simonfranken/mmp_wise2526_franksim
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

formatting

Browse Source
This commit is contained in:
franksim
2025-11-07 11:20:08 +01:00
parent 8fc3559d6c
commit b159d76517
8 changed files with 119 additions and 82 deletions
Download Patch File Download Diff File Expand all files Collapse all files

41
mmp/a3/annotation.py
View File

@@ -28,17 +28,23 @@ class AnnotationRect:
def read_groundtruth_file(path: str) -> List[AnnotationRect]:
"""Exercise 3.1b"""
annotationRects = []
with open(path, 'r') as file:
with open(path, "r") as file:
for line in file:
if line.strip():
values = line.strip().split()
annotationRects.append(AnnotationRect(float(values[0]), float(
values[1]), float(values[2]), float(values[3])))
annotationRects.append(
AnnotationRect(
float(values[0]),
float(values[1]),
float(values[2]),
float(values[3]),
)
)
return annotationRects
def get_image_with_max_annotations(dir_path: str) -> str:
img_pattern = re.compile(r'^(\d+)\.jpg$')
img_pattern = re.compile(r"^(\d+)\.jpg$")
files = set(os.listdir(dir_path))
max_file = None
max_annotations = 0
@@ -47,32 +53,41 @@ def get_image_with_max_annotations(dir_path: str) -> str:
match = img_pattern.match(fname)
if match:
img_file = os.path.join(dir_path, fname)
annotations_number = len(read_groundtruth_file(os.path.join(
dir_path, f"{match.group(1)}.gt_data.txt")))
if (annotations_number > max_annotations):
annotations_number = len(
read_groundtruth_file(
os.path.join(dir_path, f"{match.group(1)}.gt_data.txt")
)
)
if annotations_number > max_annotations:
max_file = img_file
max_annotations = annotations_number
return max_file
def visualize_image(image_path: str, output_path='output.jpg', rect_color=(255, 0, 0), width=2):
img_pattern = re.compile(r'(.*)(\.jpg)')
def visualize_image(
image_path: str, output_path="output.jpg", rect_color=(255, 0, 0), width=2
):
img_pattern = re.compile(r"(.*)(\.jpg)")
match = img_pattern.match(image_path)
annotations = read_groundtruth_file(f"{match.group(1)}.gt_data.txt")
img = Image.open(image_path).convert('RGB')
img = Image.open(image_path).convert("RGB")
draw = ImageDraw.Draw(img)
for annotation in annotations:
draw.rectangle([annotation.x1, annotation.y1, annotation.x2, annotation.y2],
outline=rect_color, width=width)
draw.rectangle(
[annotation.x1, annotation.y1, annotation.x2, annotation.y2],
outline=rect_color,
width=width,
)
img.save(output_path)
def main():
image_file = get_image_with_max_annotations(
"/home/ubuntu/mmp_wise2526_franksim/.data/mmp-public-3.2/train")
"/home/ubuntu/mmp_wise2526_franksim/.data/mmp-public-3.2/train"
)
visualize_image(image_file)

