Upload folder using huggingface_hub

README.md

@@ -5,4 +5,4 @@ app_file: app.py
 sdk: gradio
 sdk_version: 4.44.0
 ---
-# style-transfer
+# Neural Style Transfer

app.py

@@ -23,6 +23,15 @@ for param in model.parameters():
 
 style_files = os.listdir('./style_images')
 style_options = {' '.join(style_file.split('.')[0].split('_')): f'./style_images/{style_file}' for style_file in style_files}
+optimal_settings = {
+    'Starry Night': (100, True),
+    'Lego Bricks': (50, False),
+    'Mosaic': (100, False),
+    'Oil Painting': (100, False),
+    'Scream': (75, True),
+    'Great Wave': (75, False),
+    'Watercolor': (10, False),
+}
 
 @spaces.GPU(duration=20)
 def inference(content_image, style_image, style_strength, output_quality, progress=gr.Progress(track_tqdm=True)):
@@ -82,6 +91,9 @@ def inference(content_image, style_image, style_strength, output_quality, progre
 def set_slider(value):
     return gr.update(value=value)
 
+def update_settings(style):
+    return optimal_settings.get(style, (50, True))
+
 css = """
 #container {
     margin: 0 auto;
@@ -93,36 +105,27 @@ with gr.Blocks(css=css) as demo:
     gr.HTML("<h1 style='text-align: center; padding: 10px'>🖼️ Neural Style Transfer</h1>")
     with gr.Column(elem_id='container'):
         content_and_output = gr.Image(show_label=False, type='pil', sources=['upload'], format='jpg', show_download_button=False)
-        style_dropdown = gr.Radio(choices=list(style_options.keys()), label='Style', value='Starry Night', type='value')
+        style_dropdown = gr.Radio(choices=list(style_options.keys()), label='Style', info='Note: Adjustments automatically optimize for different styles.', value='Starry Night', type='value')
         with gr.Accordion('Adjustments', open=False):
             with gr.Group():
                 style_strength_slider = gr.Slider(label='Style Strength', minimum=1, maximum=100, step=1, value=50)
+                
                 with gr.Row():
-                    low_button = gr.Button('Low').click(fn=lambda: set_slider(10), outputs=[style_strength_slider])
-                    medium_button = gr.Button('Medium').click(fn=lambda: set_slider(50), outputs=[style_strength_slider])
-                    high_button = gr.Button('High').click(fn=lambda: set_slider(100), outputs=[style_strength_slider])
+                    low_button = gr.Button('Low', size='sm').click(fn=lambda: set_slider(10), outputs=[style_strength_slider])
+                    medium_button = gr.Button('Medium', size='sm').click(fn=lambda: set_slider(50), outputs=[style_strength_slider])
+                    high_button = gr.Button('High', size='sm').click(fn=lambda: set_slider(100), outputs=[style_strength_slider])
             with gr.Group():
                 output_quality = gr.Checkbox(label='More Realistic', info='Note: If unchecked, the resulting image will have a more artistic flair.', value=True)
         
         submit_button = gr.Button('Submit', variant='primary')
-        download_button = gr.DownloadButton(label='Download Image', visible=False)
-        
-        def save_generated_image(img):
-            output_path = 'generated.jpg'
-            img.save(output_path)
-            return output_path
+        download_button = gr.DownloadButton(label='Download Image', value='generated.jpg', visible=False)
     
         submit_button.click(
             fn=inference, 
             inputs=[content_and_output, style_dropdown, style_strength_slider, output_quality], 
             outputs=[content_and_output]
-        ).then(
-            fn=save_generated_image,
-            inputs=[content_and_output],
-            outputs=[download_button]
         ).then(
             fn=lambda: gr.update(visible=True),
-            inputs=[],
             outputs=[download_button]
         )
         
@@ -132,6 +135,17 @@ with gr.Blocks(css=css) as demo:
             outputs=[download_button]
         )
         
