Video Inference - TypeError: process_vision_info() got an unexpected keyword argument 'return_video_kwargs'

#2
by hmanju - opened
messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "video",
                "video": "file:///path/to/video1.mp4", #added local file path for a video here
                "max_pixels": 360 * 420,
                "fps": 1.0,
            },
            {"type": "text", "text": "Describe this video."},
        ],
    }
]


#In Qwen 2.5 VL, frame rate information is also input into the model to align with absolute time.
# Preparation for inference
text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs, video_kwargs = process_vision_info(messages, return_video_kwargs=True)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    fps=fps,
    padding=True,
    return_tensors="pt",
    **video_kwargs,
)
inputs = inputs.to("cuda")

# Inference
generated_ids = model.generate(**inputs, max_new_tokens=128)
generated_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)

TypeError                                 Traceback (most recent call last)
/tmp/ipykernel_213370/404839378.py in <module>
     34     messages, tokenize=False, add_generation_prompt=True
     35 )
---> 36 image_inputs, video_inputs, video_kwargs = process_vision_info(messages, return_video_kwargs=True)
     37 inputs = processor(
     38     text=[text],

TypeError: process_vision_info() got an unexpected keyword argument 'return_video_kwargs'

Same here with the video example, but I had success just reusing the image example (which includes video params already) and changing the content from image to video.

something like

messages = [
    {
        "role": "user",
        "content": [
            {"type": "video", "video": "file:///path/to/video1.mp4"}
            {"type": "text", "text": "Describe this video."},
        ]
    }
]

text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")

# etc

There's also far more detailed "cookbooks" on their github, including for video.

Sign up or log in to comment