#我使用GPU加速时出现了问题,我的cpu被占满了,我的GPU的使用率一上一下的
#以下是我的代码:
import numpy as np
import matplotlib.pyplot as plt
import torch
from torch.utils.data import Dataset
from torch.utils.data import DataLoader
import os
os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"
# print(torch.cuda.is_available()) # True
# # 查看GPU数量,索引号从0开始
# print(torch.cuda.current_device()) # 0
# # 根据索引号查看GPU名字
# print(torch.cuda.get_device_name(0)) # NVIDIA GeForce GTX 1050 Ti
# 定义训练设备
device = torch.device("cuda") #使用gpu
#prepare dataset
class DiabetsDataset(Dataset):
def __init__(self,filepath):
xy = np.loadtxt(filepath,delimiter=',',dtype=np.float32)
self.len = xy.shape[0] #shape会返回xy的长度,如果xy是二维shape[0]就是行数,shape[1]就是列数
self.x_data = torch.from_numpy(xy[:,:-1])
self.y_data = torch.from_numpy(xy[:, [-1]])
def __getitem__(self, index):
return self.x_data[index],self.y_data[index]
def __len__(self):
return self.len
dataset = DiabetsDataset('diabetes.csv')
train_loader = DataLoader(dataset=dataset,batch_size=32,shuffle=True,num_workers=8)
#bulid model
class Model(torch.nn.Module):
def __init__(self):
super(Model,self).__init__()
self.linear1 = torch.nn.Linear(8, 6)
self.linear2 = torch.nn.Linear(6, 4)
self.linear3 = torch.nn.Linear(4, 1)
self.sigmoid = torch.nn.Sigmoid()
def forward(self,x):
x = self.sigmoid(self.linear1(x))
x = self.sigmoid(self.linear2(x))
x = self.sigmoid(self.linear3(x))
return x
model = Model()
model.to(device) #将模型用到gpu
#LOSS and OPTIMIZER
criterion = torch.nn.BCELoss(reduction='mean')
criterion.to(device) #将损失函数放到GPU
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)
#train cycle
# training cycle forward, backward, update
if __name__ == '__main__':
for epoch in range(100):
for i, data in enumerate(train_loader, 0): # train_loader 是先shuffle后mini_batch
inputs, labels = data
inputs = inputs.to(device) #将数据放到GPU
labels = labels.to(device)#将数据放到GPU
y_pred = model(inputs)
loss = criterion(y_pred, labels)
print(epoch, i, loss.item())
optimizer.zero_grad()
loss.backward()
optimizer.step()