Hugging Face's logo

Spaces:
joselobenitezg
/
sapiens-demo
Build error

App Files Community
4
sapiens-demo
File size: 7,620 Bytes 
2e49a94
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
 
# # Example usage
# import torch
# import numpy as np
# from PIL import Image
# from torchvision import transforms
# from config import LABELS_TO_IDS
# from utils.vis_utils import visualize_mask_with_overlay

# import torch
# import torch.nn.functional as F
# import numpy as np
# import cv2

# TASK = 'depth'
# VERSION = 'sapiens_0.3b'

# model_path = get_model_path(TASK, VERSION)
# print(model_path)

# model = torch.jit.load(model_path)
# model.eval()
# model.to("cuda")


# def get_depth(image, depth_model, input_shape=(3, 1024, 768), device="cuda"):
#     # Preprocess the image
#     img = preprocess_image(image, input_shape)
    
#     # Run the model
#     with torch.no_grad():
#         result = depth_model(img.to(device))
    
#     # Post-process the output
#     depth_map = post_process_depth(result, (image.shape[0], image.shape[1]))
    
#     # Visualize the depth map
#     depth_image = visualize_depth(depth_map)
    
#     return depth_image, depth_map

# def preprocess_image(image, input_shape):
#     img = cv2.resize(image, (input_shape[2], input_shape[1]), interpolation=cv2.INTER_LINEAR).transpose(2, 0, 1)
#     img = torch.from_numpy(img)
#     img = img[[2, 1, 0], ...].float()
#     mean = torch.tensor([123.5, 116.5, 103.5]).view(-1, 1, 1)
#     std = torch.tensor([58.5, 57.0, 57.5]).view(-1, 1, 1)
#     img = (img - mean) / std
#     return img.unsqueeze(0)

# def post_process_depth(result, original_shape):
#     # Check the dimensionality of the result
#     if result.dim() == 3:
#         result = result.unsqueeze(0)
#     elif result.dim() == 4:
#         pass
#     else:
#         raise ValueError(f"Unexpected result dimension: {result.dim()}")
    
#     # Ensure we're interpolating to the correct dimensions
#     seg_logits = F.interpolate(result, size=original_shape, mode="bilinear", align_corners=False).squeeze(0)
#     depth_map = seg_logits.data.float().cpu().numpy()
    
#     # If depth_map has an extra dimension, squeeze it
#     if depth_map.ndim == 3 and depth_map.shape[0] == 1:
#         depth_map = depth_map.squeeze(0)
    
#     return depth_map

# def visualize_depth(depth_map):
#     # Normalize the depth map
#     min_val, max_val = np.nanmin(depth_map), np.nanmax(depth_map)
#     depth_normalized = 1 - ((depth_map - min_val) / (max_val - min_val))
    
#     # Convert to uint8
#     depth_normalized = (depth_normalized * 255).astype(np.uint8)
    
#     # Apply colormap
#     depth_colored = cv2.applyColorMap(depth_normalized, cv2.COLORMAP_INFERNO)
    
#     return depth_colored

# # You can add the surface normal calculation if needed
# def calculate_surface_normal(depth_map):
#     kernel_size = 7
#     grad_x = cv2.Sobel(depth_map.astype(np.float32), cv2.CV_32F, 1, 0, ksize=kernel_size)
#     grad_y = cv2.Sobel(depth_map.astype(np.float32), cv2.CV_32F, 0, 1, ksize=kernel_size)
#     z = np.full(grad_x.shape, -1)
#     normals = np.dstack((-grad_x, -grad_y, z))

#     normals_mag = np.linalg.norm(normals, axis=2, keepdims=True)
#     with np.errstate(divide="ignore", invalid="ignore"):
#         normals_normalized = normals / (normals_mag + 1e-5)

#     normals_normalized = np.nan_to_num(normals_normalized, nan=-1, posinf=-1, neginf=-1)
#     normal_from_depth = ((normals_normalized + 1) / 2 * 255).astype(np.uint8)
#     normal_from_depth = normal_from_depth[:, :, ::-1]  # RGB to BGR for cv2

#     return normal_from_depth

# from utils.vis_utils import resize_image

# pil_image = Image.open('/home/user/app/assets/image.webp')

# # Load and process an image
# image = cv2.imread('/home/user/app/assets/frame.png')
# depth_image, depth_map = get_depth(image, model)

