GithubHelp home page GithubHelp logo

Comments (12)

yfor1008 avatar yfor1008 commented on June 4, 2024 1

@jiangjingyao "--model /path/to/VGGnet_fast_rcnn_iter_70000.ckpt" need a space between "--model" and the "/path/to/VGGnet_fast_rcnn_iter_70000.ckpt"

from faster-rcnn_tf.

smallcorgi avatar smallcorgi commented on June 4, 2024

Hello @philokey
I have already uploaded the model. You can get model in Readme!

from faster-rcnn_tf.

philokey avatar philokey commented on June 4, 2024

Thank you very much!

from faster-rcnn_tf.

kaishijeng avatar kaishijeng commented on June 4, 2024

Can you upload network definition, demo_net (VGGnet_test) so that demo.py can be run?

Thanks

from faster-rcnn_tf.

smallcorgi avatar smallcorgi commented on June 4, 2024

Hi @kaishijeng,
I updated the demo.py. You can download the new demo.py and try it again.

from faster-rcnn_tf.

kaishijeng avatar kaishijeng commented on June 4, 2024

demo.py works OK now

Thanks,

from faster-rcnn_tf.

shuye-cheung avatar shuye-cheung commented on June 4, 2024

Hi, @smallcorgi @kaishijeng
./tools/demo.py works. However, I find the results (bounding boxes and corresponding scores) is not consistent when I run it twice or more. Do you encounter this problem? or any idea to fix it?

Thanks

from faster-rcnn_tf.

smallcorgi avatar smallcorgi commented on June 4, 2024

Hi @shuye-cheung ,
I found the problems in drop out layer.
If i don't use drop out in fc6 & fc7, the result will be the same.
You can try to comment out the drop out layer in /lib/networks/VGGnet_test.py.

Thanks,

from faster-rcnn_tf.

jiangjingyao avatar jiangjingyao commented on June 4, 2024

Hi @smallcorgi @shuye-cheung @kaishijeng ,I have already downloaded VGG_imagenet.npy and put it in ./models/ ,but I failed to run demo.py. my command is "./tools/demo.py --model ./models/VGG_imagenet.npy".Can you give me some suggestions ?

Thanks

from faster-rcnn_tf.

shuye-cheung avatar shuye-cheung commented on June 4, 2024

Hi, @smallcorgi ,
The problem is solved by commenting out the drop out layer.

Thanks for your prompt advise~

from faster-rcnn_tf.

shuye-cheung avatar shuye-cheung commented on June 4, 2024

Hi, @jiangjingyao I think you misunderstand the usage of VGG_imagenet.npy. VGG_imagenet.npy is a pre-trained model for training a new model.

If you want to run ./tools/demo.py, you should try
./tools/demo.py --model /path/to/VGGnet_fast_rcnn_iter_70000.ckpt

(VGGnet_fast_rcnn_iter_70000.ckpt is provide in readme)

from faster-rcnn_tf.

jiangjingyao avatar jiangjingyao commented on June 4, 2024

Thanks for your help @shuye-cheung ,I still can't run it .There is an erro in line 24," ./tools/demo.py: line 24: An unexpected syntax errors near`(' ".Do you encounter this problem? And how do you solve it?

Thanks

from faster-rcnn_tf.

Related Issues (20)

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.