Update README.md

README.md

@@ -89,17 +89,18 @@ pip install qwen-vl-utils
 Here we show a code snippet to show you how to use the chat model with `transformers` and `qwen_vl_utils`:
 
 ```python
-
 from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
 from qwen_vl_utils import process_vision_info
 
 # default: Load the model on the available device(s)
-model = Qwen2VLForConditionalGeneration.from_pretrained("Qwen/Qwen2-VL-2B-Instruct", device_map="auto")
+model = Qwen2VLForConditionalGeneration.from_pretrained(
+    "Qwen/Qwen2-VL-2B-Instruct", torch_dtype="auto", device_map="auto"
+)
 
 # We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
 # model = Qwen2VLForConditionalGeneration.from_pretrained(
-#     "Qwen/Qwen2-VL-2B-Instruct", 
-#     torch_dtype=torch.bfloat16, 
+#     "Qwen/Qwen2-VL-2B-Instruct",
+#     torch_dtype=torch.bfloat16,
 #     attn_implementation="flash_attention_2",
 #     device_map="auto",
 # )
@@ -112,27 +113,47 @@ processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-2B-Instruct")
 # max_pixels = 1280*28*28
 # processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-2B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels)
 
-# default processer
-processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-2B-Instruct")
-
-messages = [{"role": "user", "content": [{"type": "image", "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"}, {"type": "text", "text": "Describe this image."}]}]
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "image",
+                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
+            },
+            {"type": "text", "text": "Describe this image."},
+        ],
+    }
+]
 
 # Preparation for inference
-text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+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 = processor(
+    text=[text],
+    images=image_inputs,
+    videos=video_inputs,
+    padding=True,
+    return_tensors="pt",
+)
+inputs = inputs.to("cuda")
 
 # Inference: Generation of the output
 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)
+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)
 ```
 <details>
 <summary>Without qwen_vl_utils</summary>
 
 ```python
-
 from PIL import Image
 import requests
 import torch
@@ -141,7 +162,9 @@ from typing import Dict
 from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
 
 # Load the model in half-precision on the available device(s)
-model = Qwen2VLForConditionalGeneration.from_pretrained("Qwen/Qwen2-VL-2B-Instruct", device_map="auto")
+model = Qwen2VLForConditionalGeneration.from_pretrained(
+    "Qwen/Qwen2-VL-2B-Instruct", torch_dtype="auto", device_map="auto"
+)
 processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-2B-Instruct")
 
 # Image
@@ -150,16 +173,13 @@ image = Image.open(requests.get(url, stream=True).raw)
 
 conversation = [
     {
-        "role":"user",
-        "content":[
+        "role": "user",
+        "content": [
             {
-                "type":"image",
+                "type": "image",
             },
-            {
-                "type":"text",
-                "text":"Describe this image."
-            }
-        ]
+            {"type": "text", "text": "Describe this image."},
+        ],
     }
 ]
 
@@ -168,13 +188,20 @@ conversation = [
 text_prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)
 # Excepted output: '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\n<|vision_start|><|image_pad|><|vision_end|>Describe this image.<|im_end|>\n<|im_start|>assistant\n'
 
-inputs = processor(text=[text_prompt], images=[image], padding=True, return_tensors="pt")
-inputs = inputs.to('cuda')
+inputs = processor(
+    text=[text_prompt], images=[image], padding=True, return_tensors="pt"
+)
+inputs = inputs.to("cuda")
 
 # Inference: Generation of the output
 output_ids = model.generate(**inputs, max_new_tokens=128)
-generated_ids = [output_ids[len(input_ids):] for input_ids, output_ids in zip(inputs.input_ids, output_ids)]
-output_text = processor.batch_decode(generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True)
+generated_ids = [
+    output_ids[len(input_ids) :]
+    for input_ids, output_ids in zip(inputs.input_ids, output_ids)
+]
+output_text = processor.batch_decode(
+    generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True
+)
 print(output_text)
 ```
 </details>
@@ -184,17 +211,39 @@ print(output_text)
 
 ```python
 # Messages containing multiple images and a text query
-messages = [{"role": "user", "content": [{"type": "image", "image": "file:///path/to/image1.jpg"}, {"type": "image", "image": "file:///path/to/image2.jpg"}, {"type": "text", "text": "Identify the similarities between these images."}]}]
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "image", "image": "file:///path/to/image1.jpg"},
+            {"type": "image", "image": "file:///path/to/image2.jpg"},
+            {"type": "text", "text": "Identify the similarities between these images."},
+        ],
+    }
+]
 
 # Preparation for inference
-text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+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 = processor(
+    text=[text],
+    images=image_inputs,
+    videos=video_inputs,
