GitHub - metzzo/deephumor: DeepHumor tries to find out whether Deep Neural Networks are capable of understanding human humor by learning Gary Larson's cartoons. This diploma thesis consists of pre-processing an existing collection of more than 2000 cartoons, training multiple convolutional neural networks to understand the visual component and also training multiple recurrent neural network to detect punch lines in the text. A final classifier is used to merge the results. Additionally a detailed analysis regarding different configurations and an evaluation of the performance is included.

metzzo / deephumor Public

Notifications You must be signed in to change notification settings
Fork 0
Star 3

DeepHumor tries to find out whether Deep Neural Networks are capable of understanding human humor by learning Gary Larson's cartoons. This diploma thesis consists of pre-processing an existing collection of more than 2000 cartoons, training multiple convolutional neural networks to understand the visual component and also training multiple recur…

3 stars 0 forks Branches Tags Activity

Star

Notifications

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 348 Commits
.idea/runConfigurations		.idea/runConfigurations
annotator		annotator
documentation		documentation
final_evaluation		final_evaluation
final_models		final_models
good_models		good_models
pipeline		pipeline
resources		resources
rnn		rnn
.gitignore		.gitignore
.gitmodules		.gitmodules
DeepHumor_Thesis.pdf		DeepHumor_Thesis.pdf
Makefile		Makefile
README		README
pytest.ini		pytest.ini
requirements.txt		requirements.txt

Repository files navigation

# DeepHumor

## Preprocessor
Install the requirements using make install

Run tests using make test

Make sure to have Tesseract installed for OCR.

Using Python 3.6 (recommended virtualenv)


Or use Anaconda:

conda config --add channels conda-forge
conda config --add channels phygbu

conda activate C:\Users\rfischer\Miniconda3\envs\DeepHumor


## Folders

/rnn contains the experiments related to the text based models
/pipeline contains the experiments related to the CNN based models
/documentation contains the documentation assets
/annotator contains the annotator app written to annotate the cartoons