Deep-Representation-of-Visual-Descriptions

This is a direct implementation of the paper StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks by Han Zhang, Tao Xu, Hongsheng Li, Shaoting Zhang, Xiaogang Wang, Xiaolei Huang, Dimitris Metaxas.
Parts of the implementation has been taken from StackGAN repo of hanzhanggit

The aim of this project is about simplifying the concept of Attention mechanism in using it for generating images given some visual description for the images to be genrated using the modern tools.

Documentation

Dependencies

Python 3.0
Pytorch
torchfile
nltk- (‘punkt’)
pandas
scikit-learn
python-dateutil
easydict
shutil
Matplotlib
Scikit-Image(skimage)

Data Download

Repo :

MS-COCO This consists of class_names = ['BG', 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light', 'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow', 'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', 'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', 'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear', 'hair drier', 'toothbrush']
CUB_200_2011