Giter Site home page Giter Site logo

vgg16-pretrained-c's People

Contributors

idmippm avatar zfturbo avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar

vgg16-pretrained-c's Issues

How to understand is my predict true ?

Hi @ZFTurbo

When I run predict predict code it return some number I think they are probability. But I exactly didn't understand is it correct or not ? Because some values in result.txt bigger than 100.

What the numbers in output file means?

Hi, I'm quite new to machine learning and don't understand the numbers in results output file (results.txt). Are they just probabilities of what the model predicts? If so what is it predicting, there is no text next to these numbers that classify them. Usually an inference of a model gives a result like: cat 78%, dog 17% car 5%. How can i get such an output?

Can't get the result successfully

Hi, thank you for your code.
But I have trouble when running your code
Can you give me some help?

Problem1

As shown in the picture, I entered the command in the yellow box according to your method, but an error occurred, as shown in the red box.
After a simple test, I think there is a problem when reading cat.txt, so there will be some errors,
but I don't know how to fix it?
Although I can get the file "results.txt", but the file is completely empty, there is no result in the results.txt file
Can you help me with this problem?
Thank you very much!

Number of threads

Hi, if I increase the number of threads the inference time increases (and it should decrease).
I'm reviewing the code and I don't find the reason. Do you know why this happens?

Thanks.

Can't reproduce the same results

Hi. I've been trying to reproduce your example with the cat.txt file. However, the resulting number from the dense layers is 7, which is equivalent to the "cock" class.

I've used the weights that you've shared.

Not only that, but when I try to check the results between your "values_checker.py" file and the original keras vgg16 (imagenet), the results are also entirely different.

I'm fairly certain I'm using the files correctly, though that only makes me wonder even more about what the heck is going on.

Could you run the files and share the results with me? I'd be much grateful.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.