所以我现在正在学习神经网络,我注意到我的网络中有一些非常奇怪的东西。我有一个像这样创建的输入层
convN1 = register_module("convN1", torch::nn::Conv2d(torch::nn::Conv2dOptions(4, 256, 3).padding(1)));
和一个输出层,它是一个 tanh 函数。
所以它期待一个形状为 {/ batchSize /, 4, / sideLength /, / sideLength / } 的 torch::Tensor,它将输出一个只有 1 个浮点值的张量。
因此,为了进行测试,我创建了一个形状为 {4, 15, 15} 的自定义张量。
真正奇怪的部分是下面发生的事情
auto inputTensor = torch::zeros({ 1, 4, 15, 15});
inputTensor[0] = customTensor;
std::cout << network->forward(inputTensor); // Outputs something like 0.94142
inputTensor = torch::zeros({ 32, 4, 15, 15});
inputTensor[0] = customTensor;
std::cout << network->forward(inputTensor); // Outputs something like 0.1234 then 0.8543 31 times
那么为什么 customTensor 从我的网络中获得 2 个不同的值只是因为批量大小发生了变化?我不了解张量如何工作的某些部分吗?
PS我确实检查了上面的代码块在评估模式下运行。
编辑:既然有人问过这里,请更深入地了解我的网络
convN1 = register_module("convN1", torch::nn::Conv2d(torch::nn::Conv2dOptions(4, 256, 3).padding(1)));
batchNorm1 = register_module("batchNorm1", torch::nn::BatchNorm2d(torch::nn::BatchNormOptions(256)));
m_residualBatch1 = register_module(batch1Name, torch::nn::BatchNorm2d(torch::nn::BatchNormOptions(256)));
m_residualBatch2 = register_module(batch2Name, torch::nn::BatchNorm2d(torch::nn::BatchNormOptions(256)));
m_residualConv1 = register_module(conv1Name, torch::nn::Conv2d(torch::nn::Conv2dOptions(256, 256, 3).padding(1)));
m_residualConv2 = register_module(conv2Name, torch::nn::Conv2d(torch::nn::Conv2dOptions(256, 256, 3).padding(1)));
valueN1 = register_module("valueN1", torch::nn::Conv2d(256, 2, 1));
batchNorm3 = register_module("batchNorm3", torch::nn::BatchNorm2d(torch::nn::BatchNormOptions(2)));
valueN2 = register_module("valueN2", torch::nn::Linear(2 * BOARD_LENGTH, 64));
valueN3 = register_module("valueN3", torch::nn::Linear(64, 1));
它是如何前进的
torch::Tensor Net::forwadValue(torch::Tensor x)
{
x = convN1->forward(x);
x = batchNorm1->forward(x);
x = torch::relu(x);
torch::Tensor residualCopy = x.clone();
x = m_residualConv1->forward(x);
x = m_residualBatch1->forward(x);
x = torch::relu(x);
x = m_residualConv2->forward(x);
x = m_residualBatch2->forward(x);
x += residualCopy;
x = torch::relu(x);
x = valueN1->forward(x);
x = batchNorm3->forward(x)
x = torch::relu(x);
x = valueN2->forward(x.reshape({ x.sizes()[0], 30 }))
x = torch::relu(x);
x = valueN3->forward(x)
return torch::tanh(x);
}