search

yangxuntu / SGAE

220 stars 48 forks source link

Can we evaluate on RAW images outside the coco dataset.(eval_mem.py) #5

Open ravissj4 opened 5 years ago

yangxuntu commented 5 years ago

You need to extract the features as in the paper: Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome, then you can write a similar file to generate captions for raw images outside the coco dataset.

ravissj4 commented 5 years ago

You need to extract the features as in the paper: Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome, then you can write a similar file to generate captions for raw images outside the coco dataset.

Can the DataLoaderRaw be used for this above purpose ? Sorry, if this is a very trivial question, I'm very new to this.

yangxuntu commented 5 years ago

This part is written by ruotian luo, you can go to his github to learn how to use.