# surface_normal = calculate_surface_normal(depth_map)
# cv2.imwrite("output_surface_normal.jpg", surface_normal)
# # Save the results
# output_im = cv2.imwrite("output_depth_image2.jpg", depth_image)

import torch
import torch.nn.functional as F
import numpy as np
import cv2
from PIL import Image
from config import SAPIENS_LITE_MODELS_PATH

def load_model(task, version):
    try:
        model_path = SAPIENS_LITE_MODELS_PATH[task][version]
        device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
        model = torch.jit.load(model_path)
        model.eval()
        model.to(device)
        return model, device
    except KeyError as e:
        print(f"Error: Tarea o versión inválida. {e}")
        return None, None

def preprocess_image(image, input_shape):
    img = cv2.resize(image, (input_shape[2], input_shape[1]), interpolation=cv2.INTER_LINEAR).transpose(2, 0, 1)
    img = torch.from_numpy(img)
    img = img[[2, 1, 0], ...].float()
    mean = torch.tensor([123.5, 116.5, 103.5]).view(-1, 1, 1)
    std = torch.tensor([58.5, 57.0, 57.5]).view(-1, 1, 1)
    img = (img - mean) / std
    return img.unsqueeze(0)

def post_process_depth(result, original_shape):
    if result.dim() == 3:
        result = result.unsqueeze(0)
    elif result.dim() == 4:
        pass
    else:
        raise ValueError(f"Unexpected result dimension: {result.dim()}")
    
    seg_logits = F.interpolate(result, size=original_shape, mode="bilinear", align_corners=False).squeeze(0)
    depth_map = seg_logits.data.float().cpu().numpy()
    
    if depth_map.ndim == 3 and depth_map.shape[0] == 1:
        depth_map = depth_map.squeeze(0)
    
    return depth_map

def visualize_depth(depth_map):
    min_val, max_val = np.nanmin(depth_map), np.nanmax(depth_map)
    depth_normalized = 1 - ((depth_map - min_val) / (max_val - min_val))
    depth_normalized = (depth_normalized * 255).astype(np.uint8)
    depth_colored = cv2.applyColorMap(depth_normalized, cv2.COLORMAP_INFERNO)
    return depth_colored

def calculate_surface_normal(depth_map):
    kernel_size = 7
    grad_x = cv2.Sobel(depth_map.astype(np.float32), cv2.CV_32F, 1, 0, ksize=kernel_size)
    grad_y = cv2.Sobel(depth_map.astype(np.float32), cv2.CV_32F, 0, 1, ksize=kernel_size)
    z = np.full(grad_x.shape, -1)
    normals = np.dstack((-grad_x, -grad_y, z))

    normals_mag = np.linalg.norm(normals, axis=2, keepdims=True)
    with np.errstate(divide="ignore", invalid="ignore"):
        normals_normalized = normals / (normals_mag + 1e-5)

    normals_normalized = np.nan_to_num(normals_normalized, nan=-1, posinf=-1, neginf=-1)
    normal_from_depth = ((normals_normalized + 1) / 2 * 255).astype(np.uint8)
    normal_from_depth = normal_from_depth[:, :, ::-1]  # RGB to BGR for cv2

    return normal_from_depth

def process_image_or_video(input_data, task='depth', version='sapiens_0.3b'):
    model, device = load_model(task, version)
    if model is None or device is None:
        return None

    input_shape = (3, 1024, 768)

    def process_frame(frame):
        if isinstance(frame, Image.Image):
            frame = np.array(frame)
        
        if frame.shape[2] == 4:  # RGBA
            frame = cv2.cvtColor(frame, cv2.COLOR_RGBA2RGB)
        
        img = preprocess_image(frame, input_shape)
        
        with torch.no_grad():
            result = model(img.to(device))
        
        depth_map = post_process_depth(result, (frame.shape[0], frame.shape[1]))
        depth_image = visualize_depth(depth_map)
        
        return Image.fromarray(cv2.cvtColor(depth_image, cv2.COLOR_BGR2RGB))

    if isinstance(input_data, np.ndarray):  # Video frame
        return process_frame(input_data)
    elif isinstance(input_data, Image.Image):  # Imagen
        return process_frame(input_data)
    else:
        print("Tipo de entrada no soportado. Por favor, proporcione una imagen PIL o un frame de video numpy.")
        return None