Day #225 - Pytorch Sessions (14-16)

	import torch
	import torchvision
	import torchvision.transforms as transforms
	#root - Location on disc
	#Training Set Data Preperation
	#Composition of Transformations
	train_set = torchvision.datasets.FashionMNIST(root = 'C:\Intel\Data', train=True, download=True,transform=transforms.Compose([transforms.ToTensor()]))
	train_loader = torch.utils.data.DataLoader(train_set, batch_size=10)
	import numpy as np
	import matplotlib.pyplot as plt
	print(len(train_set))
	print(train_set.train_labels)
	print(train_set.train_labels.bincount())
	sample = next(iter(train_set))
	print(len(sample))
	print(type(sample))
	image,label = sample
	print(image.shape)
	plt.imshow(image.squeeze(),cmap='gray')
	print('label:',label)
	batch = next(iter(train_loader))
	print(len(batch))
	print(type(batch))
	images,labels = batch
	print(images.shape)
	print(labels.shape)
	grid = torchvision.utils.make_grid(images,nrow=10)
	plt.figure(figsize=(15,15))
	plt.imshow(np.transpose(grid,(1,2,0)))
	print('labels:',labels)
	train_loader = torch.utils.data.DataLoader(train_set, batch_size=100)
	batch = next(iter(train_loader))
	images,labels = batch
	grid = torchvision.utils.make_grid(images,nrow=10)
	plt.figure(figsize=(15,15))
	plt.imshow(np.transpose(grid,(1,2,0)))
	print('labels:',labels)

view raw pytorch_data_load.py hosted with ❤ by GitHub

	#Prepare Data
	#Build Model
	#Train Model
	#Analyze Model
	#Extract from Data Source
	#Transform in Desirable format
	#Load the Data
	import torch
	import torchvision
	import torchvision.transforms as transforms
	#pytorch has dataset and dataloader
	class OHLC(Dataset):
	def __init__(self,csv_file):
	self.data = pd.read_csv(csv_file)
	def __getitem__(self,index):
	r = self.data.iloc[index]
	label = torch.tensor(r.is_up_day,dtype=torch.long)
	sample = self.normalize(torch.tensor([r.open,r.high,r.low,r.close]))
	return sample,label
	def __len__(self):
	return len(self.data)

view raw pytorch_225.py hosted with ❤ by GitHub

Happy Mastering DL!!!