Captions an image by labeling every object the model detects is present within the image.
For details see https://deepai.org/machine-learning-model/densecap
Nvidia-Docker is recommended but not required to run this image.
cp YOUR_IMAGE_FILE in1 nvidia-docker run --rm -i -v `pwd`:/shared deepaiorg/densecap
Your output is now in out1, and the format is .json
Docker Pull Command