# Gradient of learnable circuit parameters is None when using torch interface

**URL:** <https://discuss.pennylane.ai/t/gradient-of-learnable-circuit-parameters-is-none-when-using-torch-interface/924>\
**Category:** PennyLane Help\
**Created:** [March 16, 2021, 12:34pm UTC](https://discuss.pennylane.ai/t/gradient-of-learnable-circuit-parameters-is-none-when-using-torch-interface/924 "2021-03-16T12:34:00Z")\
**Posts on this page:** 6\
**Page:** 1

<div class="post-metadata">

**Author:** ![Yang](https://yyz2.discourse-cdn.com/flex012/user_avatar/discuss.pennylane.ai/yang/32/489_2.png) [@Yang](https://discuss.pennylane.ai/u/Yang)\
**Post date:** [March 16, 2021, 12:34pm UTC](https://discuss.pennylane.ai/t/gradient-of-learnable-circuit-parameters-is-none-when-using-torch-interface/924/1 "2021-03-16T12:34:00Z")

</div>

Hi, I am implementing QCNN based on pennylane. For flexibility, I choose the torch interface. The forward process seems going well. However, when I check the gradient of circuit parameters, I find some of them is None, which results in that these parameters will not get updated during optimization.

Here is my code example.

```python
def qconv_kernel(phi, params):
    '''
    Implementation of quantum convolution kernel circuit
    ------------------------------------------
    :param phi: image pixels, [n_quibits]
    :param params: learnable convolutional weights, [n_layers * n_qubits]
    '''
    # quantum circuit implemention here
    return qml.expval(qml.PauliZ(wires=0))

def qconv_torch(inputs, params, qnode, n_in_channels=1, kernel_size=[2, 2], stride=None, padding=False):
    """
    Convolves the input image with many applications of the same quantum circuit.
    ------------------------------------------------------------------------
    :param inputs: input image, [C, H, W]
    :param params: learnable convolutional weights, [n_out_channels, n_layers * n_qubits]
    :param qnode: QNode object
    :param n_in_channels: input channels of previous layer
    :param kernel_size: size of qconv kernel, [kernel_h, kernel_w]
    :param stride: step of qconv, [stride_h, stride_w]
    :param padding: whether padding, bool
    return a new image, [C_out, H_out, W_out]
    """
    for j in range(0, in_h-kernel_size[0], stride[0]):
        for k in range(0, in_w-kernel_size[1], stride[1]):
            channel_results = []
            for c_in in range(inputs.shape[0]):
                img_patch = []
                for h in range(kernel_size[0]):
                    for w in range(kernel_size[1]):
                        img_patch.append(inputs[c_in, j+h, k+w])
                out_pixel = qnode(torch.tensor(img_patch), params[i])
            out[:, j//stride[0], k//stride[1]] = torch.tensor(out_pixel)
    return out

class QCNN_torch(torch.nn.Module):
    def __init__ (self, cfg):
        super(). __init__ ()
        n_quibit = sum(cfg.MODEL.QCNN.KERNEL_SIZE)
        self.DIM = cfg.MODEL.QCNN.DIM
        dev = qml.device(cfg.CIRCUIT.BACKEND, wires=n_quibit)
        self.qnode = qml.QNode(qconv_kernel, dev, interface='torch')
        self.qconv_param = []
        for i in range(len(self.DIM)-1):
            param_weight = np.random.uniform(0, 2*math.pi, shape1*shape2)
            param_weight = np.reshape(param_weight, (shape1, shape2))
            param_weight = torch.nn.Parameter(torch.tensor(param_weight, requires_grad=True))
            self.register_parameter('layer'+str(i+1), param_weight)
            self.qconv_param.append(param_weight)

        # FC
        n_feat = ((28//(2**(len(self.DIM)-1)))**2) * self.DIM[-1]
        stdv = 1./n_feat
        self.fc = np.random.uniform(-stdv, stdv, n_feat*10)
        self.fc = np.reshape(self.fc, (n_feat, 10))
        self.fc = torch.nn.Parameter(torch.FloatTensor(self.fc))

    def forward(self, x):
        out = []
        for b in range(len(x)):
            bx = x[b]
            for i in range(len(self.DIM)-1):
                bx = qconv_torch(bx, self.qconv_param[i], self.qnode, n_in_channels=self.DIM[i])
            out.append(bx.flatten().unsqueeze(0) @ self.fc)
        return torch.cat(out, dim=0)
if __name__ ==' __main__':
    opt = get_opt()
    cfg = get_config(opt.config_file)

    loss_fn = torch.nn.CrossEntropyLoss()

    qcnn = QCNN_torch(cfg)
    optimizer = torch.optim.Adam(params=qcnn.parameters(), lr=0.1)
    optimizer.zero_grad()

    inputs = torch.rand(4, 1, 28, 28)
    out = qcnn(inputs)
    
    loss = loss_fn(out, torch.LongTensor([1, 2, 3, 4]))
    optimizer.param_groups[0]['params'][0].retain_grad()
    loss.backward()
    optimizer.step()

