Skip to content
This repository was archived by the owner on Jul 1, 2025. It is now read-only.

Fix broken headings in Markdown files #3

Open
bryant1410 wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Fix broken headings in Markdown files #3

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions Readme.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,21 +1,21 @@
#NeuralTalkAnimator
# NeuralTalkAnimator

The NeuralTalkAnimator is a python helper, that creates captioned videos with [NeuralTalk](https://github.com/karpathy/neuraltalk).
It takes a folder with videos and returns a folder with captuned videos back.

##Instruction
## Instruction
0) Download this repo
1) Download [VGG_ILSVRC_16_layers.caffemodel](http://www.robots.ox.ac.uk/~vgg/software/very_deep/caffe/VGG_ILSVRC_16_layers.caffemodel) and place it in the `python_features` folder
2) Download [coco_cnn_lstm_v2.p](https://cs.stanford.edu/people/karpathy/neuraltalk/coco_cnn_lstm_v2.zip) and place it in the `cv` folder
3) Put Your Videos in the the `videos` folder
4) `python extract.py --captionfrequency 30`
5) Get videos with generated captions at `videos/processed`

##Requirements
## Requirements
- PIL
- FFMPEG

##Demo
## Demo

[https://www.youtube.com/watch?v=Nrh5Tpze79I](https://www.youtube.com/watch?v=Nrh5Tpze79I)
[https://www.youtube.com/watch?v=OTcQCM9daOU](https://www.youtube.com/watch?v=OTcQCM9daOU)
Expand All @@ -24,7 +24,7 @@ It takes a folder with videos and returns a folder with captuned videos back.
![captions](https://i.imgur.com/FH4aTUt.jpg)


#NeuralTalk
# NeuralTalk

This project contains *Python+numpy* source code for learning **Multimodal Recurrent Neural Networks** that describe images with sentences.

Expand Down