Update app.py

app.py

@@ -1,14 +1,15 @@
 import numpy as np
 import torch
 import torchvision.transforms as T
-from decord import VideoReader, cpu
 from PIL import Image
 from torchvision.transforms.functional import InterpolationMode
 from transformers import AutoModel, AutoTokenizer
+import gradio as gr
 
 IMAGENET_MEAN = (0.485, 0.456, 0.406)
 IMAGENET_STD = (0.229, 0.224, 0.225)
 
+# Build the image transform
 def build_transform(input_size):
     MEAN, STD = IMAGENET_MEAN, IMAGENET_STD
     transform = T.Compose([
@@ -19,195 +20,73 @@ def build_transform(input_size):
     ])
     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
-
+# Dynamic preprocessing
 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_ratios = sorted(
+        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),
+        key=lambda x: x[0] * x[1]
+    )
+    target_aspect_ratio = target_ratios[0]
     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 = (
+    processed_images = [
+        resized_img.crop((
             (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
+        ))
+        for i in range(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')
+# Load image dynamically from user upload
+def load_image(image, input_size=448, max_num=12):
     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
 
-# If you want to load a model using multiple GPUs, please refer to the `Multiple GPUs` section.
+# Load the model and tokenizer
 path = 'OpenGVLab/InternVL2_5-1B'
 model = AutoModel.from_pretrained(
     path,
     torch_dtype=torch.bfloat16,
     low_cpu_mem_usage=True,
     use_flash_attn=True,
-    trust_remote_code=True).eval().cuda()
-tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
-
-# set the max number of tiles in `max_num`
-pixel_values = load_image('./examples/image1.jpg', max_num=12).to(torch.bfloat16).cuda()
-generation_config = dict(max_new_tokens=1024, do_sample=True)
-
-# pure-text conversation (纯文本对话)
-question = 'Hello, who are you?'
-response, history = model.chat(tokenizer, None, question, generation_config, history=None, return_history=True)
-print(f'User: {question}\nAssistant: {response}')
-
-question = 'Can you tell me a story?'
-response, history = model.chat(tokenizer, None, question, generation_config, history=history, return_history=True)
-print(f'User: {question}\nAssistant: {response}')
-
-# single-image single-round conversation (单图单轮对话)
-question = '<image>\nPlease describe the image shortly.'
-response = model.chat(tokenizer, pixel_values, question, generation_config)
-print(f'User: {question}\nAssistant: {response}')
-
-# single-image multi-round conversation (单图多轮对话)
-question = '<image>\nPlease describe the image in detail.'
-response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=None, return_history=True)
-print(f'User: {question}\nAssistant: {response}')
-
-question = 'Please write a poem according to the image.'
-response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=history, return_history=True)
-print(f'User: {question}\nAssistant: {response}')
-
-# multi-image multi-round conversation, combined images (多图多轮对话，拼接图像)
-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)
+    trust_remote_code=True
+).eval().cuda()
 
-question = '<image>\nDescribe the two images in detail.'
-response, history = model.chat(tokenizer, pixel_values, question, generation_config,
-                               history=None, return_history=True)
-print(f'User: {question}\nAssistant: {response}')
-
-question = 'What are the similarities and differences between these two images.'
-response, history = model.chat(tokenizer, pixel_values, question, generation_config,
-                               history=history, return_history=True)
-print(f'User: {question}\nAssistant: {response}')
-
-# multi-image multi-round conversation, separate images (多图多轮对话，独立图像)
-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-1: <image>\nImage-2: <image>\nDescribe the two images in detail.'
-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}')
-
-question = 'What are the similarities and differences between these two images.'
-response, history = model.chat(tokenizer, pixel_values, question, generation_config,
-                               num_patches_list=num_patches_list,
-                               history=history, return_history=True)
-print(f'User: {question}\nAssistant: {response}')
-
-# batch inference, single image per sample (单图批处理)
-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()
-num_patches_list = [pixel_values1.size(0), pixel_values2.size(0)]
-pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0)
-
-questions = ['<image>\nDescribe the image in detail.'] * len(num_patches_list)
-responses = model.batch_chat(tokenizer, pixel_values,
-                             num_patches_list=num_patches_list,
-                             questions=questions,
-                             generation_config=generation_config)
-for question, response in zip(questions, responses):
-    print(f'User: {question}\nAssistant: {response}')
-
-# video multi-round conversation (视频多轮对话)
-def get_index(bound, fps, max_frame, first_idx=0, num_segments=32):
-    if bound:
-        start, end = bound[0], bound[1]
-    else:
-        start, end = -100000, 100000
-    start_idx = max(first_idx, round(start * fps))
-    end_idx = min(round(end * fps), max_frame)
-    seg_size = float(end_idx - start_idx) / num_segments
-    frame_indices = np.array([
-        int(start_idx + (seg_size / 2) + np.round(seg_size * idx))
-        for idx in range(num_segments)
-    ])
-    return frame_indices
-
-def load_video(video_path, bound=None, input_size=448, max_num=1, num_segments=32):
-    vr = VideoReader(video_path, ctx=cpu(0), num_threads=1)
-    max_frame = len(vr) - 1
-    fps = float(vr.get_avg_fps())
-
-    pixel_values_list, num_patches_list = [], []
-    transform = build_transform(input_size=input_size)
-    frame_indices = get_index(bound, fps, max_frame, first_idx=0, num_segments=num_segments)
-    for frame_index in frame_indices:
-        img = Image.fromarray(vr[frame_index].asnumpy()).convert('RGB')
-        img = dynamic_preprocess(img, image_size=input_size, use_thumbnail=True, max_num=max_num)
-        pixel_values = [transform(tile) for tile in img]
-        pixel_values = torch.stack(pixel_values)
-        num_patches_list.append(pixel_values.shape[0])
-        pixel_values_list.append(pixel_values)
-    pixel_values = torch.cat(pixel_values_list)
-    return pixel_values, num_patches_list
-
-video_path = './examples/red-panda.mp4'
-pixel_values, num_patches_list = load_video(video_path, num_segments=8, max_num=1)
-pixel_values = pixel_values.to(torch.bfloat16).cuda()
-video_prefix = ''.join([f'Frame{i+1}: <image>\n' for i in range(len(num_patches_list))])
-question = video_prefix + 'What is the red panda doing?'
-# Frame1: <image>\nFrame2: <image>\n...\nFrame8: <image>\n{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}')
+tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
 
-question = 'Describe this video in detail.'
-response, history = model.chat(tokenizer, pixel_values, question, generation_config,
-                               num_patches_list=num_patches_list, history=history, return_history=True)
-print(f'User: {question}\nAssistant: {response}')
+# Define the function for Gradio interface
+def process_image(image):
+    try:
+        pixel_values = load_image(image, max_num=12).to(torch.bfloat16).cuda()
+        generation_config = dict(max_new_tokens=1024, do_sample=True)
+        question = '<image>\nPlease describe the image in detail.'
+        response = model.chat(tokenizer, pixel_values, question, generation_config)
+        return response
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+# Create Gradio Interface
+demo = gr.Interface(
+    fn=process_image,
+    inputs=gr.Image(type="pil"),
+    outputs="text",
+    title="Dynamic Image Processing with InternVL",
+    description="Upload an image and get detailed responses using the InternVL model."
+)
+
+# Launch the Gradio app
+if __name__ == "__main__":
+    demo.launch(server_name="0.0.0.0", server_port=7860)