Ali Waqas aliwaqas333

🎯

Focusing

aliwaqas333 / rledata.json

Created November 7, 2022 02:19

sample rle format

aliwaqas333 / install.sh

Created June 2, 2022 18:36 — forked from HoKim98/install.sh

[Ubuntu] OpenVSLAM automatic installation script

	#!/bin/bash

	cd ~/Desktop

	# ---------------------------
	## 0. Requirements
	# ---------------------------
	sudo apt-get update
	sudo apt-get install -y build-essential git pkg-config cmake make \
	gcc curl wget unzip \

aliwaqas333 / image_test.py

Created June 19, 2020 10:37

functions to test custom images

	def singleImage(path, label= None, show= False):
	img = cv2.imread(path)
	assert img is not None,"Immage wasn't read properly"
	img = cv2.resize(img, (100, 100))
	img = torch.from_numpy(img)
	img = img.permute((2, 0,1)) # model expects image to be of shape [3, 100, 100]
	img = img.unsqueeze(dim=0).float() # convert single image to batch [1, 3, 100, 100]
	img = img.to('cuda') # Using the same device as the model
	pred = model(img)
	_, preds = torch.max(pred, dim=1)

aliwaqas333 / model_fit.py

Last active June 19, 2020 10:31

	@torch.no_grad()
	def evaluate(model, val_loader):
	model.eval()
	outputs = [model.validation_step(batch) for batch in val_loader]
	return model.validation_epoch_end(outputs)

	def fit(epochs, lr, model, train_loader, val_loader, opt_func=torch.optim.SGD):
	history = []
	optimizer = torch.optim.SGD(model.parameters(), lr=0.001, momentum=0.9)
	for epoch in range(epochs):

aliwaqas333 / tocuda.py

Created June 19, 2020 10:28

basic function for GPU feature in PyTorch

	def get_default_device():
	"""Pick GPU if available, else CPU"""
	if torch.cuda.is_available():
	return torch.device('cuda')
	else:
	return torch.device('cpu')

	device = get_default_device()

	def to_device(data, device):

aliwaqas333 / imageClassification.py

Created June 19, 2020 10:14

Image Classification base class

	class ImageClassificationBase(nn.Module):
	def training_step(self, batch):
	images, labels = batch
	out = self(images) # Generate predictions
	loss = F.cross_entropy(out, labels.long()) # Calculate loss
	return loss

	def validation_step(self, batch):
	images, labels = batch
	out = self(images) # Generate predictions

aliwaqas333 / model.py

Created June 19, 2020 09:46

model creation

	class MaskDetection(ImageClassificationBase):
	def __init__(self):
	super().__init__()
	self.network = nn.Sequential(
	nn.Conv2d(3, 100, kernel_size=3, padding=1),
	nn.ReLU(),
	nn.Conv2d(100, 128, kernel_size=3, stride=1, padding=1),
	nn.ReLU(),
	nn.MaxPool2d(2, 2), # output: 128 x 8 x 8

aliwaqas333 / data_loader_creation.py

Created June 19, 2020 09:27

To create a dataloader in PyTorch

	from torch.utils.data.dataloader import DataLoader
	from torchvision.utils import make_grid
	batch_size = 32

	train_dl = DataLoader(train_ds, batch_size*2, shuffle=True)
	val_dl = DataLoader(val_ds, batch_size*2)

aliwaqas333 / dataset_creation.py

Last active June 19, 2020 09:24

We will use pytorch Dataset Class to create our dataset

	from torch.utils.data.dataset import Dataset
	from torchvision.transforms import Compose, ToTensor
	class MaskDataset(Dataset):
	""" Masked faces dataset
	0 = 'no mask'
	1 = 'mask'
	"""
	def __init__(self, train_data):
	self.train_data = train_data
	self.transformations = Compose([

aliwaqas333 / data_extraction.py

Created June 19, 2020 09:08

This class is used to extract images from various directories

	REBUILD_DATA = True

	if REBUILD_DATA: #if we are running it for the first time
	data_path = Path('F:/FILES/AI/face-mask-dataset/')
	maskPath = data_path/'dataset1/AFDB_masked_face_dataset'
	maskPath2= data_path/'dataset2/webface_masked'
	nonMaskPath = data_path/'dataset1/AFDB_face_dataset'
	path_dirs = [ [maskPath,1],[nonMaskPath,0] ] #path and label
	if not os.path.exists(data_path):
	raise Exception("The data path doesn't exist")