Open in app
Deborah Digges
180 Followers
About

Sign in

180 Followers
About
Open in app
Deborah Digges

Deborah Digges

Jan 6, 2017·1 min read

I am of the opinion that the “NVIDIA model” has only 3 fully connected layers and not 4 as you have indicated in the diagram.

1164 is the shape of the flattened conv layer, so I don’t think we actually need another flattened layer of size 1164.

What do you think?

Deborah Digges

Software Engineer, writer, and artist.

Learning human driving behavior using NVIDIA’s neural network model and image augmentation.
61
4

Vivek Yadav

More from Deborah Digges

Software Engineer, writer, and artist.

More From Medium

A Deep Dive Into GitHub Actions

Deborah Digges in Better Programming

Deploy Your Gatsby Site With GitHub Actions

Deborah Digges in Better Programming

Delving Into Docker Container Actions

Deborah Digges in Better Programming

Navigating the GitHub Marketplace

Deborah Digges in Better Programming

Gatsby Up & Running: Creating a CD Pipeline

Deborah Digges in JavaScript in Plain English

From Jekyll to Gatsby: 7 Simple Steps

Deborah Digges in JavaScript in Plain English

12 Things I Stole From People More Successful Than Me

Vincent Carlos in Mind Cafe

Ryan Holiday’s 100 Very Short Rules for a Better Life

Ryan Holiday in Forge

About

Help

Legal

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store