Method inference

visual_chatgpt.py:791–799

(self, inputs)

                         "like: what is the background color of the last image, how many cats in this figure, what is in this figure. "
                         "The input to this tool should be a comma separated string of two, representing the image_path and the question")
    def inference(self, inputs):
        image_path, question = inputs.split(",")[0], ','.join(inputs.split(',')[1:])
        raw_image = Image.open(image_path).convert('RGB')
        inputs = self.processor(raw_image, question, return_tensors="pt").to(self.device, self.torch_dtype)
        out = self.model.generate(**inputs)
        answer = self.processor.decode(out[0], skip_special_tokens=True)
        print(f"\nProcessed VisualQuestionAnswering, Input Image: {image_path}, Input Question: {question}, "
              f"Output Answer: {answer}")
        return answer


class Segmenting: