Is it possible to prompt this model with two or more texts for each image and get masks for each? Something like this inputs = processor(images=images, text=["cat", "dog"], return_tensors="pt").to(device)?
Russian trains is here: https://rasp.yandex.ru/map/trains/
Sakharov had some insight into the implications
Is it possible to prompt this model with two or more texts for each image and get masks for each? Something like this inputs = processor(images=images, text=["cat", "dog"], return_tensors="pt").to(device)?
Russian trains is here: https://rasp.yandex.ru/map/trains/
Sakharov had some insight into the implications