# TypeError: unhashable type: 'numpy.ndarray' **URL:** \ **Category:** PennyLane Help\ **Created:** [April 30, 2021, 4:30pm UTC](https://discuss.pennylane.ai/t/typeerror-unhashable-type-numpy-ndarray/1012 "2021-04-30T16:30:36Z")\ **Posts on this page:** 4\ **Page:** 1
**Author:** ![Alice\_Wong](https://yyz2.discourse-cdn.com/flex012/user_avatar/discuss.pennylane.ai/alice_wong/32/505_2.png) [@Alice\_Wong](https://discuss.pennylane.ai/u/Alice_Wong)\ **Post date:** [April 30, 2021, 4:30pm UTC](https://discuss.pennylane.ai/t/typeerror-unhashable-type-numpy-ndarray/1012/1 "2021-04-30T16:30:36Z")
Hi guys, I am working on classification problem with Gaussian state as input features. ```auto dev = qml.device('strawberryfields.fock', wires=3, cutoff_dim=10) @qml.qnode(dev) def quantum_neural_net(pars,cm): mean_vector=np.array([[0.0], [0.0], [0.0], [0.0]]) cm=cm.reshape((4,4)) qml.GaussianState(cm, mean_vector, wires=range(2)) CVNeuralNetLayers(*pars,wires=range(3)) return qml.expval(qml.X(0)) ``` The definitions of mean square error function and cost function I used are same as [https://pennylane.ai/qml/demos/tutorial\_variational\_classifier.html](https://pennylane.ai/qml/demos/tutorial_variational_classifier.html) ```auto def square_loss(labels, predictions): loss = 0 for l, p in zip(labels, predictions): loss = loss + (l - p) ** 2 loss = loss / len(labels) return loss def cost(weights, cov_matrix, labels): predictions = [quantum_neural_net(weights, f) for f in cov_matrix] return square_loss(labels, predictions) ``` I use AdamOptimizer for optimization but return error "unhashable type: ‘numpy.ndarray’ " ```auto init_pars=cvqnn_layers_all(n_layers=2, n_wires=3, seed= None) opt = AdamOptimizer(0.01, beta1=0.9, beta2=0.999) var = init_pars for i in range(10): var = opt.step(lambda v: cost(v, xtr,ytr), var) #xtr,ytr are training dataset and training labels, respectively . predictions_train = [np.sign(quantum_neural_net(var,cm)) for cm in xtr] print(i + 1, cost(var, xtr, ytr)) ``` As some solutions I found, I rewrited the cost function as: ```auto def cost(weights, cov_matrix, labels): predictions=np.zeros((len(labels),1), dtype=object) for i in range(len(labels)): predictions[i,0]= quantum_neural_net(weights, cov_matrix[i,:]) return square_loss(labels, predictions) ``` It can run now, but with warning " the output seems independent with input" and unexpected outputs : ```auto 1 [tensor(0.69090221, requires_grad=True)] 2 [tensor(0.69090221, requires_grad=True)] 3 [tensor(0.69090221, requires_grad=True)] 4 [tensor(0.69090221, requires_grad=True)] 5 [tensor(0.69090221, requires_grad=True)] 6 [tensor(0.69090221, requires_grad=True)] 7 [tensor(0.69090221, requires_grad=True)] 8 [tensor(0.69090221, requires_grad=True)] 9 [tensor(0.69090221, requires_grad=True)] 10 [tensor(0.69090221, requires_grad=True)] ``` ---
**Author:** ![sjahangiri](https://yyz2.discourse-cdn.com/flex012/user_avatar/discuss.pennylane.ai/sjahangiri/32/1443_2.png) [@sjahangiri](https://discuss.pennylane.ai/u/sjahangiri)\ **Post date:** [April 30, 2021, 10:30pm UTC](https://discuss.pennylane.ai/t/typeerror-unhashable-type-numpy-ndarray/1012/2 "2021-04-30T22:30:16Z")
Hi @Alice_Wong and welcome to the forum! I could not reproduce the errors you reported since the code you shared is incomplete. Could you please share minimal working/non-working examples so I can have a deeper look at the code and the errors? Thanks. ---
**Author:** ![Alice\_Wong](https://yyz2.discourse-cdn.com/flex012/user_avatar/discuss.pennylane.ai/alice_wong/32/505_2.png) [@Alice\_Wong](https://discuss.pennylane.ai/u/Alice_Wong)\ **Post date:** [May 1, 2021, 12:19am UTC](https://discuss.pennylane.ai/t/typeerror-unhashable-type-numpy-ndarray/1012/3 "2021-05-01T00:19:18Z")
Thanks for your reply! The document is the dataset I used. [gaussian\_classification.txt](https://discuss.pennylane.ai/uploads/short-url/eCX1ho4BxVjEHv4boCZ5pffYcHE.txt) (104.3 KB) Here is the full code which non-working with TypeError: ```auto import pennylane as qml from pennylane import numpy as np from pennylane.templates.layers import CVNeuralNetLayers from pennylane.init import cvqnn_layers_all from pennylane.optimize import AdamOptimizer ``` ```auto import pickle as pkl with open('./gaussian_classification.txt', 'rb') as f1: data=pkl.load(f1) XX=data[:,0:16] YY=data[:,16] # shift label from {0, 1} to {-1, 1} YY = YY* 2 - np.ones((len(YY))) #15%data from original dataset np.random.seed(0) num_data = len(YY) num_train = int(0.15 * num_data) index = np.random.permutation(range(num_data)) xtr = XX[index[:num_train]] ytr = YY[index[:num_train]] xt = XX[index[num_train:]] yt = YY[index[num_train:]] ``` ```auto dev = qml.device('strawberryfields.fock', wires=3, cutoff_dim=10) @qml.qnode(dev) def quantum_neural_net(pars,cm): mean_vector=np.array([[0.0], [0.0], [0.0], [0.0]]) cm=cm.reshape((4,4)) qml.GaussianState(cm, mean_vector, wires=range(2)) CVNeuralNetLayers(*pars,wires=range(3)) return qml.expval(qml.X(0)) ``` ```auto def square_loss(labels, predictions): loss = 0 for l, p in zip(labels, predictions): loss = loss + (l - p) ** 2 loss = loss / len(labels) return loss def cost(weights, cov_matrix, labels): predictions = [quantum_neural_net(weights, f) for f in cov_matrix] return square_loss(labels, predictions) ``` ```auto init_pars=cvqnn_layers_all(n_layers=2, n_wires=3, seed= None) opt = AdamOptimizer(0.01, beta1=0.9, beta2=0.999) var = init_pars for it in range(10): var = opt.step(lambda v: cost(v, xtr,ytr), var) predictions_train = [np.sign(quantum_neural_net(var,cm)) for cm in xtr] print(it + 1, cost(var, xtr, ytr)) ``` ---
**Author:** ![sjahangiri](https://yyz2.discourse-cdn.com/flex012/user_avatar/discuss.pennylane.ai/sjahangiri/32/1443_2.png) [@sjahangiri](https://discuss.pennylane.ai/u/sjahangiri)\ **Post date:** [May 1, 2021, 10:44pm UTC](https://discuss.pennylane.ai/t/typeerror-unhashable-type-numpy-ndarray/1012/4 "2021-05-01T22:44:46Z")
Thanks @Alice_Wong for the code. The vector of means created in the `quantum_neural_net` function should be an array containing the mean position and momentum quadrature of each mode. You currently have an array of lists which I believe is the reason for getting that error. Please define `mean_vector` as `mean_vector = np.array([0.0, 0.0, 0.0, 0.0])` to get correct outputs. Please let me know if you have any other questions.