qqyouhappy的博客

Pytorch参考torchtorch torch.Tensor torch.Storage torch.nn torch.nn.functional torch.nn.init torch.optim torch.autograd torch.multiprocessing torch.legacy torch.cuda torch.utils.ffi torch.utils.data torch.utils.model_zootorchvisiontorchvis

1.查看GPUnvidia-smi2.安装CUDAhttps://developer.nvidia.com/cuda-downloads下载相应版本，需要先安装合适的GCC版本。将CUDA添加到环境变量sudo gedit ~/.bashrc export PATH=/usr/local/cuda-10.2/bin${PATH:+:$PATH}} export LD_LIBRARY_PATH=/usr/local/cuda-10.2/lib64${LD_LIBRARY_PA

查看Tensor中的元素总个数，可使用Tensor.numel()或者Tensor.nelement()函数，两者等价。

class SimpleCNN(nn.Module): def __init__(self): super(SimpleCNN, self).__init__() layer1 = nn.Sequential() #class torch.nn.Conv2d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True) ...

待续

1.常规class Logistic_regression_1(nn.Module): def __init__(self): super(Logistic_regression_1, self).__init__() self.lr = nn.Linear(2, 1) self.sm = nn.Sigmoid() def forward(self, x): x = self.lr(x) x = s...

读取数据加载数据定义模型初始化模型定义损失函数优化函数

Tensor张量类型 CPU and GPU PyTorch and NumPy Variables变量 Back Propagation1.Pytorch的Tensor 数据类型有32 位浮点型 torch.FloatTensor 、 64 位浮点型 torch.DoubleTensor 、 16 位整型 torch.ShortTensor 、 32 位整型 torch.lntTens...

# CPU Onlyconda install pytorch==1.2.0 torchvision==0.4.0 cpuonly -c pytorch# CPU Onlyconda install pytorch==1.2.0 torchvision==0.4.0 cpuonly