ml-jku / chef Goto Github PK
View Code? Open in Web Editor NEWLicense: MIT License
License: MIT License
Hi, in the paper it is mentioned that two fully connected layers are used on top of the ResNets ("We utilize a ResNet-10 backbone architecture as proposed in Guo et al. (2019). The residual blocks have 64, 128, 256, 512, 4000, and 1000 units, where the latter two are fully connected ReLU layers"). But lines 78 and 81 in pretrain.py show that actually 3 fully connected layers are used.
How many fully connected layers were used and with which size ? and if the answer is 3, do you know how crucial is this 3rd huge (~100M parameters) layer to get "more hierarchical" features and get representation fusion to work as shown in the paper (ensemble outperforms all single layers)?
Thanks in advance.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.