set resize_and_pad_centered_to_long_side as resize function
Browse files
processing_colgranitevision.py
CHANGED
@@ -133,14 +133,60 @@ class ColGraniteVisionProcessor(LlavaNextProcessor):
|
|
133 |
"""
|
134 |
Resize and pad the image to the required format.
|
135 |
"""
|
136 |
-
return self.
|
137 |
image=image,
|
138 |
factor=self.factor,
|
139 |
min_size=self.min_size,
|
140 |
max_size=self.max_size,
|
141 |
fill_color=0
|
142 |
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
143 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
144 |
def resize_and_pad_centered(self,
|
145 |
image: Image.Image,
|
146 |
factor: int,
|
|
|
133 |
"""
|
134 |
Resize and pad the image to the required format.
|
135 |
"""
|
136 |
+
return self.resize_and_pad_centered_to_long_side(
|
137 |
image=image,
|
138 |
factor=self.factor,
|
139 |
min_size=self.min_size,
|
140 |
max_size=self.max_size,
|
141 |
fill_color=0
|
142 |
)
|
143 |
+
|
144 |
+
def resize_and_pad_centered_to_long_side(
|
145 |
+
self,
|
146 |
+
image: Image.Image,
|
147 |
+
factor: int,
|
148 |
+
min_size: int,
|
149 |
+
max_size: int,
|
150 |
+
fill_color=0
|
151 |
+
) -> Image.Image:
|
152 |
+
"""
|
153 |
+
Resizes and pads an image such that:
|
154 |
+
- The long side is set to `max_size`.
|
155 |
+
- The short side is scaled proportionally but not below `min_size`.
|
156 |
+
- The image is centered within the final padded area.
|
157 |
+
|
158 |
+
:param image: PIL Image
|
159 |
+
:param factor: Factor to make dimensions divisible by
|
160 |
+
:param min_size: Minimum allowed size for the short side
|
161 |
+
:param max_size: Target size for the long side
|
162 |
+
:param fill_color: Background padding color (default black)
|
163 |
+
:return: Resized and padded image
|
164 |
+
"""
|
165 |
+
|
166 |
+
# Get original size
|
167 |
+
width, height = image.size
|
168 |
|
169 |
+
if min_size == -1 or max_size == -1:
|
170 |
+
return image.convert("RGB")
|
171 |
+
|
172 |
+
# Step 1: scale long side to max_size, keep aspect ratio
|
173 |
+
if width > height:
|
174 |
+
scale_factor = max_size / width
|
175 |
+
target_width = max_size
|
176 |
+
max_scale_factor = max(min_size / height, scale_factor)
|
177 |
+
target_height = round(height * max_scale_factor)
|
178 |
+
else:
|
179 |
+
scale_factor = max_size / height
|
180 |
+
target_height = max_size
|
181 |
+
max_scale_factor = max(min_size / width, scale_factor)
|
182 |
+
target_width = round(width * max_scale_factor)
|
183 |
+
|
184 |
+
# Resize the image
|
185 |
+
resized_image = image.resize((target_width, target_height), Image.LANCZOS)
|
186 |
+
final_image =resized_image.convert("RGB")
|
187 |
+
|
188 |
+
return final_image
|
189 |
+
|
190 |
def resize_and_pad_centered(self,
|
191 |
image: Image.Image,
|
192 |
factor: int,
|