shekhatr

.python-version

@@ -0,0 +1 @@
+3.9.18

Pipfile

@@ -0,0 +1,11 @@
+[[source]]
+url = "https://pypi.org/simple"
+verify_ssl = true
+name = "pypi"
+
+[packages]
+
+[dev-packages]
+
+[requires]
+python_version = "3.10"

code/colour.py

@@ -0,0 +1,30 @@
+import matplotlib.colors as mcolors
+
+# Given color list
+label_clrs = [
+ "#ff0000", "#2e8b57", "#808000", "#800000", "#000080", "#2f4f4f", "#ffa500",
+ "#00ff00", "#ba55d3", "#00fa9a", "#00ffff", "#0000ff", "#f08080", "#ff00ff",
+ "#1e90ff", "#ffff54", "#dda0dd", "#ff1493", "#87cefa", "#ffe4c4"
+]
+
+# Number of colors needed
+num_colors_needed = 91
+
+# Calculate the number of times to repeat the original list
+repeat_times = num_colors_needed // len(label_clrs) + 1
+
+# Repeat the original list
+extended_clrs = label_clrs * repeat_times
+
+# Get evenly spaced colors from the extended list
+extended_clrs = extended_clrs[:num_colors_needed]
+
+# Check if there are any duplicate colors
+if len(set(extended_clrs)) != len(extended_clrs):
+ # If duplicates exist, generate additional colors
+ additional_colors_needed = num_colors_needed - len(extended_clrs)
+ additional_colors = list(mcolors.CSS4_COLORS.keys())[:additional_colors_needed]
+ extended_clrs.extend(additional_colors)
+
+# Display the extended list of colors
+print(extended_clrs)

code/da.py

@@ -0,0 +1,79 @@
+import torch as th
+from torch.utils.data import Dataset
+import os
+import PIL.Image as Image
+import csv
+from typing import Callable, Optional, Tuple, Union, List
+
+
+class VOC_Detection(Dataset):
+ """
+ A custom Dataset for the VOC Detection data. An index number (starting from 0) and a color is assigned to each of
+ the labels of the dataset.
+ """
+ C = 20
+
+ index2label = ["person",
+ "bird", "cat", "cow", "dog", "horse", "sheep",
+ "aeroplane", "bicycle", "boat", "bus", "car", "motorbike", "train",
+ "bottle", "chair", "diningtable", "pottedplant", "sofa", "tvmonitor"]
+
+ label2index = {label: index for index, label in enumerate(index2label)}
+
+ label_clrs = ["#ff0000",
+ "#2e8b57", "#808000", "#800000", "#000080", "#2f4f4f", "#ffa500",
+ "#00ff00", "#ba55d3", "#00fa9a", "#00ffff", "#0000ff", "#f08080", "#ff00ff",
+ "#1e90ff", "#ffff54", "#dda0dd", "#ff1493", "#87cefa", "#ffe4c4"]
+
+ def __init__(self, root_dir: str, split: str = 'train',
+ transforms: Optional[Callable] = None) -> None:
+ """ Initialize the VOC_Detection Dataset object.
+
+ :param root_dir: The root directory of the dataset (this directory contains two directories 'train/' and
+ 'test/'.
+ :param split: The split of the dataset ('train' or 'test')
+ :param transforms: The transforms that are applied to the images (x) and their corresponding targets (y).
+ """
+
+ assert split == 'train' or split == 'test'
+ split_dir = os.path.join(root_dir, split)
+
+ self.img_dir = os.path.join(split_dir, "images")
+ self.annot_dir = os.path.join(split_dir, "targets")
+ self.pseudonyms = [filename[:-4] for filename in os.listdir(self.annot_dir)]
+
+ self.transforms = transforms
+
+ def __len__(self) -> int:
+ """
+ Return the total number of instances of the dataset.
+
+ :return: total instances of the dataset
+ """
+ return len(self.pseudonyms)
+
+ def __getitem__(self, idx: int) -> Tuple[Union[th.Tensor, Image.Image], th.Tensor]:
+ """
+ Given an index number in range [0, dataset's length) , return the corresponding image and target of the dataset.
+ If transforms is defined, the images and their targets are first transformed and then return by the function.
+
+ :param idx: The given index number
+ :return: The (x,y)-pair of the image and the target
+ """
+ pid = self.pseudonyms[idx]
+ img_path = os.path.join(self.img_dir, f'{pid}.jpg')
+ annot_path = os.path.join(self.annot_dir, f'{pid}.csv')
+
+ img = Image.open(img_path)
+ target = []
+ with open(annot_path, 'r') as csv_file:
+ csv_reader = csv.reader(csv_file)
+ next(csv_reader) # Remove the header
+ for row in csv_reader:
+ target.append([self.label2index[row[0]]] + [int(row[i]) for i in range(1, 5)])
+ target = th.Tensor(target)
+
+ if self.transforms is not None:
+ img, target = self.transforms((img, target))
+
+ return img, target

