The function of tf.reshape(tensor, shape, name=None)
is to transform tensor into the form of parameter shape.
The shape is in the form of a list, and the special point is that -1 can exist in the list. The meaning of -1 is that we do not need to specify the size of this dimension ourselves, the function will automatically calculate, but there can only be one -1 in the list. (Of course, if there are multiple -1s, it is an equation with multiple solutions)
Well, another important point I want to say is how to transform the matrix according to the shape. In fact, the simple thought is,
reshape(t, shape) => reshape(t, [-1]) => reshape(t, shape)
First change the matrix t into a one-dimensional matrix, and then change the form of the matrix.
Official example:
# tensor 't' is [1, 2, 3, 4, 5, 6, 7, 8, 9] # tensor 't' has shape [9] reshape(t, [3, 3]) ==> [[1, 2, 3], [4, 5, 6], [7, 8, 9]] # tensor 't' is [[[1, 1], [2, 2]], # [[3, 3], [4, 4]]] # tensor 't' has shape [2, 2, 2] reshape(t, [2, 4]) ==> [[1, 1, 2, 2], [3, 3, 4, 4]] # tensor 't' is [[[1, 1, 1], # [2, 2, 2]], # [[3, 3, 3], # [4, 4, 4]], # [[5, 5, 5], # [6, 6, 6]]] # tensor 't' has shape [3, 2, 3] # pass '[-1]' to flatten 't' reshape(t, [-1]) ==> [1, 1, 1, 2, 2, 2, 3, 3, 3, 4, 4, 4, 5, 5, 5, 6, 6, 6] # -1 can also be used to infer the shape # -1 is inferred to be 9: reshape(t, [2, -1]) ==> [[1, 1, 1, 2, 2, 2, 3, 3, 3], [4, 4, 4, 5, 5, 5, 6, 6, 6]] # -1 is inferred to be 2: reshape(t, [-1, 9]) ==> [[1, 1, 1, 2, 2, 2, 3, 3, 3], [4, 4, 4, 5, 5, 5, 6, 6, 6]] # -1 is inferred to be 3: reshape(t, [ 2, -1, 3]) ==> [[[1, 1, 1], [2, 2, 2], [3, 3, 3]], [[4, 4, 4], [5, 5, 5], [6, 6, 6]]] # tensor 't' is [7] # shape `[]` reshapes to a scalar reshape(t, []) ==> 7