Remove code snippet, add base model (#2)

- Remove code snippet, add base model (ff512191277128d482bc2baaf052ef54155a256e)


Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

README.md

@@ -2,6 +2,8 @@
 license: mit
 pipeline_tag: image-segmentation
 library_name: transformers
+base_model:
+- OpenGVLab/InternVL2_5-2B
 ---
 
 # MLLMSeg: Unlocking the Potential of MLLMs in Referring Expression Segmentation via a Light-weight Mask Decoder
@@ -33,111 +35,9 @@ pip install -r requirements.txt # Assuming requirements.txt from the cloned repo
 pip install flash-attn==2.3.6 --no-build-isolation # Note: requires GPU to install
 ```
 
-### Inference Code 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, 0.225)
-
-def build_transform(input_size):
-    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):
-    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):
-    orig_width, orig_height = image.size
-    aspect_ratio = orig_width / orig_height
-
-    # calculate the existing image aspect ratio
-    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])
-
-    # find the closest aspect ratio to the target
-    target_aspect_ratio = find_closest_aspect_ratio(
-        aspect_ratio, target_ratios, orig_width, orig_height, image_size)
-
-    # calculate the target width and height
-    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]
-
-    # resize the image
-    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 the image
-        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_file, input_size=448, max_num=12):
-    image = Image.open(image_file).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 the model and tokenizer
-# Note: trust_remote_code=True is required for this model architecture
-model_path = 'jcwang0602/MLLMSeg_InternVL2_5_1B_RES' 
-model = AutoModel.from_pretrained(
-    model_path,
-    torch_dtype=torch.bfloat16,
-    low_cpu_mem_usage=True,
-    trust_remote_code=True).eval().cuda()
-tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True, use_fast=False)
-
-# Example image (replace with your image path)
-# You can find example images in the GitHub repository of MLLMSeg, e.g., in the 'examples/images' directory.
-image_path = './path/to/your/image.png' 
-pixel_values = load_image(image_path, max_num=6).to(torch.bfloat16).cuda()
-generation_config = dict(max_new_tokens=1024, do_sample=True)
-
-# Example query for referring expression segmentation
-question = "Please segment the person in the image." # Replace with your specific referring expression
-response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=None, return_history=True)
-print(f'User: {question}
-Assistant: {response}')
+## Usage
+
+Refer to the Github README: 
 
 # The 'response' will contain the segmentation mask coordinates in a specific format (normalized 0-1000).
 # You will need to parse these coordinates and visualize the mask as per the paper's methodology or example scripts.