readme

README.md

@@ -15,7 +15,7 @@ base_model: microsoft/Phi-4-mini-instruct
 # Model Card for LLaVA_MORE-phi_4-finetuning
 
 <div align="center">
-  <img src="https://huggingface.co/aimagelab/LLaVA_MORE-phi_4-finetuning/resolve/main/images/image_no_back.png" width="200" height="200">
+  <!-- <img src="https://github.com/aimagelab/LLaVA-MORE/blob/main/images/image_no_back.png" width="200" height="200"> -->
   <h1>  🔥 LLaVA-MORE 🔥
     
  A Comparative Study of LLMs and Visual Backbones <br>for Enhanced Visual Instruction Tuning
@@ -28,6 +28,18 @@ LLaVA-MORE integrates recent language models with diverse visual backbones. It e
 
 It is designed for multimodal reasoning, generation, and instruction following, and provides insights into the design of more effective MLLMs.
 
+## Citation
+If you make use of our work, please cite our paper:
+
+```bibtex
+@inproceedings{cocchi2025llava,
+      title={{LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning}},
+      author={Cocchi, Federico and Moratelli, Nicholas and Caffagni, Davide and Sarto, Sara and Baraldi, Lorenzo and Cornia, Marcella and Cucchiara, Rita},
+      booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops},
+      year={2025}
+}
+```
+
 ## Model Details
 
