Update README.md

README.md

@@ -256,18 +256,104 @@ The model follows a connection pattern of Vision Encoder → MLP Adapter → Lan
 ## 5. Usage
 
 ```python
-from transformers import AutoTokenizer, AutoConfig, AutoModel, CLIPImageProcessor
-from utils_ import split_model, load_image
-import sys, os
+import math
 import torch
+import torchvision.transforms as T
+from PIL import Image
+from torchvision.transforms.functional import InterpolationMode
+from transformers import AutoConfig, AutoModel, AutoTokenizer
 
+IMAGENET_MEAN = (0.485, 0.456, 0.406)
+IMAGENET_STD = (0.229, 0.224, 0.225)
 
-path = 'Skywork/Skywork-R1V-38B'
-image_path = "/path/to/image"
+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
 
-device_map, visible_devices = split_model(path)
-tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
+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
+    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_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
+
+def split_model(model_path):
+    device_map = {}
+    world_size = torch.cuda.device_count()
+    config = AutoConfig.from_pretrained(model_path, trust_remote_code=True)
+    num_layers = config.llm_config.num_hidden_layers
+    num_layers_per_gpu = math.ceil(num_layers / (world_size - 0.5))
+    num_layers_per_gpu = [num_layers_per_gpu] * world_size
+    num_layers_per_gpu[0] = math.ceil(num_layers_per_gpu[0] * 0.5)
+    layer_cnt = 0
+    for i, num_layer in enumerate(num_layers_per_gpu):
+        for j in range(num_layer):
+            device_map[f'language_model.model.layers.{layer_cnt}'] = i
+            layer_cnt += 1
+    device_map['vision_model'] = 0
+    device_map['mlp1'] = 0
+    device_map['language_model.model.tok_embeddings'] = 0
+    device_map['language_model.model.embed_tokens'] = 0
+    device_map['language_model.output'] = 0
+    device_map['language_model.model.norm'] = 0
+    device_map['language_model.model.rotary_emb'] = 0
+    device_map['language_model.lm_head'] = 0
+    device_map[f'language_model.model.layers.{num_layers - 1}'] = 0
+    return device_map
+
+path = 'Skywork/Skywork-R1V-38B'
+device_map = split_model(path)
 model = AutoModel.from_pretrained(
     path,
     torch_dtype=torch.bfloat16,
@@ -276,19 +362,25 @@ model = AutoModel.from_pretrained(
     use_flash_attn=True,
     trust_remote_code=True,
     device_map=device_map).eval()
-    
+tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
 generation_config = dict(max_new_tokens=64000, do_sample=True, temperature=0.6, top_p=0.95, repetition_penalty=1.05)
-pixel_values = load_image(image_path, max_num=12).to(torch.bfloat16).cuda()
-
-# pure-text conversation (纯文本对话)
-question = 'If all cats can fly, and Tom is a cat, can Tom fly?'
-response = model.chat(tokenizer, None, question, generation_config, history=None)
-print(f'User: {question}\nAssistant: {response}')
 
-# single-image single-round conversation (单图单轮对话)
+# single-image conversation
+pixel_values = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda()
 question = '<image>\nSelect the correct option from this question.'
 response = model.chat(tokenizer, pixel_values, question, generation_config)
 print(f'User: {question}\nAssistant: {response}')
+
+# multi-image conversation 
+pixel_values1 = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda()
+pixel_values2 = load_image('./examples/image2.jpg', max_num=12).to(torch.bfloat16).cuda()
+pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0)
+num_patches_list = [pixel_values1.size(0), pixel_values2.size(0)]
+question = '<image>\n<image>\nSelect the correct option from this question.'
+response, history = model.chat(tokenizer, pixel_values, question, generation_config,
+                               num_patches_list=num_patches_list,
+                               history=None, return_history=True)
+print(f'User: {question}\nAssistant: {response}')
 ```
 
 ---