Ufdjrw

I am trying to use AutoGrad to calculate the derivative of a certain piece of code.
A part of this code, consists of a Neural Network implemented in PyTorch.
However, I have some troubles to use AutoGrad to calculate the derivative of my NN.

I created a small script to reproduce the problem :

import torch
import autograd.numpy as np
from autograd import grad

inputDimension = 10
hiddenLayerDimension = 10
outputDimension = 1

model = torch.nn.Sequential(
 torch.nn.Linear(inputDimension, hiddenLayerDimension),
 torch.nn.ReLU(),
 torch.nn.Linear(hiddenLayerDimension, outputDimension),
)

def functionToDifferentiate(input):
 # This line below represents the 'other' calculations. In reality it is more involved
 scaledInput = input * 3
 inputTensor = torch.from_numpy(scaledInput).type(torch.FloatTensor)
 return model(inputTensor)

randomInput = np.random.rand(inputDimension)
gradientFunctionOfModel = grad(functionToDifferentiate)

print(functionToDifferentiate(randomInput))
print(gradientFunctionOfModel(randomInput))

When running this code, the last line crashes with the following stack trace:

Traceback (most recent call last):
 File "replaced_for_privacy_reasons/stackOverFlowQuestion.py", line 25, in <module>
 print(gradientFunctionOfModel(randomInput))
 File "replaced_for_privacy_reasons/venv/lib/python3.6/site-packages/autograd/wrap_util.py", line 20, in nary_f
 return unary_operator(unary_f, x, *nary_op_args, **nary_op_kwargs)
 File "replaced_for_privacy_reasons/venv/lib/python3.6/site-packages/autograd/differential_operators.py", line 24, in grad
 vjp, ans = _make_vjp(fun, x)
 File "replaced_for_privacy_reasons/venv/lib/python3.6/site-packages/autograd/core.py", line 10, in make_vjp
 end_value, end_node = trace(start_node, fun, x)
 File "replaced_for_privacy_reasons/venv/lib/python3.6/site-packages/autograd/tracer.py", line 10, in trace
 end_box = fun(start_box)
tensor([0.0228], grad_fn=<AddBackward0>)
 File "replaced_for_privacy_reasons/venv/lib/python3.6/site-packages/autograd/wrap_util.py", line 15, in unary_f
 return fun(*subargs, **kwargs)
 File "replaced_for_privacy_reasons/stackOverFlowQuestion.py", line 18, in functionToDifferentiate
 inputTensor = torch.from_numpy(input).type(torch.FloatTensor)
TypeError: expected np.ndarray (got ArrayBox)

I do know that it is possible to create my inputs directly as PyTorch Tensors, instead of as Numpy vectors and calculate gradients wrt to those vectors.
This is however not a good option for me, since this Neural Network is only part of a complete function for which I want to calculate the Gradient.

Any help is highly appreciated