```

The problem is that I can only get the gradient of `qcnn.fc` but not other parameters.

Any suggestions are helpful. Thank you in advance.

---

<div class="post-metadata">

**Author:** ![josh](https://yyz2.discourse-cdn.com/flex012/user_avatar/discuss.pennylane.ai/josh/32/100_2.png) [@josh](https://discuss.pennylane.ai/u/josh)\
**Post date:** [March 16, 2021, 12:42pm UTC](https://discuss.pennylane.ai/t/gradient-of-learnable-circuit-parameters-is-none-when-using-torch-interface/924/2 "2021-03-16T12:42:18Z")

</div>

Hi @Yang! Welcome to the forum 🙂

Would you be able to reduce your code example above to a minimal, non-working example? That is, by removing parts of the code to make the example as small as possible.

This will help us pin down exactly what might be going wrong!

---

<div class="post-metadata">

**Author:** ![Yang](https://yyz2.discourse-cdn.com/flex012/user_avatar/discuss.pennylane.ai/yang/32/489_2.png) [@Yang](https://discuss.pennylane.ai/u/Yang)\
**Post date:** [March 16, 2021, 1:08pm UTC](https://discuss.pennylane.ai/t/gradient-of-learnable-circuit-parameters-is-none-when-using-torch-interface/924/3 "2021-03-16T13:08:14Z")

</div>

Yes, I removed some unnecessary parts of code. Because the failure of gradient propagation may result from the tensor assignment operation, I keep most of them. Hope it is clear and short enough.

---

<div class="post-metadata">

**Author:** ![Yang](https://yyz2.discourse-cdn.com/flex012/user_avatar/discuss.pennylane.ai/yang/32/489_2.png) [@Yang](https://discuss.pennylane.ai/u/Yang)\
**Post date:** [March 17, 2021, 7:02am UTC](https://discuss.pennylane.ai/t/gradient-of-learnable-circuit-parameters-is-none-when-using-torch-interface/924/4 "2021-03-17T07:02:58Z")

</div>

Hi @josh. Thank you for your concern. I have solved this problem. It’s more about pytorch operations rather than pennylane. Could you please delete this topic?

---

<div class="post-metadata">

**Author:** ![josh](https://yyz2.discourse-cdn.com/flex012/user_avatar/discuss.pennylane.ai/josh/32/100_2.png) [@josh](https://discuss.pennylane.ai/u/josh)\
**Post date:** [March 19, 2021, 5:41am UTC](https://discuss.pennylane.ai/t/gradient-of-learnable-circuit-parameters-is-none-when-using-torch-interface/924/5 "2021-03-19T05:41:37Z")

</div>

No worries @Yang, I will close the topic. Feel free to open a new thread if you have any other questions!

---

<div class="post-metadata">

**Author:** ![josh](https://yyz2.discourse-cdn.com/flex012/user_avatar/discuss.pennylane.ai/josh/32/100_2.png) [@josh](https://discuss.pennylane.ai/u/josh)\
**Post date:** [March 19, 2021, 5:41am UTC](https://discuss.pennylane.ai/t/gradient-of-learnable-circuit-parameters-is-none-when-using-torch-interface/924/6 "2021-03-19T05:41:41Z")

</div>