**This is my model function.**

def mx_model_output_grad(mx_model, x, labels_batch):

x = nd.array(x.cpu().detach().numpy(), ctx=mx.gpu())

labels_batch = nd.array(labels_batch.detach().numpy())

x_ = mx.io.DataBatch(data=(x,), label=(labels_batch,))

mx_model.forward(x_, is_train=False)

x_feature = mx_model.get_outputs()

return x, x_feature

**This is my loss**

consin_loss = gluon.loss.CosineEmbeddingLoss()

```
adv_x_nd, adv_feature = mx_model_output_grad(mx_model,adv_x,labels_batch)
adv_x_nd.attach_grad()
#adv_feature.attach_grad()
temp = nd.ones((1)).as_in_context(mx.gpu())
temp_label = -nd.ones((1)).as_in_context(mx.gpu())
adv_feature = adv_feature[0].as_in_context(mx.gpu())
with autograd.record():
Loss = -consin_loss(target_feature[0], adv_feature[0], temp_label, temp)
#np.dot(target_feature,adv_feature)/(np.linalg.norm(target_feature)*(np.linalg.norm(adv_feature)))
#adv_x_nd = nd.array(adv_x.cpu().detach().numpy())
#adv_x_nd.attach_grad()
#Loss = -adv_out[0][target]
Loss.backward(retain_graph=True)
```

**But, I get this error.**

mxnet.base.MXNetError: [07:33:57] src/imperative/imperative.cc:285: Check failed: !AGInfo::IsNone(*i) Cannot differentiate node because it is not in a computational graph. You need to set is_recording to true or use autograd.record() to save computational graphs for backward. If you want to differentiate the same graph twice, you need to pass retain_graph=True to backward.