+        style_dropdown.change(
+            fn=lambda style: set_slider(update_settings(style)[0]), 
+            inputs=[style_dropdown], 
+            outputs=[style_strength_slider]
+        )
+        style_dropdown.change(
+            fn=lambda style: gr.update(value=update_settings(style)[1]), 
+            inputs=[style_dropdown], 
+            outputs=[output_quality]
+        )
+        
         examples = gr.Examples(
             examples=[
                 ['./content_images/TajMahal.jpg', 'Starry Night', 75, True],

vgg16.py

@@ -0,0 +1,73 @@
+import torch.nn as nn
+import torchvision.models as models
+
+""" VGG_16 Architecture
+VGG(
+  (features): Sequential(
+    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (1): ReLU(inplace=True)
+    (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (3): ReLU(inplace=True)
+    (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
+    (5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (6): ReLU(inplace=True)
+    (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (8): ReLU(inplace=True)
+    (9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
+    (10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (11): ReLU(inplace=True)
+    (12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (13): ReLU(inplace=True)
+    (14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (15): ReLU(inplace=True)
+    (16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
+    (17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (18): ReLU(inplace=True)
+    (19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (20): ReLU(inplace=True)
+    (21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (22): ReLU(inplace=True)
+    (23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
+    (24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (25): ReLU(inplace=True)
+    (26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (27): ReLU(inplace=True)
+    (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (29): ReLU(inplace=True)
+    (30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
+  )
+  (avgpool): AdaptiveAvgPool2d(output_size=(7, 7))
+  (classifier): Sequential(
+    (0): Linear(in_features=25088, out_features=4096, bias=True)
+    (1): ReLU(inplace=True)
+    (2): Dropout(p=0.5, inplace=False)
+    (3): Linear(in_features=4096, out_features=4096, bias=True)
+    (4): ReLU(inplace=True)
+    (5): Dropout(p=0.5, inplace=False)
+    (6): Linear(in_features=4096, out_features=1000, bias=True)
+  )
+)
+"""
+
+class VGG_16(nn.Module):
+    def __init__(self):
+        super(VGG_16, self).__init__()
+        self.model = models.vgg19(weights='DEFAULT').features[:30]
+        
+        for i, _ in enumerate(self.model):
+            if i in [4, 9, 16, 23]:
+                self.model[i] = nn.AvgPool2d(kernel_size=2, stride=2, padding=0)
+                
+    def forward(self, x):
+        features = []
+        
+        for i, layer in enumerate(self.model):
+            x = layer(x)
+            if i in [0, 5, 10, 17, 24]:
+                features.append(x)
+        return features
+    
+
+if __name__ == '__main__':
+    model = VGG_16()
+    print(model)

vgg19.py

@@ -1,6 +1,60 @@
 import torch.nn as nn
 import torchvision.models as models
 
+""" VGG_19 Architecture
+VGG(
+  (features): Sequential(
+    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (1): ReLU(inplace=True)
+    (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (3): ReLU(inplace=True)
+    (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
+    (5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (6): ReLU(inplace=True)
+    (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (8): ReLU(inplace=True)
+    (9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
+    (10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (11): ReLU(inplace=True)
+    (12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (13): ReLU(inplace=True)
+    (14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (15): ReLU(inplace=True)
+    (16): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (17): ReLU(inplace=True)
+    (18): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
+    (19): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (20): ReLU(inplace=True)
+    (21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (22): ReLU(inplace=True)
+    (23): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (24): ReLU(inplace=True)
+    (25): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (26): ReLU(inplace=True)
+    (27): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
+    (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (29): ReLU(inplace=True)
+    (30): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (31): ReLU(inplace=True)
+    (32): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (33): ReLU(inplace=True)
+    (34): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (35): ReLU(inplace=True)
+    (36): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
+  )
+  (avgpool): AdaptiveAvgPool2d(output_size=(7, 7))
+  (classifier): Sequential(
+    (0): Linear(in_features=25088, out_features=4096, bias=True)
+    (1): ReLU(inplace=True)
+    (2): Dropout(p=0.5, inplace=False)
+    (3): Linear(in_features=4096, out_features=4096, bias=True)
+    (4): ReLU(inplace=True)
+    (5): Dropout(p=0.5, inplace=False)
+    (6): Linear(in_features=4096, out_features=1000, bias=True)
+  )
+)
+"""
+
 class VGG_19(nn.Module):
     def __init__(self):
         super(VGG_19, self).__init__()