search

chihyaoma / cyclical-visual-captioning

PyTorch code for: Learning to Generate Grounded Visual Captions without Localization Supervision
https://arxiv.org/abs/1906.00283
Other
44 stars 3 forks source link

inference on own video #1

Open nikky4D opened 4 years ago

nikky4D commented 4 years ago

Hi,

I am writing code to apply video captioning models on a single input video. Can you show me how to apply your model on a single input video or single input image? Is there a demo I can follow for the step by step approach? I'm new to this area and trying to understand what is required for testing video captioning models.

nikky4D commented 4 years ago

Hi Again,

Would you have a description of how to go about running this on my own video/set of videos for only inference?

Thanks