File size: 8,303 Bytes
8935f2f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1a8a785
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
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
---
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
# Doc / guide: https://huggingface.co/docs/hub/model-cards
{}
---
# Model Card for Model ID

copy/paste/save as pix2pixinference.py
```
import argparse
import torch
from torchvision.transforms import Compose, Resize, ToTensor, Normalize, ToPILImage
from torchvision.utils import save_image
from PIL import Image
import os
import io
from huggingface_hub import hf_hub_download
import sys
import matplotlib.pyplot as plt

# Import the model architecture - assuming it's locally available
# If not, we'll need to define it here
try:
    from modeling_pix2pix import GeneratorUNet
except ImportError:
    print("Couldn't import model architecture, defining it here...")
    # Define the UNet architecture as it appears in the original code
    import torch.nn as nn
    import torch.nn.functional as F

    def weights_init_normal(m):
        classname = m.__class__.__name__
        if classname.find("Conv") != -1:
            torch.nn.init.normal_(m.weight.data, 0.0, 0.02)
        elif classname.find("BatchNorm2d") != -1:
            torch.nn.init.normal_(m.weight.data, 1.0, 0.02)
            torch.nn.init.constant_(m.bias.data, 0.0)

    class UNetDown(nn.Module):
        def __init__(self, in_size, out_size, normalize=True, dropout=0.0):
            super(UNetDown, self).__init__()
            layers = [nn.Conv2d(in_size, out_size, 4, 2, 1, bias=False)]
            if normalize:
                layers.append(nn.InstanceNorm2d(out_size))
            layers.append(nn.LeakyReLU(0.2))
            if dropout:
                layers.append(nn.Dropout(dropout))
            self.model = nn.Sequential(*layers)

        def forward(self, x):
            return self.model(x)

    class UNetUp(nn.Module):
        def __init__(self, in_size, out_size, dropout=0.0):
            super(UNetUp, self).__init__()
            layers = [
                nn.ConvTranspose2d(in_size, out_size, 4, 2, 1, bias=False),
                nn.InstanceNorm2d(out_size),
                nn.ReLU(inplace=True),
            ]
            if dropout:
                layers.append(nn.Dropout(dropout))
            self.model = nn.Sequential(*layers)

        def forward(self, x, skip_input):
            x = self.model(x)
            x = torch.cat((x, skip_input), 1)
            return x

    class GeneratorUNet(nn.Module):
        def __init__(self, in_channels=3, out_channels=3):
            super(GeneratorUNet, self).__init__()

            self.down1 = UNetDown(in_channels, 64, normalize=False)
            self.down2 = UNetDown(64, 128)
            self.down3 = UNetDown(128, 256)
            self.down4 = UNetDown(256, 512, dropout=0.5)
            self.down5 = UNetDown(512, 512, dropout=0.5)
            self.down6 = UNetDown(512, 512, dropout=0.5)
            self.down7 = UNetDown(512, 512, dropout=0.5)
            self.down8 = UNetDown(512, 512, normalize=False, dropout=0.5)

            self.up1 = UNetUp(512, 512, dropout=0.5)
            self.up2 = UNetUp(1024, 512, dropout=0.5)
            self.up3 = UNetUp(1024, 512, dropout=0.5)
            self.up4 = UNetUp(1024, 512, dropout=0.5)
            self.up5 = UNetUp(1024, 256)
            self.up6 = UNetUp(512, 128)
            self.up7 = UNetUp(256, 64)

            self.final = nn.Sequential(
                nn.ConvTranspose2d(128, out_channels, 4, 2, 1),
                nn.Tanh(),
            )

        def forward(self, x):
            # U-Net generator with skip connections from encoder to decoder
            d1 = self.down1(x)
            d2 = self.down2(d1)
            d3 = self.down3(d2)
            d4 = self.down4(d3)
            d5 = self.down5(d4)
            d6 = self.down6(d5)
            d7 = self.down7(d6)
            d8 = self.down8(d7)
            u1 = self.up1(d8, d7)
            u2 = self.up2(u1, d6)
            u3 = self.up3(u2, d5)
            u4 = self.up4(u3, d4)
            u5 = self.up5(u4, d3)
            u6 = self.up6(u5, d2)
            u7 = self.up7(u6, d1)
