Open in app
Jonathan Hui
17.1K Followers
About

Sign in

17.1K Followers
About
Open in app
Thank you for that great explanaion but there is some questions if you can clarify it more
4
1

Abdessamed Gori

Jonathan Hui

Jonathan Hui

May 8, 2018·1 min read

(1) No particular theoretical reason. A possible reason is the ground truth objects have scale closer to those layers and therefore we want more guesses.

(2) 38*38*4 + 19*19*6 + 10*10*6 + 5*5*6 + 3*3*4 + 1*1*4 = 8732

Written by

Jonathan Hui

Deep Learning

More from Jonathan Hui

Deep Learning

More From Medium

TensorFlow Automatic Differentiation (AutoDiff)

Jonathan Hui

TensorFlow Dataset & Data Preparation

Jonathan Hui

F is a second-order derivative.

Jonathan Hui

AI chips: FPGA

Jonathan Hui

TensorFlow Libraries and Extensions

Jonathan Hui

TensorFlow Eager Execution v.s. Graph (@tf.function)

Jonathan Hui

TensorFlow RNN models

Jonathan Hui

TensorFlow Keras Preprocessing Layers & Dataset Performance

Jonathan Hui

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