theano中的共享变量索引错误

Question

共享变量索引存在问题。

train_set_x的形状为(n, 3, 50176)，n大于index

我可以使用以下代码从共享变量 train_set_x 中获取值

train_set_x.get_value(borrow=True)[index]

array([[ 143., 142., 142., ..., 141., 141., 145.], [ 114., 113., 113., ..., 141., 141., 145.], [ 108., 107., 107., ..., 139., 139., 143.]], dtype=float32)

但我无法通过以下代码获得价值

check = theano.function([index], x, givens = {x : train_set_x[index]})
check(index)

显示错误信息

*** IndexError: index out of bounds
Apply node that caused the error: GpuSubtensor{int64}(<CudaNdarrayType(float32, 3D)>, ScalarFromTensor.0)
Toposort index: 1
Inputs types: [CudaNdarrayType(float32, 3D), Scalar(int64)]
Inputs shapes: [(1039, 3, 50176), ()]
Inputs strides: [(150528, 50176, 1), ()]
Inputs values: ['not shown', 1039]
Outputs clients: [[HostFromGpu(GpuSubtensor{int64}.0)]]

HINT: Re-running with most Theano optimization disabled could give you a back-trace of when this node was created. This can be done with by setting the Theano flag 'optimizer=fast_compile'. If that does not work, Theano optimizations can be disabled with 'optimizer=None'.
HINT: Use the Theano flag 'exception_verbosity=high' for a debugprint and storage map footprint of this apply node.

它们之间有什么区别？以及将 train_set_x 中的值与 theano.function 一起使用的方法是什么？

Answer 1

Inputs values: ['not shown', 1039] 显示作为索引参数传递的值（它是 1039），Inputs shapes: [(1039, 3, 50176), ()] 行显示您的 n 是 1039。

所以看起来你真的像 theano 所说的那样越界了。 以下示例适用于我：

train_set_x = theano.shared(np.random.rand(10, 3, 3))
x = theano.tensor.matrix()
index = theano.tensor.iscalar()
check = theano.function([index], x, givens = {x : train_set_x[index]}
check(3)

虽然check(10) 显示非常相似的错误：

IndexError: index out of bounds
Apply node that caused the error: Subtensor{int32}(<TensorType(float64, 3D)>, ScalarFromTensor.0)
Toposort index: 1
Inputs types: [TensorType(float64, 3D), Scalar(int32)]
Inputs shapes: [(10, 3, 3), ()]
Inputs strides: [(72, 24, 8), ()]
Inputs values: ['not shown', 10]
Outputs clients: [[DeepCopyOp(Subtensor{int32}.0)]]

HINT: Use the Theano flag 'exception_verbosity=high' for a debugprint and storage map footprint of this apply node