code/dataset.py

@@ -0,0 +1,73 @@
+import torch as th
+from torch.utils.data import Dataset
+import os
+import PIL.Image as Image
+import csv
+from typing import Callable, Optional, Tuple, Union, List
+
+
+class VOC_Detection(Dataset):
+ """
+ A custom Dataset for the VOC Detection data. An index number (starting from 0) and a color is assigned to each of
+ the labels of the dataset.
+ """
+ C = 91
+
+ index2label = [ 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light', 'fire hydrant', 'street sign', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow', 'elephant', 'bear', 'zebra', 'giraffe', 'hat', 'backpack', 'umbrella', 'shoe', 'eye glasses', 'handbag', 'tie', 'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', 'tennis racket', 'bottle', 'plate', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', 'potted plant', 'bed', 'mirror', 'dining table', 'window', 'desk', 'toilet', 'door', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'blender', 'book', 'clock', 'vase', 'scissors', 'teddy bear', 'hair drier', 'toothbrush', 'hair brush']
+
+ label2index = {label: index for index, label in enumerate(index2label)}
+
+ label_clrs = ['#ff0000', '#2e8b57', '#808000', '#800000', '#000080', '#2f4f4f', '#ffa500', '#00ff00', '#ba55d3', '#00fa9a', '#00ffff', '#0000ff', '#f08080', '#ff00ff', '#1e90ff', '#ffff54', '#dda0dd', '#ff1493', '#87cefa', '#ffe4c4', '#ff0000', '#2e8b57', '#808000', '#800000', '#000080', '#2f4f4f', '#ffa500', '#00ff00', '#ba55d3', '#00fa9a', '#00ffff', '#0000ff', '#f08080', '#ff00ff', '#1e90ff', '#ffff54', '#dda0dd', '#ff1493', '#87cefa', '#ffe4c4', '#ff0000', '#2e8b57', '#808000', '#800000', '#000080', '#2f4f4f', '#ffa500', '#00ff00', '#ba55d3', '#00fa9a', '#00ffff', '#0000ff', '#f08080', '#ff00ff', '#1e90ff', '#ffff54', '#dda0dd', '#ff1493', '#87cefa', '#ffe4c4', '#ff0000', '#2e8b57', '#808000', '#800000', '#000080', '#2f4f4f', '#ffa500', '#00ff00', '#ba55d3', '#00fa9a', '#00ffff', '#0000ff', '#f08080', '#ff00ff', '#1e90ff', '#ffff54', '#dda0dd', '#ff1493', '#87cefa', '#ffe4c4', '#ff0000', '#2e8b57', '#808000', '#800000', '#000080', '#2f4f4f', '#ffa500', '#00ff00', '#ba55d3', '#00fa9a', '#00ffff']
+
+ def __init__(self, root_dir: str, split: str = 'train',
+ transforms: Optional[Callable] = None) -> None:
+ """ Initialize the VOC_Detection Dataset object.
+
+ :param root_dir: The root directory of the dataset (this directory contains two directories 'train/' and
+ 'test/'.
+ :param split: The split of the dataset ('train' or 'test')
+ :param transforms: The transforms that are applied to the images (x) and their corresponding targets (y).
+ """
+
+ assert split == 'train' or split == 'test'
+ split_dir = os.path.join(root_dir, split)
+
+ self.img_dir = os.path.join(split_dir, "images")
+ self.annot_dir = os.path.join(split_dir, "targets")
+ self.pseudonyms = [filename[:-4] for filename in os.listdir(self.annot_dir)]
+
+ self.transforms = transforms
+
+ def __len__(self) -> int:
+ """
+ Return the total number of instances of the dataset.
+
+ :return: total instances of the dataset
+ """
+ return len(self.pseudonyms)
+
+ def __getitem__(self, idx: int) -> Tuple[Union[th.Tensor, Image.Image], th.Tensor]:
+ """
+ Given an index number in range [0, dataset's length) , return the corresponding image and target of the dataset.
+ If transforms is defined, the images and their targets are first transformed and then return by the function.
+
+ :param idx: The given index number
+ :return: The (x,y)-pair of the image and the target
+ """
+ pid = self.pseudonyms[idx]
+ img_path = os.path.join(self.img_dir, f'{pid}.jpg')
+ annot_path = os.path.join(self.annot_dir, f'{pid}.csv')
+
+ img = Image.open(img_path)
+ target = []
+ with open(annot_path, 'r') as csv_file:
+ csv_reader = csv.reader(csv_file)
+ next(csv_reader) # Remove the header
+ for row in csv_reader:
+ target.append([self.label2index[row[0]]] + [int(row[i]) for i in range(1, 5)])
+ target = th.Tensor(target)
+
+ if self.transforms is not None:
+ img, target = self.transforms((img, target))
+
+ return img, target

