dt42 / squeezenet_demo Goto Github PK
View Code? Open in Web Editor NEWLicense: GNU General Public License v3.0
License: GNU General Public License v3.0
Hello sir,
I tried to run the file squeezenet_demo.py but i encountered some error about import. Would you mind telling me how to install simdat.core because i cant find anywhere in your code.
Also i didnt see you mention anywhere about the place you put your labels file of your training data. Can you tell me how you did it also.
Thank a lot man !
On line 47 of model.py you have:
merge2 = merge(
[fire3_expand1, fire3_expand2], mode='concat', concat_axis=1)
I believe this should be:
merge3 = merge(
[fire3_expand1, fire3_expand2], mode='concat', concat_axis=1)
since there already exists a merge2 layer on line 35. Renaming it to merge3 should reduce ambiguity.
Are there keras weights for sqeezenet pertained on imageNet?
I guess that you are willing to share the source code, so I file this bug. A FOSS license will empower everyone to reproduce, distribute, or create derivative works from your work.
For more details, you can refer to the "What happens if I don't choose a license" section of this page: https://help.github.com/articles/open-source-licensing/
Hi, thanks for your work here. Are you planning on training this on Imagenet and releasing the weights ? I'm considering doing this on my end (and have access to Titan X gpus). Unfortunately the Squeezenet paper doesn't contain all the information needed, e.g. the validation split used, the data augmentation, etc.
Hi!
How can I solve the problem?
from simdat.core import dp_tools
ImportError: No module named 'simdat'
Thank you!
merge_i = Concatenate(axis=1)(a,b)
otherwise, it's half done.
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.