            return self.final(u7)


def parse_args():
    parser = argparse.ArgumentParser(description="Generate images using Pix2Pix model from HuggingFace Hub")
    parser.add_argument(
        "--repo_id",
        type=str,
        required=True,
        help="HuggingFace Hub repository ID (e.g., 'username/model_name')"
    )
    parser.add_argument(
        "--model_file",
        type=str,
        default="model.pt",
        help="Name of the model file in the repository"
    )
    parser.add_argument(
        "--input_image",
        type=str,
        required=True,
        help="Path to input image (night image to transform to day)"
    )
    parser.add_argument(
        "--output_image",
        type=str,
        default="output.png",
        help="Path to save the generated image"
    )
    parser.add_argument(
        "--image_size",
        type=int,
        default=256,
        help="Size of the input/output images"
    )
    parser.add_argument(
        "--display",
        action="store_true",
        help="Display input and output images using matplotlib"
    )
    parser.add_argument(
        "--token",
        type=str,
        default=None,
        help="HuggingFace token for accessing private repositories"
    )
    return parser.parse_args()


def main():
    args = parse_args()
    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
    
    print(f"Using device: {device}")
    
    # Set up image transformations
    transform_input = Compose([
        Resize((args.image_size, args.image_size)),
        ToTensor(),
        Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)),
    ])
    
    # Initialize model
    print("Initializing model...")
    generator = GeneratorUNet()
    generator.to(device)
    
    # Download model from Hugging Face Hub
    print(f"Downloading model from {args.repo_id}...")
    try:
        model_path = hf_hub_download(
            repo_id=args.repo_id,
            filename=args.model_file,
            token=args.token
        )
        print(f"Model downloaded to {model_path}")
    except Exception as e:
        print(f"Error downloading model: {e}")
        sys.exit(1)
    
    # Load model weights
    try:
        generator.load_state_dict(torch.load(model_path, map_location=device))
        generator.eval()
        print("Model loaded successfully")
    except Exception as e:
        print(f"Error loading model weights: {e}")
        sys.exit(1)
    
    # Load and preprocess input image
    try:
        image = Image.open(args.input_image).convert("RGB")
        original_image = image.copy()
        input_tensor = transform_input(image).unsqueeze(0).to(device)
        print(f"Input image loaded: {args.input_image}")
    except Exception as e:
        print(f"Error loading input image: {e}")
        sys.exit(1)
    
    # Generate output image
    print("Generating image...")
    with torch.no_grad():
        fake_B = generator(input_tensor)
    
    # Save the output image
    try:
        # Denormalize and convert back to image
        output_image = fake_B.cpu()
        save_image(output_image, args.output_image, normalize=True)
        print(f"Output image saved to {args.output_image}")
        
        # Create a PIL image for display if needed
        to_pil = ToPILImage()
        output_pil = to_pil(output_image.squeeze(0) * 0.5 + 0.5)
    except Exception as e:
        print(f"Error saving output image: {e}")
        sys.exit(1)
    
    # Display images if requested
    if args.display:
        try:
            plt.figure(figsize=(10, 5))
            
            plt.subplot(1, 2, 1)
            plt.title("Input Image (Night)")
            plt.imshow(original_image)
            plt.axis("off")
            
            plt.subplot(1, 2, 2)
            plt.title("Generated Image (Day)")
            plt.imshow(output_pil)
            plt.axis("off")
            
            plt.tight_layout()
            plt.show()
        except Exception as e:
            print(f"Error displaying images: {e}")


if __name__ == "__main__":
    main()
```
python pix2pixinference.py --repo_id "uisikdag/gan-pix2pix-night2day" --input_image "night_image.jpg" --output_image "day_image.png"