assignment-a1: adapts to template code

mmp/a1/main.py

@@ -1,5 +1,16 @@
 from typing import Sequence
 import torch
+from torchvision.transforms import functional as F
+from torchvision import transforms, models
+from PIL import Image
+
+
+def pad_to_square(img):
+    w, h = img.size
+    max_wh = max(w, h)
+    pad = ((max_wh - w) // 2, (max_wh - h) // 2)
+    padding = (pad[0], pad[1], max_wh - w - pad[0], max_wh - h - pad[1])
+    return F.pad(img, padding, fill=0, padding_mode='constant')
 
 
 def build_batch(paths: Sequence[str], transform=None) -> torch.Tensor:
@@ -9,7 +20,20 @@ def build_batch(paths: Sequence[str], transform=None) -> torch.Tensor:
     @param transform: One or multiple image transformations for augmenting the batch images.
     @return: Returns one single tensor that contains every image.
     """
-    raise NotImplementedError()
+    preprocess = transforms.Compose([
+        transforms.Lambda(pad_to_square),
+        transforms.Resize((224, 224)),
+        transforms.ToTensor(),
+        transforms.Normalize(mean=[0.485, 0.456, 0.406],
+                             std=[0.229, 0.224, 0.225]),
+    ])
+    imgs = []
+    for path in paths:
+        img = Image.open(path).convert('RGB')
+        img = preprocess(img)
+        imgs.append(img)
+    batch = torch.stack(imgs)
+    return batch
 
 
 def get_model() -> torch.nn.Module:
@@ -17,7 +41,9 @@ def get_model() -> torch.nn.Module:
 
     @return: Returns a neural network, initialised with pretrained weights.
     """
-    raise NotImplementedError()
+    model = models.resnet18(
+        weights=models.ResNet18_Weights.DEFAULT)
+    return model
 
 
 def main():