 ### Model Description
@@ -94,113 +106,6 @@ export TOKENIZER_PATH=$model_path
 python -u src/llava/eval/run_llava.py --model-path $model_path --model-architecture $model_architecture --conv-mode $conversation
 ```
 
-**Direct Python Inference Example:**
-
-This example demonstrates how to load the model and perform a simple inference. Note that the image preprocessing part, essential for LLaVA-style models, is included for a complete example.
-
-```python
-import numpy as np
-import torch
-import torchvision.transforms as T
-from PIL import Image
-from torchvision.transforms.functional import InterpolationMode
-from transformers import AutoModel, AutoTokenizer
-
-IMAGENET_MEAN = (0.485, 0.456, 0.406)
-IMAGENET_STD = (0.229, 0.224, 0.406)
-
-def build_transform(input_size):
-    """Builds the image transformation pipeline."""
-    MEAN, STD = IMAGENET_MEAN, IMAGENET_STD
-    transform = T.Compose([
-        T.Lambda(lambda img: img.convert('RGB') if img.mode != 'RGB' else img),
-        T.Resize((input_size, input_size), interpolation=InterpolationMode.BICUBIC),
-        T.ToTensor(),
-        T.Normalize(mean=MEAN, std=STD)
-    ])
-    return transform
-
-def find_closest_aspect_ratio(aspect_ratio, target_ratios, width, height, image_size):
-    """Finds the target aspect ratio closest to the image's aspect ratio."""
-    best_ratio_diff = float('inf')
-    best_ratio = (1, 1)
-    area = width * height
-    for ratio in target_ratios:
-        target_aspect_ratio = ratio[0] / ratio[1]
-        ratio_diff = abs(aspect_ratio - target_aspect_ratio)
-        if ratio_diff < best_ratio_diff:
-            best_ratio_diff = ratio_diff
-            best_ratio = ratio
-        elif ratio_diff == best_ratio_diff:
-            if area > 0.5 * image_size * image_size * ratio[0] * ratio[1]:
-                best_ratio = ratio
-    return best_ratio
-
-def dynamic_preprocess(image, min_num=1, max_num=12, image_size=448, use_thumbnail=False):
-    """Dynamically preprocesses images for multi-scale input."""
-    orig_width, orig_height = image.size
-    aspect_ratio = orig_width / orig_height
-
-    target_ratios = set(
-        (i, j) for n in range(min_num, max_num + 1) for i in range(1, n + 1) for j in range(1, n + 1) if
-        i * j <= max_num and i * j >= min_num)
-    target_ratios = sorted(target_ratios, key=lambda x: x[0] * x[1])
-
-    target_aspect_ratio = find_closest_aspect_ratio(
-        aspect_ratio, target_ratios, orig_width, orig_height, image_size)
-
-    target_width = image_size * target_aspect_ratio[0]
-    target_height = image_size * target_aspect_ratio[1]
-    blocks = target_aspect_ratio[0] * target_aspect_ratio[1]
-
-    resized_img = image.resize((target_width, target_height))
-    processed_images = []
-    for i in range(blocks):
-        box = (
-            (i % (target_width // image_size)) * image_size,
-            (i // (target_width // image_size)) * image_size,
-            ((i % (target_width // image_size)) + 1) * image_size,
-            ((i // (target_width // image_size)) + 1) * image_size
-        )
-        split_img = resized_img.crop(box)
-        processed_images.append(split_img)
-    assert len(processed_images) == blocks
-    if use_thumbnail and len(processed_images) != 1:
-        thumbnail_img = image.resize((image_size, image_size))
-        processed_images.append(thumbnail_img)
-    return processed_images
-
-def load_image(image_path, input_size=448, max_num=12):
-    """Loads and preprocesses an image."""
-    image = Image.open(image_path).convert('RGB')
-    transform = build_transform(input_size=input_size)
-    images = dynamic_preprocess(image, image_size=input_size, use_thumbnail=True, max_num=max_num)
-    pixel_values = [transform(image) for image in images]
-    pixel_values = torch.stack(pixel_values)
-    return pixel_values
-
-# Load model and tokenizer
-model_id = "aimagelab/LLaVA_MORE-phi_4-finetuning" # This specific model
-model = AutoModel.from_pretrained(
-    model_id,
-    torch_dtype=torch.bfloat16, # Or torch.float16 if bfloat16 is not supported by your GPU
-    low_cpu_mem_usage=True,
-    trust_remote_code=True
-).eval().cuda() # Move model to GPU
-tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True, use_fast=False)
-
-# Example Usage
-# Replace 'path/to/your_image.jpg' with a valid image file on your system
-# Or download an example image: e.g., !wget -P ./examples/images/ https://huggingface.co/aimagelab/LLaVA_MORE-llama_3_1-8B-finetuning/resolve/main/images/plot.png
-pixel_values = load_image('./examples/images/plot.png', max_num=6).to(torch.bfloat16).cuda()
-generation_config = dict(max_new_tokens=1024, do_sample=True)
-
-question = "Describe the image in detail."
-response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=None, return_history=True)
-print(f'User: {question}
-Assistant: {response}')
-```
-
 ## Training Details
 
 ### Training Data
@@ -251,15 +156,3 @@ For a complete list of all LLaVA-MORE checkpoints, you can refer to the [Hugging
 We thank the [LLaVA](https://github.com/haotian-liu/LLaVA.git) team for open-sourcing a modular codebase to extend and train different models within the LLaVA family. We are also happy users of the [lmms-eval](https://github.com/EvolvingLMMs-Lab/lmms-eval.git) library, which has significantly reduced the evaluation time of our checkpoints across different datasets.
 
 We also thank [CINECA](https://www.hpc.cineca.it/systems/hardware/leonardo/) for the availability of high-performance computing resources used to train LLaVA-MORE. This work is supported by the PNRR-M4C2 project [FAIR - Future Artificial Intelligence Research](https://fondazione-fair.it/) and by the PNRR project [ITSERR - Italian Strengthening of Esfri RI Resilience](https://www.itserr.it/).
-
-## Citation
-If you make use of our work, please cite our paper:
-
-```bibtex
-@inproceedings{cocchi2025llava,
-      title={{LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning}},
-      author={Cocchi, Federico and Moratelli, Nicholas and Caffagni, Davide and Sarto, Sara and Baraldi, Lorenzo and Cornia, Marcella and Cucchiara, Rita},
-      booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops},
-      year={2025}
-}
-```