lua - 如何使用 Torch 生成的模型进行预测？

Question

我已经执行了 neuralnetwork_tutorial.lua .现在我有了模型，我想用我自己的一些手写图像来测试它。但是我已经尝试了很多方法来存储权重，现在通过使用 torch save and load methods 来存储完整的模型。 .

但是现在我尝试使用 model:forward(testImageTensor)

预测我自己的手写图像(转换为 28X28 DoubleTensor)

...ches/torch/install/share/lua/5.1/dp/model/sequential.lua:30: attempt to index local 'carry' (a nil value)
stack traceback:
        ...ches/torch/install/share/lua/5.1/dp/model/sequential.lua:30: in function '_forward'
        ...s/torches/torch/install/share/lua/5.1/dp/model/model.lua:60: in function 'forward'
        [string "model:forward(testImageTensor)"]:1: in main chunk
        [C]: in function 'xpcall'
        ...aries/torches/torch/install/share/lua/5.1/trepl/init.lua:588: in function 'repl'
        ...ches/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:185: in main chunk
        [C]: at 0x0804d650

Answer 1

您有两个选择。

一个。使用封装的 nn.Module转发你的torch.Tensor :

mlp2 = mlp:toModule(datasource:trainSet():sub(1,2))
input = testImageTensor:view(1, 1, 32, 32)
output = mlp2:forward(input)

两个。将您的 torch.Tensor 封装到 dp.ImageView 中并通过您的 dp.Model 转发:

inputView = dp.ImageView('bchw', testImageTensor:view(1, 1, 32, 32))
outputView = mlp:forward(inputView, dp.Carry{nSample=1})
output = outputView:forward('b')