Shape must be rank 1 but is rank 2 tflearn error

buydadip picture buydadip · Nov 11, 2017 · Viewed 12.8k times · Source

I am using a DNN provided by tflearn to learn from some data. My data variable has a shape of (6605, 32) and my labels data has a shape of (6605,) which I reshape in the code below to (6605, 1)...

# Target label used for training
labels = np.array(data[label], dtype=np.float32)

# Reshape target label from (6605,) to (6605, 1)
labels = tf.reshape(labels, shape=[-1, 1])

# Data for training minus the target label.
data = np.array(data.drop(label, axis=1), dtype=np.float32)

# DNN
net = tflearn.input_data(shape=[None, 32])
net = tflearn.fully_connected(net, 32)
net = tflearn.fully_connected(net, 32)
net = tflearn.fully_connected(net, 1, activation='softmax')
net = tflearn.regression(net)

# Define model.
model = tflearn.DNN(net)
model.fit(data, labels, n_epoch=10, batch_size=16, show_metric=True)

This gives me a couple of errors, the first is...

tensorflow.python.framework.errors_impl.InvalidArgumentError: Shape must be rank 1 but is rank 2 for 'strided_slice' (op: 'StridedSlice') with input shapes: [6605,1], [1,16], [1,16], [1].

...and the second is...

During handling of the above exception, another exception occurred:

ValueError: Shape must be rank 1 but is rank 2 for 'strided_slice' (op: 'StridedSlice') with input shapes: [6605,1], [1,16], [1,16], [1].

I have no idea what rank 1 and rank 2 are, so I do not have an idea as to how to fix this issue.

Answer

Nipun Wijerathne picture Nipun Wijerathne · Nov 11, 2017

In Tensorflow, rank is the number of dimensions of a tensor (not similar to the matrix rank). As an example, following tensor has a rank of 2.

t1 = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]])
print(t1.shape) # prints (3, 3)

Moreover, following tensor has a rank of 3.

t2 = np.array([[[1, 1, 1], [2, 2, 2]], [[3, 3, 3], [4, 4, 4]]])
print(t2.shape) # prints (2, 2, 3)

Since tflearn is build on top of Tensorflow, inputs should not be tensors. I have modified your code as follows and commented where necessary.

# Target label used for training
labels = np.array(data[label], dtype=np.float32)

# Reshape target label from (6605,) to (6605, 1)
labels =np.reshape(labels,(-1,1)) #makesure the labels has the shape of (?,1)

# Data for training minus the target label.
data = np.array(data.drop(label, axis=1), dtype=np.float32)
data = np.reshape(data,(-1,32)) #makesure the data has the shape of (?,32)

# DNN
net = tflearn.input_data(shape=[None, 32])
net = tflearn.fully_connected(net, 32)
net = tflearn.fully_connected(net, 32)
net = tflearn.fully_connected(net, 1, activation='softmax')
net = tflearn.regression(net)

# Define model.
model = tflearn.DNN(net)
model.fit(data, labels, n_epoch=10, batch_size=16, show_metric=True)

Hope this helps.