What are Shape layers functions in lasagne layers?

Recipe Objective - What are Shape layers functions in lasagne layers?

Shape layers:-

1. ReshapeLayer - A layer reshaping its input tensor to another tensor of the same total number of elements.

2. reshape - alias of ReshapeLayer.

3. FlattenLayer - A layer that flattens its input.

4. flatten - alias of FlattenLayer.

5. DimshuffleLayer - A layer that rearranges the dimension of its input tensor.

6. dimshuffle - alias of DimshuffleLayer.

7. PadLayer - Pad all dimensions except the first "batch_ndim" with "width" zeros on both sides.

8. pad - alias of PadLayer.

9. SliceLayer - Slices the input at a specific axis and at specific indices.

For more related projects:-

/projects/data-science-projects/keras-deep-learning-projects
/projects/data-science-projects/neural-network-projects

Example:-

from lasagne.layers import InputLayer, ReshapeLayer, DimshuffleLayer, SliceLayer
ly_in = InputLayer((32, 100, 20))
ly1 = ReshapeLayer(ly_in, ((32, 50, 40)))
print(ly1.output_shape)

ly_in2 = InputLayer((None, 100, 20))
ly2 = ReshapeLayer(ly_in2, ([0], [1], 5, -1))
print(ly2.output_shape)

ly_in3 = InputLayer((2, 3, 5, 7))
ly3 = DimshuffleLayer(ly_in3, (3, 2, 1, 'x', 0))
print(ly3.output_shape)

ly_in4 = InputLayer((2, 3, 4))
print(SliceLayer(ly_in4, indices=0, axis=1).output_shape)