remove resizing and cropping

train_dreambooth_lora_sdxl_advanced.py

@@ -1070,8 +1070,8 @@ class DreamBoothDataset(Dataset):
         self.original_sizes = []
         self.crop_top_lefts = []
         self.pixel_values = []
-        train_resize = transforms.Resize(size, interpolation=transforms.InterpolationMode.BILINEAR)
-        train_crop = transforms.CenterCrop(size) if center_crop else transforms.RandomCrop(size)
+        #train_resize = transforms.Resize(size, interpolation=transforms.InterpolationMode.BILINEAR)
+        #train_crop = transforms.CenterCrop(size) if center_crop else transforms.RandomCrop(size)
         train_flip = transforms.RandomHorizontalFlip(p=1.0)
         train_transforms = transforms.Compose(
             [
@@ -1087,18 +1087,20 @@ class DreamBoothDataset(Dataset):
             if not image.mode == "RGB":
                 image = image.convert("RGB")
             self.original_sizes.append((image.height, image.width))
-            image = train_resize(image)
+            #image = train_resize(image)
 
             if not single_image and args.random_flip and random.random() < 0.5:
                 # flip
                 image = train_flip(image)
             if args.center_crop or single_image:
-                y1 = max(0, int(round((image.height - args.resolution) / 2.0)))
-                x1 = max(0, int(round((image.width - args.resolution) / 2.0)))
-                image = train_crop(image)
+                pass
+                #y1 = max(0, int(round((image.height - args.resolution) / 2.0)))
+                #x1 = max(0, int(round((image.width - args.resolution) / 2.0)))
+                #image = train_crop(image)
             else:
-                y1, x1, h, w = train_crop.get_params(image, (args.resolution, args.resolution))
-                image = crop(image, y1, x1, h, w)
+                pass
+                #y1, x1, h, w = train_crop.get_params(image, (args.resolution, args.resolution))
+                #image = crop(image, y1, x1, h, w)
             crop_top_left = (y1, x1)
             self.crop_top_lefts.append(crop_top_left)
             image = train_transforms(image)
@@ -1121,17 +1123,17 @@ class DreamBoothDataset(Dataset):
                 if not image.mode == "RGB":
                     image = image.convert("RGB")
                 self.original_sizes_class_imgs.append((image.height, image.width))
-                image = train_resize(image)
+                # image = train_resize(image)
                 if args.random_flip and random.random() < 0.5:
                     # flip
                     image = train_flip(image)
                 if args.center_crop:
-                    y1 = max(0, int(round((image.height - args.resolution) / 2.0)))
-                    x1 = max(0, int(round((image.width - args.resolution) / 2.0)))
-                    image = train_crop(image)
+                    #y1 = max(0, int(round((image.height - args.resolution) / 2.0)))
+                    #x1 = max(0, int(round((image.width - args.resolution) / 2.0)))
+                    #image = train_crop(image)
                 else:
-                    y1, x1, h, w = train_crop.get_params(image, (args.resolution, args.resolution))
-                    image = crop(image, y1, x1, h, w)
+                    #y1, x1, h, w = train_crop.get_params(image, (args.resolution, args.resolution))
+                    #image = crop(image, y1, x1, h, w)
                 crop_top_left = (y1, x1)
                 self.crop_top_lefts_class_imgs.append(crop_top_left)
                 image = train_transforms(image)
@@ -1147,8 +1149,8 @@ class DreamBoothDataset(Dataset):
 
         self.image_transforms = transforms.Compose(
             [
-                transforms.Resize(size, interpolation=transforms.InterpolationMode.BILINEAR),
-                transforms.CenterCrop(size) if center_crop else transforms.RandomCrop(size),
+                # transforms.Resize(size, interpolation=transforms.InterpolationMode.BILINEAR),
+                # transforms.CenterCrop(size) if center_crop else transforms.RandomCrop(size),
                 transforms.ToTensor(),
                 transforms.Normalize([0.5], [0.5]),
             ]