Build a FC layer‐based neural network to recognize hand‐written digits
$30-250 USD
Paid on delivery
Train and test a neural network for entire MNIST hand‐ written digit dataset. Some information of the network is as follows:
-Its structure is 784‐200‐50‐10. Here 784 means the input layer has 784 input neurons. This is because each image in MNIST dataset is 28x28 and you need to stretch them to a length‐784 vector. 200 and 50 are the number of neurons in hidden layers. 10 is the number of neurons in output layer since there are 10 types of digits.
-The two hidden layers are followed by ReLU layers.
-The output layer is a softmax layer.
Use a deep learning framework to train and test this network.
For dataset loading in Pytorch, you can refer to the following example code: [login to view URL] (feel free to use tensor but I’m not sure how you would go about loading the mnist dataset)
I've included a py file to download the MNIST database if you need it
Project ID: #24855675
About the project
Awarded to:
Hi, I have understand your project and willing to do it with in specific time and budget. Here, My Name is [login to view URL] Subhani. My domain of specialization is Machine Learning, Deep Learning, NLP, and Big data Analytics. More
7 freelancers are bidding on average $117 for this job
We will do your python work I am writing this proposal in order to work for you in Software and Web Development. We are highly trained professional developers seeking to freelance and earn online. Having a flair in pr More
Hello, Hope this message finds you well, I checked your details and I believe that my experience is what you are looking 4. I have been working on similar projects for the past eight years, and I have the essential sk More
Hi, I am a professional programmer and will give you the best work I have an Innovative tech mind with 10 years of experience working as a computer programmer. Capable of working with a variety of technology and softwa More