+    padding=True,
+    return_tensors="pt",
+)
+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)
+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)
 ```
 </details>
@@ -203,21 +252,63 @@ print(output_text)
 <summary>Video inference</summary>
 
 ```python
-
 # Messages containing a images list as a video and a text query
-messages = [{"role": "user", "content": [{"type": "video", "video": ["file:///path/to/frame1.jpg", "file:///path/to/frame2.jpg", "file:///path/to/frame3.jpg", "file:///path/to/frame4.jpg"], 'fps': 1.0}, {"type": "text", "text": "Describe this video."}]}]
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "video",
+                "video": [
+                    "file:///path/to/frame1.jpg",
+                    "file:///path/to/frame2.jpg",
+                    "file:///path/to/frame3.jpg",
+                    "file:///path/to/frame4.jpg",
+                ],
+                "fps": 1.0,
+            },
+            {"type": "text", "text": "Describe this video."},
+        ],
+    }
+]
 # Messages containing a video and a text query
-messages = [{"role": "user", "content": [{"type": "video", "video": "file:///path/to/video1.mp4", 'max_pixels': 360*420, 'fps': 1.0}, {"type": "text", "text": "Describe this video."}]}]
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "video",
+                "video": "file:///path/to/video1.mp4",
+                "max_pixels": 360 * 420,
+                "fps": 1.0,
+            },
+            {"type": "text", "text": "Describe this video."},
+        ],
+    }
+]
 
 # Preparation for inference
-text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+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 = processor(
+    text=[text],
+    images=image_inputs,
+    videos=video_inputs,
+    padding=True,
+    return_tensors="pt",
+)
+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)
+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)
 ```
 </details>
@@ -226,22 +317,47 @@ print(output_text)
 <summary>Batch inference</summary>
 
 ```python
-
 # Sample messages for batch inference
-messages1 = [{"role": "user", "content": [{"type": "image", "image": "file:///path/to/image1.jpg"}, {"type": "image", "image": "file:///path/to/image2.jpg"}, {"type": "text", "text": "What are the common elements in these pictures?"}]}]
-messages2 = [{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Who are you?"}]
+messages1 = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "image", "image": "file:///path/to/image1.jpg"},
+            {"type": "image", "image": "file:///path/to/image2.jpg"},
+            {"type": "text", "text": "What are the common elements in these pictures?"},
+        ],
+    }
+]
+messages2 = [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": "Who are you?"},
+]
 # Combine messages for batch processing
 messages = [messages1, messages1]
 
 # Preparation for batch inference
-texts = [processor.apply_chat_template(msg, tokenize=False, add_generation_prompt=True) for msg in messages]
+texts = [
+    processor.apply_chat_template(msg, tokenize=False, add_generation_prompt=True)
+    for msg in messages
+]
 image_inputs, video_inputs = process_vision_info(messages)
-inputs = processor(text=texts, images=image_inputs, videos=video_inputs, padding=True, return_tensors="pt")
+inputs = processor(
+    text=texts,
+    images=image_inputs,
+    videos=video_inputs,
+    padding=True,
+    return_tensors="pt",
+)
+inputs = inputs.to("cuda")
 
 # Batch 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_texts = processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)
+generated_ids_trimmed = [
+    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
+]
+output_texts = processor.batch_decode(
+    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
+)
 print(output_texts)
 ```
 </details>
@@ -253,22 +369,46 @@ For input images, we support local files, base64, and URLs. For videos, we curre
 ```python
 # You can directly insert a local file path, a URL, or a base64-encoded image into the position where you want in the text.
 ## Local file path
-messages = [{"role": "user", "content": [{"type": "image", "image": "file:///path/to/your/image.jpg"}, {"type": "text", "text": "Describe this image."}]}]
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "image", "image": "file:///path/to/your/image.jpg"},
+            {"type": "text", "text": "Describe this image."},
+        ],
+    }
+]
 ## Image URL
-messages = [{"role": "user", "content": [{"type": "image", "image": "http://path/to/your/image.jpg"}, {"type": "text", "text": "Describe this image."}]}]
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "image", "image": "http://path/to/your/image.jpg"},
+            {"type": "text", "text": "Describe this image."},
+        ],
+    }
+]
 ## Base64 encoded image
-messages = [{"role": "user", "content": [{"type": "image", "image": "data:image;base64,/9j/..."}, {"type": "text", "text": "Describe this image."}]}]
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "image", "image": "data:image;base64,/9j/..."},
+            {"type": "text", "text": "Describe this image."},
+        ],
+    }
+]
 ```
 #### Image Resolution for performance boost
 
