GithubHelp home page GithubHelp logo

zhujiagang / dtpp Goto Github PK

View Code? Open in Web Editor NEW
71.0 71.0 22.0 459.63 MB

Deep networks with Temporal Pyramid Pooling. The official implementation for "End-to-end Video-level Representation Learning for Action Recognition, ICPR 2018."

License: BSD 2-Clause "Simplified" License

Python 94.98% Shell 2.91% MATLAB 2.11%

dtpp's People

Contributors

zhujiagang 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  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

dtpp's Issues

Reproducing the inference

I'm currently trying to reproduce the inference in arbitrary videos of the HMDB51 dataset by using the pretrained weights.

So far, I have:

  1. Compiled OpenCV with the contrib module and cuda support
  2. Successfully compiled caffe (caffe-tpp-net) with CUDA and python support
  3. Set up the PYTHONPATH environment variable so python2.7 may find the compiled modules
  4. Downloaded the pretrained weights with get_init_models.sh and get_kinetics_pretraining_models.sh

Since README.md doesn't mention how to perform inference, I read README_old.md and found that there is a script tools/eval_net.py for that purpose. So I ran:

python tools/eval_net.py hmdb51 1 rgb /var/datasets/hmdb51/ models/hmdb51/flow_tpp_delete_dropout_deploy.prototxt ./init_models/hmdb51_split_1_tsn_flow_reference_bn_inception.caffemodel

But, after a ton of messages, that gave me the following error:

Traceback (most recent call last):
File "tools/eval_net.py", line 125, in
video_scores = map(eval_video, eval_video_list)
File "tools/eval_net.py", line 69, in eval_video
video_frame_path = f_info[0][vid]
KeyError: '20060723sfjffbumblebeesuitman_run_f_cm_np2_ri_med_1'

The path to the dataset is correct, and I have unpacked all rar files from the HMDB dataset. The README_old.md file mentions a script scripts/extract_optical_flow.sh for preprocessing the video files, but in the master branch, this script doesn't exist.

So, are there any further steps necessary for reproducing inference?

No module named 'pyparrots

in pyActionRecog, action_parrots.py has ''import pyparrots.dnn as dnn'', When I run, ‘’No module named 'pyparrots'‘’ appears.How do I get pyparrots?It would be my pleasure if you could answer for me.Thanks
PS:If you can speak Chinese, we can use Chinese to communicate.

fatal: no submodule mapping found in .gitmodules for path 'lib/caffe-tpp-net-python'

Hello,

Thank you for publishing the code for your work!
I'm trying to reproduce it, but had an issue. When trying to clone the DTPP repository, I get the following error:

fatal: no submodule mapping found in .gitmodules for path 'lib/caffe-tpp-net-python'

Browsing the lib folder on github, I see that the caffe-tpp-net-python is not linked to any repository. Perhaps there was an error in the declaration of this submodule?

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.