PyTensor utils

compile(inputs, outputs[, random_seed, mode])	Use pytensor.function with specialized pymc rewrites always enabled.
gradient(f[, vars])
hessian(f[, vars, negate_output])
hessian_diag(f[, vars, negate_output])
jacobian(f[, vars])
inputvars(a)	Get the inputs into PyTensor variables.
cont_inputs(a)	Get the continuous inputs into PyTensor variables.
floatX(X)	Convert a PyTensor tensor or numpy array to pytensor.config.floatX type.
intX(X)	Convert a pytensor tensor or numpy array to pytensor.tensor.int32 type.
constant_fold(xs[, raise_not_constant])	Use constant folding to get constant values of a graph.
CallableTensor(tensor)	Turns a symbolic variable with one input into a function that returns symbolic arguments with the one variable replaced with the input.
join_nonshared_inputs(point, outputs, inputs)	Create new outputs and input TensorVariables where the non-shared inputs are joined in a single raveled vector input.
make_shared_replacements(point, vars, model)	Make shared replacements for all other variables than the ones passed.
convert_data(data)