 The model supports a wide range of resolution inputs. By default, it uses the native resolution for input, but higher resolutions can enhance performance at the cost of more computation. Users can set the minimum and maximum number of pixels to achieve an optimal configuration for their needs, such as a token count range of 256-1280, to balance speed and memory usage.
 
 ```python
-
-min_pixels = 256*28*28
-max_pixels = 1280*28*28
-processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-2B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels)
-
+min_pixels = 256 * 28 * 28
+max_pixels = 1280 * 28 * 28
+processor = AutoProcessor.from_pretrained(
+    "Qwen/Qwen2-VL-2B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels
+)
 ```
 
 Besides, We provide two methods for fine-grained control over the image size input to the model:
@@ -279,21 +419,49 @@ Besides, We provide two methods for fine-grained control over the image size inp
 
 ```python
 # min_pixels and max_pixels
-messages = [{"role": "user", "content": [{"type": "image", "image": "file:///path/to/your/image.jpg", "resized_height": 280, "resized_width": 420}, {"type": "text", "text": "Describe this image."}]}]
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "image",
+                "image": "file:///path/to/your/image.jpg",
+                "resized_height": 280,
+                "resized_width": 420,
+            },
+            {"type": "text", "text": "Describe this image."},
+        ],
+    }
+]
 # resized_height and resized_width
-messages = [{"role": "user", "content": [{"type": "image", "image": "file:///path/to/your/image.jpg", "min_pixels": 50176, "max_pixels": 50176}, {"type": "text", "text": "Describe this image."}]}]
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "image",
+                "image": "file:///path/to/your/image.jpg",
+                "min_pixels": 50176,
+                "max_pixels": 50176,
+            },
+            {"type": "text", "text": "Describe this image."},
+        ],
+    }
+]
 ```
 
-**Limitations:**
+## Limitations
 
-1. Does not support audio extraction from videos.
-2. Limited to data available up until June 2023.
-3. Limited coverage of character/IP recognition.
-4. Complex instruction following capabilities need enhancement.
-5. Counting abilities, particularly in complex scenarios, require improvement.
-6. Handling of complex charts by the model still needs refinement.
-7. The model performs poorly in spatial relationship reasoning, especially in reasoning about object positions in a 3D space.
+While Qwen2-VL are applicable to a wide range of visual tasks, it is equally important to understand its limitations. Here are some known restrictions:
 
+1. Lack of Audio Support: The current model does **not comprehend audio information** within videos.
+2. Data timeliness: Our image dataset is **updated until June 2023**, and information subsequent to this date may not be covered.
+3. Constraints in Individuals and Intellectual Property (IP): The model's capacity to recognize specific individuals or IPs is limited, potentially failing to comprehensively cover all well-known personalities or brands.
+4. Limited Capacity for Complex Instruction: When faced with intricate multi-step instructions, the model's understanding and execution capabilities require enhancement.
+5. Insufficient Counting Accuracy: Particularly in complex scenes, the accuracy of object counting is not high, necessitating further improvements.
+6. Weak Spatial Reasoning Skills: Especially in 3D spaces, the model's inference of object positional relationships is inadequate, making it difficult to precisely judge the relative positions of objects.
+
+These limitations serve as ongoing directions for model optimization and improvement, and we are committed to continually enhancing the model's performance and scope of application.
 
 
 ## Citation
@@ -301,8 +469,16 @@ messages = [{"role": "user", "content": [{"type": "image", "image": "file:///pat
 If you find our work helpful, feel free to give us a cite.
 
 ```
-@article{qwen2vl,
-  title={Qwen2-VL Technical Report},
+@article{Qwen2-VL,
+  title={Qwen2-VL},
+  author={Qwen team},
   year={2024}
 }
+
+@article{Qwen-VL,
+  title={Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond},
+  author={Bai, Jinze and Bai, Shuai and Yang, Shusheng and Wang, Shijie and Tan, Sinan and Wang, Peng and Lin, Junyang and Zhou, Chang and Zhou, Jingren},
+  journal={arXiv preprint arXiv:2308.12966},
+  year={2023}
+}
 ```