tika-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "ASF GitHub Bot (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (TIKA-2322) Video labeling using existing ObjectRecognition
Date Mon, 01 May 2017 14:25:04 GMT

    [ https://issues.apache.org/jira/browse/TIKA-2322?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15990864#comment-15990864
] 

ASF GitHub Bot commented on TIKA-2322:
--------------------------------------

chrismattmann commented on a change in pull request #175: TIKA-2322: update dockerfile
URL: https://github.com/apache/tika/pull/175#discussion_r114130786
 
 

 ##########
 File path: tika-parsers/src/main/resources/org/apache/tika/parser/recognition/tf/InceptionVideoRestDockerfile
 ##########
 @@ -70,24 +67,24 @@ RUN \
   pip install --upgrade https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-1.0.1-cp27-none-linux_x86_64.whl
--ignore-installed  && \
   pip install flask requests
 
-# Get the TF-slim dependencies 
+# Get the TF-slim dependencies
 # Downloading from a specific commit for future compatibility
-RUN wget https://github.com/tensorflow/models/archive/c15fada28113eca32dc98d6e3bec4755d0d5b4c2.zip

-
-RUN unzip c15fada28113eca32dc98d6e3bec4755d0d5b4c2.zip 
+RUN wget https://github.com/tensorflow/models/archive/c15fada28113eca32dc98d6e3bec4755d0d5b4c2.zip
+RUN unzip c15fada28113eca32dc98d6e3bec4755d0d5b4c2.zip
 
 RUN \
   wget https://raw.githubusercontent.com/smadha/tika/TIKA-2322/tika-parsers/src/main/resources/org/apache/tika/parser/recognition/tf/inceptionapi.py
-O /usr/bin/inceptionapi.py && \
   wget https://raw.githubusercontent.com/smadha/tika/TIKA-2322/tika-parsers/src/main/resources/org/apache/tika/parser/recognition/tf/video_util.py
-O /usr/bin/video_util.py && \
   chmod +x /usr/bin/inceptionapi.py && \
   chmod +x /usr/bin/video_util.py
-  
-# clean up cache, so we can publish smaller image to hub
+
+# clean up cache + delete src files, so we can publish smaller image to hub
 RUN apt-get clean
+RUN rm -rf /usr/local/src
 
 Review comment:
   makes sense
 
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


> Video labeling using existing ObjectRecognition
> -----------------------------------------------
>
>                 Key: TIKA-2322
>                 URL: https://issues.apache.org/jira/browse/TIKA-2322
>             Project: Tika
>          Issue Type: Improvement
>          Components: parser
>            Reporter: Madhav Sharan
>            Assignee: Chris A. Mattmann
>              Labels: memex
>             Fix For: 1.15
>
>
> Currently TIKA supports ObjectRecognition in Images. I am proposing to extend this to
support videos. 
> Idea is -
> 1. Extract frames from video and run IncV3 to get labels for these frames. 
> 2. We average confidence scores of same labels for each frame. 
> 3. Return results in sorted order of confidence score. 
> I am writing code for different modes of frame extractions -
> 1. Extract center image.
> 2. Extract frames after every fixed interval.
> 3. Extract N frames equally divided across video.
> We used this approach in [0]. Code in [1]
> [0] https://github.com/USCDataScience/hadoop-pot
> [1] https://github.com/USCDataScience/video-recognition



--
This message was sent by Atlassian JIRA
(v6.3.15#6346)

Mime
View raw message