update readme & add run_img.py

README.md

@@ -104,21 +104,26 @@ python evaluate.py -m zoedepth --pretrained_resource="local::./depth_anything_fi
 
 ## 推理
 ```
-python run.py --encoder vitb --img-path assets/examples --outdir depth_vis
+python run_img.py --encoder vitb --img-path assets/examples --outdir depth_vis
+# 注意更改模型文件路径
 ```
 ## result
 <!-- 此处填算法效果测试图（包括输入、输出） -->
-训练loss情况，红色为GPU，蓝色为DCU
+训练结果：loss情况，红色为GPU，蓝色为DCU
 <div align=center>
     <img src="./doc/loss.png"/>
 </div>
-测试图片
+
+
+推理结果
+
+DCU
 <div align=center>
-    <img src="./doc/test1.png"/>
+    <img src="./doc/demo1_img_depth_dcu.png"/>
 </div>
-测试结果
+GPU
 <div align=center>
-    <img src="./doc/testPrediction.png"/>
+    <img src="./doc/demo1_img_depth_gpu.png"/>
 </div>
 
 ### 精度

run_img.py

+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
+
+
+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
+    
+    
+    os.environ['CUDA_VISIBLE_DEVICES'] = '5'    
+
+    DEVICE = 'cuda:0' if torch.cuda.is_available() else 'cpu'
+    
+    # 手动加载模型
+    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]}
+    }
+    encoder = 'vitb' # or 'vitb', 'vits'
+    depth_anything = DepthAnything(model_configs[args.encoder])
+
+    latest = torch.load(f'./metric_depth/depth_anything_finetune/xxx_best.pt', map_location='cpu')
+    # print('********************************')
+    # for k, v in latest.items():
+    #     print(k)
+    # print('********************************')
+    # for k, v in latest["model"].items():
+    #     print(k)
+    # print('********************************')
+    my_state_dict = {} 
+    for key in latest['model'].keys(): 
+        my_state_dict[key.replace('core.core.', '')] = latest['model'][key]
+    # print('********************************')
+    # for k, v in my_state_dict.items():
+    #     print(k)
+    # print('********************************')
+    depth_anything.load_state_dict(my_state_dict, strict=False)
+
+
+    depth_anything.to(DEVICE)
+
+    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 = cv2.imread(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:
+            cv2.imwrite(os.path.join(args.outdir, filename[:filename.rfind('.')] + '_depth.png'), depth)
+        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])
+            
+            cv2.imwrite(os.path.join(args.outdir, filename[:filename.rfind('.')] + '_img_depth.png'), final_result)
+        
\ No newline at end of file