Shot Type Classification Package
Project description
Plugin package: Shot Type Classification
This package includes all methods to classify a given shot/or image sequence in one of the categories Extreme Long Shot (ELS), Long Shot (LS), Medium Shot (MS) or Close-Up Shot (CU).
Package Description
PDF format: vhh_stc_pdf
HTML format (only usable if repository is available in local storage): vhh_stc_html
Quick Setup
This package includes a setup.py script and a requirements.txt file which are needed to install this package for custom applications. The following instructions have to be done to used this library in your own application:
Requirements:
- Ubuntu 18.04 LTS
- CUDA 10.1 + cuDNN
- python version 3.6.x
Create a virtual environment:
- create a folder to a specified path (e.g. /xxx/vhh_stc/)
- python3 -m venv /xxx/vhh_stc/
Activate the environment:
- source /xxx/vhh_stc/bin/activate
Checkout vhh_stc repository to a specified folder:
- git clone https://github.com/dahe-cvl/vhh_stc
Install the stc package and all dependencies:
- Update pip and setuptools (tested using pip==20.2.3 and setuptools==50.3.0)
- Install the Wheel package:
pip install wheel
- change to the root directory of the repository (includes setup.py)
python setup.py bdist_wheel
- The aforementioned command should create a /dist directory containing a wheel. Install the package using
python -m pip install dist/xxx.whl
NOTE: You can check the success of the installation by using the commend pip list. This command should give you a list with all installed python packages and it should include vhh-stc.
Install PyTorch :
Install a Version of PyTorch depending on your setup. Consult the PyTorch website for detailed instructions.
Setup environment variables:
- source /data/dhelm/python_virtenv/vhh_sbd_env/bin/activate
- export CUDA_VISIBLE_DEVICES=1
- export PYTHONPATH=$PYTHONPATH:/XXX/vhh_stc/:/XXX/vhh_stc/Develop/:/XXX/vhh_stc/Demo/
Run demo script
- change to root directory of the repository
- python Demo/vhh_stc_run_on_single_video.py
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file vhh_stc-1.0.0.tar.gz
.
File metadata
- Download URL: vhh_stc-1.0.0.tar.gz
- Upload date:
- Size: 11.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.24.0 setuptools/50.3.0 requests-toolbelt/0.9.1 tqdm/4.50.2 CPython/3.6.5
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 |
7e799b2437310526828bff75358c28f1891b39f6c9829be98fa9054c8a6431b1
|
|
MD5 |
b1f10e6f0ee788271f3e4c6cc4509eb2
|
|
BLAKE2b-256 |
61cca8a8f6c598c878ba05f8ab9f145cbc8c93f6263968ee87f7098796a57f8e
|
File details
Details for the file vhh_stc-1.0.0-py3-none-any.whl
.
File metadata
- Download URL: vhh_stc-1.0.0-py3-none-any.whl
- Upload date:
- Size: 25.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.24.0 setuptools/50.3.0 requests-toolbelt/0.9.1 tqdm/4.50.2 CPython/3.6.5
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 |
df97e39b9c1ffacc20a3779cd477f88d7483355a9d4662077cdfaaaa2027c319
|
|
MD5 |
2b14da23f20d6d73e7cace57b5bc8a8e
|
|
BLAKE2b-256 |
6dc765a3b7204f098a90d442e5a63e4bd35bd6d23af315ec2e5eb7b21d8fa90d
|