49
mmp/a3/dataset.py
View File

@@ -17,7 +17,7 @@ class MMP_Dataset(torch.utils.data.Dataset):
@param image_size: Desired image size that this dataset should return
"""
self.image_size = image_size
img_pattern = re.compile(r'^(\d+)\.jpg$')
img_pattern = re.compile(r"^(\d+)\.jpg$")
files = set(os.listdir(path_to_data))
self.images = []
@@ -25,12 +25,14 @@ class MMP_Dataset(torch.utils.data.Dataset):
match = img_pattern.match(fname)
if match:
img_file = os.path.join(path_to_data, fname)
annotations = read_groundtruth_file(os.path.join(
path_to_data, f"{match.group(1)}.gt_data.txt"))
annotations = read_groundtruth_file(
os.path.join(path_to_data, f"{match.group(1)}.gt_data.txt")
)
self.images.append((img_file, annotations))
self.images.sort(key=lambda x: int(
re.match(r"(.*/)(\d+)(\.jpg)", x[0]).group(2)))
self.images.sort(
key=lambda x: int(re.match(r"(.*/)(\d+)(\.jpg)", x[0]).group(2))
)
def __getitem__(self, idx: int) -> Tuple[torch.Tensor, int]:
"""
@@ -38,15 +40,16 @@ class MMP_Dataset(torch.utils.data.Dataset):
"""
img = Image.open(self.images[idx][0]).convert("RGB")
padding = self.__padding__(img)
transform = transforms.Compose([
transforms.Pad(padding, 0),
transforms.Resize((self.image_size, self.image_size)),
transforms.ToTensor(),
transforms.Normalize(
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]
)
])
transform = transforms.Compose(
[
transforms.Pad(padding, 0),
transforms.Resize((self.image_size, self.image_size)),
transforms.ToTensor(),
transforms.Normalize(
mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]
),
]
)
return (transform(img), 1 if len(self.images[idx][1]) > 1 else 0)
def __padding__(self, img) -> Tuple[int, int, int, int]:
@@ -61,16 +64,24 @@ class MMP_Dataset(torch.utils.data.Dataset):
def get_dataloader(
path_to_data: str, image_size: int, batch_size: int, num_workers: int, is_train: bool = True
path_to_data: str,
image_size: int,
batch_size: int,
num_workers: int,
is_train: bool = True,
) -> DataLoader:
"""Exercise 3.2d"""
path = os.path.join(path_to_data, "train") if is_train else os.path.join(
path_to_data, "val")
path = (
os.path.join(path_to_data, "train")
if is_train
else os.path.join(path_to_data, "val")
)
dataset = MMP_Dataset(path_to_data=path, image_size=image_size)
dataloader = DataLoader(
dataset, batch_size=batch_size,
dataset,
batch_size=batch_size,
shuffle=is_train,
num_workers=num_workers,
pin_memory=True
pin_memory=True,
)
return dataloader

25
mmp/a3/main.py
View File

@@ -7,8 +7,9 @@ from .dataset import get_dataloader
def main():
"""Put your code for Exercise 3.3 in here"""
parser = argparse.ArgumentParser()
parser.add_argument('--tensorboard', action='store_true',
help='Enable TensorBoard logging')
parser.add_argument(
"--tensorboard", action="store_true", help="Enable TensorBoard logging"
)
args = parser.parse_args()
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
@@ -16,17 +17,24 @@ def main():
model = MmpNet(num_classes=2).to(device=device)
dataloader_train = get_dataloader(
path_to_data=".data/mmp-public-3.2",
image_size=244, batch_size=32, num_workers=6, is_train=True
image_size=244,
batch_size=32,
num_workers=6,
is_train=True,
)
dataloader_eval = get_dataloader(
path_to_data=".data/mmp-public-3.2",
image_size=244, batch_size=32, num_workers=6, is_train=False
image_size=244,
batch_size=32,
num_workers=6,
is_train=False,
)
criterion, optimizer = get_criterion_optimizer(model=model)
writer = None
if args.tensorboard:
from torch.utils.tensorboard import SummaryWriter
writer = SummaryWriter(log_dir="runs/a3_mmpnet")
for epoch in range(train_epochs):
@@ -37,14 +45,11 @@ def main():
device=device,
criterion=criterion,
)
val_acc = eval_epoch(
model=model,
loader=dataloader_eval,
device=device
)
val_acc = eval_epoch(model=model, loader=dataloader_eval, device=device)
print(
f"Epoch [{epoch+1}/{train_epochs}] - Train Loss: {train_loss:.4f} - Val Acc: {val_acc:.4f}")
f"Epoch [{epoch + 1}/{train_epochs}] - Train Loss: {train_loss:.4f} - Val Acc: {val_acc:.4f}"
)
if writer is not None:
writer.add_scalar("Loss/train", train_loss, epoch)