import argparse
import cv2
import numpy as np
import os
import torch
import torch.nn.functional as F
from torchvision.transforms import Compose
from tqdm import tqdm

from depth_anything.dpt import DepthAnything
from depth_anything.util.transform import Resize, NormalizeImage, PrepareForNet

def read_image_safe(path):
    """
    [解决中文路径问题] 读取图片
    使用 numpy 读取字节流再解码，绕过 cv2.imread 的路径编码 bug
    """
    try:
        # np.fromfile 读取文件内容到内存
        img_array = np.fromfile(path, dtype=np.uint8)
        # cv2.imdecode 解码内存数据
        img = cv2.imdecode(img_array, cv2.IMREAD_COLOR)
        return img
    except Exception as e:
        print(f"Error reading image {path}: {e}")
        return None

def write_image_safe(path, img):
    """
    [解决中文路径问题] 保存图片
    使用 cv2.imencode 编码再用 numpy 保存，绕过 cv2.imwrite 的路径编码 bug
    """
    try:
        # 获取文件扩展名 (例如 .png)
        ext = os.path.splitext(path)[1]
        if not ext:
            ext = ".png"
        
        # cv2.imencode 编码图片
        success, img_array = cv2.imencode(ext, img)
        if success:
            # tofile 保存到文件
            img_array.tofile(path)
            return True
        else:
            print(f"Error encoding image for {path}")
            return False
    except Exception as e:
        print(f"Error writing image {path}: {e}")
        return False

if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--img-path', type=str)
    parser.add_argument('--outdir', type=str, default='./vis_depth')
    parser.add_argument('--encoder', type=str, default='vitl', choices=['vits', 'vitb', 'vitl'])
    
    parser.add_argument('--pred-only', dest='pred_only', action='store_true', help='only display the prediction')
    parser.add_argument('--grayscale', dest='grayscale', action='store_true', help='do not apply colorful palette')
    
    args = parser.parse_args()
    
    margin_width = 50
    caption_height = 60
    
    font = cv2.FONT_HERSHEY_SIMPLEX
    font_scale = 1
    font_thickness = 2
    
    DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu'
    
    # Way 1 离线模式
    model_configs = {
        'vitl': {'encoder': 'vitl', 'features': 256, 'out_channels': [256, 512, 1024, 1024]},
        'vitb': {'encoder': 'vitb', 'features': 128, 'out_channels': [96, 192, 384, 768]},
        'vits': {'encoder': 'vits', 'features': 64, 'out_channels': [48, 96, 192, 384]}
    }
    depth_anything = DepthAnything(model_configs[args.encoder]).to(DEVICE).eval()
    depth_anything.load_state_dict(torch.load(f'./checkpoints/depth_anything_{args.encoder}14.pth'))

    # Way 2 在线下载模式
    # depth_anything = DepthAnything.from_pretrained('LiheYoung/depth_anything_{}14'.format(args.encoder)).to(DEVICE).eval()
    
    total_params = sum(param.numel() for param in depth_anything.parameters())
    print('Total parameters: {:.2f}M'.format(total_params / 1e6))
    
    transform = Compose([
        Resize(
            width=518,
            height=518,
            resize_target=False,
            keep_aspect_ratio=True,
            ensure_multiple_of=14,
            resize_method='lower_bound',
            image_interpolation_method=cv2.INTER_CUBIC,
        ),
        NormalizeImage(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
        PrepareForNet(),
    ])
    
    if os.path.isfile(args.img_path):
        if args.img_path.endswith('txt'):
            with open(args.img_path, 'r') as f:
                filenames = f.read().splitlines()
        else:
            filenames = [args.img_path]
    else:
        filenames = os.listdir(args.img_path)
        filenames = [os.path.join(args.img_path, filename) for filename in filenames if not filename.startswith('.')]
        filenames.sort()
    
    os.makedirs(args.outdir, exist_ok=True)
    
    for filename in tqdm(filenames):
        raw_image = read_image_safe(filename)
        image = cv2.cvtColor(raw_image, cv2.COLOR_BGR2RGB) / 255.0
        
        h, w = image.shape[:2]
        
        image = transform({'image': image})['image']
        image = torch.from_numpy(image).unsqueeze(0).to(DEVICE)
        
        with torch.no_grad():
            depth = depth_anything(image)
        
        depth = F.interpolate(depth[None], (h, w), mode='bilinear', align_corners=False)[0, 0]
        depth = (depth - depth.min()) / (depth.max() - depth.min()) * 255.0
        
        depth = depth.cpu().numpy().astype(np.uint8)
        
        if args.grayscale:
            depth = np.repeat(depth[..., np.newaxis], 3, axis=-1)
        else:
            depth = cv2.applyColorMap(depth, cv2.COLORMAP_INFERNO)
        
        filename = os.path.basename(filename)
        
        if args.pred_only:
            if write_image_safe(os.path.join(args.outdir, filename[:filename.rfind('.')] + '.png'), depth):
                print(f"Saved: {os.path.join(args.outdir, filename[:filename.rfind('.')] + '.png')}")
            else:
                print(f"Failed to save: {os.path.join(args.outdir, filename[:filename.rfind('.')] + '.png')}")
        else:
            split_region = np.ones((raw_image.shape[0], margin_width, 3), dtype=np.uint8) * 255
            combined_results = cv2.hconcat([raw_image, split_region, depth])
            
            caption_space = np.ones((caption_height, combined_results.shape[1], 3), dtype=np.uint8) * 255
            captions = ['Raw image', 'Depth Anything']
            segment_width = w + margin_width
            
            for i, caption in enumerate(captions):
                # Calculate text size
                text_size = cv2.getTextSize(caption, font, font_scale, font_thickness)[0]

                # Calculate x-coordinate to center the text
                text_x = int((segment_width * i) + (w - text_size[0]) / 2)

                # Add text caption
                cv2.putText(caption_space, caption, (text_x, 40), font, font_scale, (0, 0, 0), font_thickness)
            
            final_result = cv2.vconcat([caption_space, combined_results])

            if write_image_safe(os.path.join(args.outdir, filename[:filename.rfind('.')] + '.png'), final_result):
                print(f"Saved: {os.path.join(args.outdir, filename[:filename.rfind('.')] + '.png')}")
            else:
                print(f"Failed to save: {os.path.join(args.outdir, filename[:filename.rfind('.')] + '.png')}")