Image Captioning in Human-like Manner

Requirements

Please download, unzip, and place the images in: coco/images/
Please download and place the annotations in: coco/annotations/
python3 -m venv venv
source venv/bin/activate
pip3 install -r requirements.txt
jupyter lab
Experiment and attempt to load all images and captions with the pycocotools API library. Use pycocoDemo notebook for reference.

Name		Name	Last commit message	Last commit date
Latest commit History 30 Commits
flickr		flickr
pycocoevalcap		pycocoevalcap
.gitignore		.gitignore
00. pycocoDemo.ipynb		00. pycocoDemo.ipynb
01. coco_descriptions.ipynb		01. coco_descriptions.ipynb
02. train_image_extracted.ipynb		02. train_image_extracted.ipynb
03. Dataset Information.ipynb		03. Dataset Information.ipynb
04. Model.ipynb		04. Model.ipynb
05. Training.ipynb		05. Training.ipynb
06. Inference.ipynb		06. Inference.ipynb
07. Validation.ipynb		07. Validation.ipynb
08. Performance Measure.ipynb		08. Performance Measure.ipynb
README.md		README.md
Stats.md		Stats.md
Visualization.ipynb		Visualization.ipynb
embedding_matrix.pkl		embedding_matrix.pkl
get_stanford_models.py		get_stanford_models.py
get_stanford_models.sh		get_stanford_models.sh
index_and_words.pkl		index_and_words.pkl
model.h5		model.h5
model.json		model.json
model_plot.png		model_plot.png
modified_inception.h5		modified_inception.h5
pycocoEvalCap.ipynb		pycocoEvalCap.ipynb
requirements.txt		requirements.txt