FSP matrix op
This op is used to calculate the flow of solution procedure (FSP) matrix of two 4-D Tensor feature maps. Given feature map x with shape [x_channel, h, w] and feature map y with shape [y_channel, h, w], we can get the fsp matrix of x and y in two steps:
reshape x into matrix with shape [x_channel, h * w] and reshape and transpose y into matrix with shape [h * w, y_channel].
multiply x and y to get fsp matrix with shape [x_channel, y_channel].
The output is a batch of fsp matrices.
x (Variable) – A 4-D Tensor feature map with shape [batch_size, x_channel, height, width]. A Tensor with type float32, float64.
y (Variable) – A 4-D Tensor feature map with shape [batch_size, y_channel, height, width]. The y_channel can be different with the x_channel of Input(X) while the other dimensions must be the same with Input(X)’s. A Tensor with type float32, float64.
The output of FSP op with shape [batch_size, x_channel, y_channel]. The x_channel is the channel of x and the y_channel is the channel of y. A Tensor with type float32, float64.
- Return type
fsp matrix (Variable)
import paddle.fluid as fluid data = fluid.data(name='data', shape=[None, 3, 32, 32]) feature_map_0 = fluid.layers.conv2d(data, num_filters=2, filter_size=3) feature_map_1 = fluid.layers.conv2d(feature_map_0, num_filters=2, filter_size=1) loss = fluid.layers.fsp_matrix(feature_map_0, feature_map_1)