction
respectively. Same test data set will be provided to each script.
14 freelancers are bidding on average $55 for this job
Hi, Currently I'm working in Deep Learning Field and I know how to complete this project. I've worked on similar projects and can complete as soon as required.
My name is Dimitri, I studied in Georgia at 'TSU University' and have obtained a master's degree in computer science, I have studied neural networks for 2 years. if it's your wish, I'll try to help you.
I am a professional full-time CNN engineer. I like to practice my skills outside my working hours. This seems to be an easy student-level image classification CNN task. python version 3 is no problem.