인공지능 공부/pytorch
(2022.07.06) Pytorch Car Object Detection
import cv2 import numpy as np import pandas as pd import matplotlib.pyplot as plt import albumentations as A from albumentations.pytorch.transforms import ToTensorV2 import torch from torch.utils.data import Dataset, DataLoader from torchvision.models.detection.faster_rcnn import FastRCNNPredictor from torchvision.models.detection import FasterRCNN from torchvision.models.detection import faster..
(2022.07.04) Rcnn Fruit object detection (pytorch)
import pandas as pd import numpy as np import os import random import matplotlib.pyplot as plt import matplotlib.patches as patches import cv2 import torch import torchvision from torchvision import transforms, datasets from torchvision.models.detection import * from torchvision.models.detection.faster_rcnn import FastRCNNPredictor from torch.utils.data import Dataset # from engine import train_..
(2022.07.03) Brain Tumor MRI detection
import numpy as np import matplotlib.pyplot as plt import torch import torch.nn as nn import torchvision.transforms as transforms from PIL import Image import gc from sklearn.model_selection import train_test_split import os dataset_path = './practic_torch/data/brain_tumor_dataset' paths = [] labels = [] # os.walk()는 하위의 폴더들을 for문으로 탐색 for label in ['yes','no']: for dirname, _, filenames in os.w..
(2022.07.01) Pytorch Rice Classification
import torch import torch.nn as nn import torch.nn.functional as F import torch.optim as optim import torch.utils.data as data from torch.optim import Adam import torchvision.transforms as transforms import torchvision.datasets as datasets from torch.utils.data import DataLoader from torch.utils.data import Dataset from random import randint from PIL import Image import matplotlib.pyplot as plt ..
(2022.07.01) CNN
import torch import torch.nn as nn import torch.nn.functional as F import torchvision import torchvision.transforms as transforms import matplotlib.pyplot as plt import numpy as np # Device configuration device = torch.device("cuda:0" if torch.cuda.is_available() else 'cpu') # Hyoer-parameters num_epochs = 4 batch_size = 4 learning_rate = 0.001 # dataset has PILImage images of range [0, 1]. # We..
(2022.07.01) Feed Forward Net
import torch import torch.nn as nn import torchvision import torchvision.transforms as transforms import matplotlib.pyplot as plt #device config device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu') #hyper parmameters input_size = 784 # 28*28 hidden_size = 100 num_classes = 10 num_epochs = 2 batch_size = 100 learning_rate = 0.001 #MNIST train_dataset = torchvision.datasets.MNIS..
(2022.06.30) Dataset and Dataloader
''' epoch = 1 forward and backward pass of ALL training samples batch_size = number of training samples in one forward & backward pass number of = iterations = number of passes, each pass using [batch_size] number of sampeles e.g. 100 samples, batch_size = 20 --> 100/20 = 5 iterations for 1 epoch ''' import torch import torchvision from torch.utils.data import Dataset, DataLoader import numpy as..
(2022.06.30) pytorch linear_regression
''' 1) Design model(input, output, forward pass) 2) Construct loss and optimizer 3) Traning loop - forward pass : compute prediction and loss - backward pass : gradients - updata weights ''' import torch import torch.nn as nn import numpy as np from sklearn import datasets from sklearn.preprocessing import StandardScaler from sklearn.model_selection import train_test_split # prepare data bc = da..