code/ddp.py

@@ -0,0 +1,104 @@
+import os
+from datetime import datetime
+import argparse
+import torch.multiprocessing as mp
+import torchvision
+import torchvision.transforms as transforms
+import torch
+import torch.nn as nn
+import torch.distributed as dist
+from apex.parallel import DistributedDataParallel as DDP
+from apex import amp
+
+
+def main():
+ parser = argparse.ArgumentParser()
+ parser.add_argument('-n', '--nodes', default=1, type=int, metavar='N',
+ help='number of data loading workers (default: 4)')
+ parser.add_argument('-g', '--gpus', default=1, type=int,
+ help='number of gpus per node')
+ parser.add_argument('-nr', '--nr', default=0, type=int,
+ help='ranking within the nodes')
+ parser.add_argument('--epochs', default=2, type=int, metavar='N',
+ help='number of total epochs to run')
+ args = parser.parse_args()
+ args.world_size = args.gpus * args.nodes
+ os.environ['MASTER_ADDR'] = 'localhost'
+ os.environ['MASTER_PORT'] = '8888'
+ mp.spawn(train, nprocs=args.gpus, args=(args,))
+
+
+class ConvNet(nn.Module):
+ def __init__(self, num_classes=10):
+ super(ConvNet, self).__init__()
+ self.layer1 = nn.Sequential(
+ nn.Conv2d(1, 16, kernel_size=5, stride=1, padding=2),
+ nn.BatchNorm2d(16),
+ nn.ReLU(),
+ nn.MaxPool2d(kernel_size=2, stride=2))
+ self.layer2 = nn.Sequential(
+ nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2),
+ nn.BatchNorm2d(32),
+ nn.ReLU(),
+ nn.MaxPool2d(kernel_size=2, stride=2))
+ self.fc = nn.Linear(7*7*32, num_classes)
+
+ def forward(self, x):
+ out = self.layer1(x)
+ out = self.layer2(out)
+ out = out.reshape(out.size(0), -1)
+ out = self.fc(out)
+ return out
+
+
+def train(gpu, args):
+ rank = args.nr * args.gpus + gpu
+ dist.init_process_group(backend='nccl', init_method='env://', world_size=args.world_size, rank=rank)
+ torch.manual_seed(0)
+ model = ConvNet()
+ torch.cuda.set_device(gpu)
+ model.cuda(gpu)
+ batch_size = 100
+ # define loss function (criterion) and optimizer
+ criterion = nn.CrossEntropyLoss().cuda(gpu)
+ optimizer = torch.optim.SGD(model.parameters(), 1e-4)
+ # Wrap the model
+ model = nn.parallel.DistributedDataParallel(model, device_ids=[gpu])
+ # Data loading code
+ train_dataset = torchvision.datasets.MNIST(root='./data',
+ train=True,
+ transform=transforms.ToTensor(),
+ download=True)
+ train_sampler = torch.utils.data.distributed.DistributedSampler(train_dataset,
+ num_replicas=args.world_size,
+ rank=rank)
+ train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
+ batch_size=batch_size,
+ shuffle=False,
+ num_workers=0,
+ pin_memory=True,
+ sampler=train_sampler)
+
+ start = datetime.now()
+ total_step = len(train_loader)
+ for epoch in range(args.epochs):
+ for i, (images, labels) in enumerate(train_loader):
+ images = images.cuda(non_blocking=True)
+ labels = labels.cuda(non_blocking=True)
+ # Forward pass
+ outputs = model(images)
+ loss = criterion(outputs, labels)
+
+ # Backward and optimize
+ optimizer.zero_grad()
+ loss.backward()
+ optimizer.step()
+ if (i + 1) % 100 == 0 and gpu == 0:
+ print('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'.format(epoch + 1, args.epochs, i + 1, total_step,
+ loss.item()))
+ if gpu == 0:
+ print("Training complete in: " + str(datetime.now() - start))
+
+
+if __name__ == '__main__':
+ main()