【发布时间】：2021-08-22 13:20:48
【问题描述】：
我的记忆力有很大问题。我正在开发一个带有 GUI 的大型应用程序，用于测试和优化神经网络。主程序显示 GUI，但训练是在线程中完成的。在我的应用程序中，我需要一个接一个地训练许多具有不同参数的模型。为此，我需要为每次尝试创建一个模型。当我训练一个时，我想删除它并训练新的，但我不能删除旧模型。我正在尝试做这样的事情：
del model
torch.cuda.empty_cache()
但 GPU 内存不会改变，
然后我尝试这样做：
model.cpu()
del model
当我将模型移动到 CPU 时，GPU 内存被释放但 CPU 内存增加。 在每次训练尝试中，记忆力一直在增加。只有当我关闭我的应用程序并再次运行它时，所有内存才会被释放。
有没有办法从 GPU 或 CPU 中永久删除模型？
编辑： 代码：
线程，训练过程取悦：
class uczeniegridsearcch(QObject):
endofoneloop = pyqtSignal()
endofonesample = pyqtSignal()
finished = pyqtSignal()
def __init__(self, train_loader, test_loader, epoch, optimizer, lenoftd, lossfun, numberofsamples, optimparams, listoflabels, model_name, num_of_class, pret):
super(uczeniegridsearcch, self).__init__()
self.train_loaderup = train_loader
self.test_loaderup = test_loader
self.epochup = epoch
self.optimizername = optimizer
self.lenofdt = lenoftd
self.lossfun = lossfun
self.numberofsamples = numberofsamples
self.acc = 0
self.train_loss = 0
self.sendloss = 0
self.optimparams = optimparams
self.listoflabels = listoflabels
self.sel_Net = model_name
self.num_of_class = num_of_class
self.sel_Pret = pret
self.modelforsend = []
def setuptrainmodel(self):
if self.sel_Net == "AlexNet":
model = models.alexnet(pretrained=self.sel_Pret)
model.classifier[6] = torch.nn.Linear(4096, self.num_of_class)
elif self.sel_Net == "ResNet50":
model = models.resnet50(pretrained=self.sel_Pret)
model.fc = torch.nn.Linear(model.fc.in_features, self.num_of_class)
elif self.sel_Net == "VGG13":
model = models.vgg13(pretrained=self.sel_Pret)
model.classifier[6] = torch.nn.Linear(model.classifier[6].in_features, self.num_of_class)
elif self.sel_Net == "DenseNet201":
model = models.densenet201(pretrained=self.sel_Pret)
model.classifier = torch.nn.Linear(model.classifier.in_features, self.num_of_class)
elif self.sel_Net == "MNASnet":
model = models.mnasnet1_0(pretrained=self.sel_Pret)
model.classifier[1] = torch.nn.Linear(model.classifier[1].in_features, self.num_of_class)
elif self.sel_Net == "ShuffleNet v2":
model = models.shufflenet_v2_x1_0(pretrained=self.sel_Pret)
model.fc = torch.nn.Linear(model.fc.in_features, self.num_of_class)
elif self.sel_Net == "SqueezeNet":
model = models.squeezenet1_0(pretrained=self.sel_Pret)
model.classifier[1] = torch.nn.Conv2d(512, self.num_of_class, kernel_size=(1, 1), stride=(1, 1))
model.num_classes = self.num_of_class
elif self.sel_Net == "GoogleNet":
model = models.googlenet(pretrained=self.sel_Pret)
model.fc = torch.nn.Linear(model.fc.in_features, self.num_of_class)
return model
def train(self):
for x in range(self.numberofsamples):
torch.cuda.empty_cache()
modelup = self.setuptrainmodel()
device = torch.device('cuda')
optimizerup = TableWidget.setupotimfun(self, modelup, self.optimizername, self.optimparams[(x, 0)],
self.optimparams[(x, 1)], self.optimparams[(x, 2)],
self.optimparams[(x, 3)],
self.optimparams[(x, 4)], self.optimparams[(x, 5)])
modelup = modelup.to(device)
best_accuracy = 0.0
train_error_count = 0
for epoch in range(self.epochup):
for images, labels in iter(self.train_loaderup):
images = images.to(device)
labels = labels.to(device)
optimizerup.zero_grad()
outputs = modelup(images)
loss = TableWidget.setuplossfun(self, lossfun=self.lossfun, outputs=outputs, labels=labels)
self.train_loss += loss
loss.backward()
optimizerup.step()
train_error_count += float(torch.sum(torch.abs(labels - outputs.argmax(1))))
self.train_loss /= len(self.train_loaderup)
test_error_count = 0.0
for images, labels in iter(self.test_loaderup):
images = images.to(device)
labels = labels.to(device)
outputs = modelup(images)
test_error_count += float(torch.sum(torch.abs(labels - outputs.argmax(1))))
test_accuracy = 1.0 - float(test_error_count) / float(self.lenofdt)
print('%s, %d,%d: %f %f' % ("Próba nr:", x+1, epoch, test_accuracy, self.train_loss), "Parametry: ", self.optimparams[x,:])
self.acc = test_accuracy
self.sendloss = self.train_loss.item()
self.endofoneloop.emit()
self.endofonesample.emit()
modelup.cpu()
del modelup,optimizerup,device,test_accuracy,test_error_count,train_error_count,loss,labels,images,outputs
torch.cuda.empty_cache()
self.finished.emit()
我如何在主块中调用线程：
self.qtest = uczeniegridsearcch(self.train_loader,self.test_loader, int(self.InputEpoch.text()),
self.sel_Optim,len(self.test_dataset), self.sel_Loss,
int(self.numberofsamples.text()), self.params, self.listoflabels,
self.sel_Net,len(self.sel_ImgClasses),self.sel_Pret)
self.qtest.endofoneloop.connect(self.inkofprogress)
self.qtest.endofonesample.connect(self.inksamples)
self.qtest.finished.connect(self.prints)
testtret = threading.Thread(target=self.qtest.train)
testtret.start()
【问题讨论】：
标签： python memory pytorch gpu cpu