首先,我曾使用过像'model.cuda()'这样的模型和数据转换为cuda。但是它仍然有这样的问题。我调试模型的每一层,每个模块的权重为iscuda = True。那么有人知道为什么会出现这样的问题吗?
我有两种模型,一种是resnet50,另一种包含第一个模型作为主干。
class FC_Resnet(nn.Module):
def __init__(self, model, num_classes):
super(FC_Resnet, self).__init__()
# feature encoding
self.features = nn.Sequential(
model.conv1,
model.bn1,
model.relu,
model.maxpool,
model.layer1,
model.layer2,
model.layer3,
model.layer4)
# classifier
num_features = model.layer4[1].conv1.in_channels
self.classifier = nn.Sequential(
nn.Conv2d(num_features, num_classes, kernel_size=1, bias=True))
def forward(self, x):
# children=self.features.children()
# for child in children:
# if child.weight is not None:
# print(child.weight.device)
x = self.features(x)
x = self.classifier(x)
return x
def fc_resnet50(num_classes=20, pre_trained=True):
model = FC_Resnet(models.resnet50(pre_trained), num_classes)
return model
还有一个:
class PeakResponseMapping(nn.Sequential):
def __init__(self, *args, **kargs):
super(PeakResponseMapping, self).__init__(*args)
...
def forward(self, input, class_threshold=0, peak_threshold=30, retrieval_cfg=None):
assert input.dim() == 4
if self.inferencing:
input.requires_grad_()
class_response_maps = super(PeakResponseMapping, self).forward(input)
return class_response_maps
主要很简单:
def main():
dataset = VOC(img_transform=image_transform())
dataloader = DataLoader(dataset, batch_size=BATCH_SIZE, shuffle=True)
model = peak_response_mapping(fc_resnet50(), win_size=3, sub_pixel_locating_factor=8, enable_peak_stimulation=True)
model=model.cuda()
for step, (b_x, b_y) in enumerate(dataloader):
b_x.cuda()
b_y.cuda()
result = model.forward(b_x)
答案 0 :(得分:1)
您需要将b_x.cuda()
分配回b_x
:
b_x = b_x.cuda()
b_y = b_y.cuda()
查看.cuda()
的文档:
在CUDA内存中返回此对象的副本。
因此,b_x.cuda()
返回b_x
的副本,并且不会以就地 的方式影响b_x
。< / p>
答案 1 :(得分:1)
在堆栈跟踪中的某个地方,Torch期望使用CPU张量(torch.FloatTensor
),但正在获得GPU / CUDA张量(torch.cuda.FloatTensor
)。
给出张量tensor
:
tensor.to('cpu')
返回张量的CPU版本tensor.to('cuda')
返回张量的CUDA版本要编写与硬件无关的代码:
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
那么您可以做:
tensor.to(device)
对于OP,它变为:
result = model.forward(b_x.to(device))