I have a numpy array list something like the follows:
a=np.array([tf.convert_to_tensor(1),tf.convert_to_tensor(2)])
I want to convert this list into a tensor.
My real list is not like the constant example but some complex tensor, so does anyone know how to do this?
I assume all of the tensors have the same shape. Then you can just call tf.stack:
>>> print(tf.stack([tf.convert_to_tensor(1), tf.convert_to_tensor(2)]))
Tensor("stack:0", shape=(2,), dtype=int32)
Note that it accepts the list, not numpy array.
Related
I have a pandas dataframe containing np.arrays in each cell (see the photo to understand better). Each array is 1000 samples long. However, when trying to use this as a training data in LSTM, it won't go through. enter image description here
model.fit(x_train, y_train, epochs = 15)
ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type numpy.ndarray).
How do I tackle this? Can't find an answer elsewhere, tried this:
x_train=np.asarray(x_train).astype(np.float32)
but it failed due ValueError: setting an array element with a sequence.
Is there another way to use this sort of numpy arrays as input?
I was trying to train LSTM with my pandas dataframe data containing 1000 sample long np.arrays
I tried searching for the documentation online but I can't find anything that gives me an answer. What does .numpy() function do? The example code given is:
y_true = []
for X_batch, y_batch in mnist_test:
y_true.append(y_batch.numpy()[0].tolist())
Both in Pytorch and Tensorflow, the .numpy() method is pretty much straightforward. It converts a tensor object into an numpy.ndarray object. This implicitly means that the converted tensor will be now processed on the CPU.
Ever getting a problem understanding some PyTorch function you may ask help().
import torch
t = torch.tensor([1,2,3])
help(t.numpy)
Out:
Help on built-in function numpy:
numpy(...) method of torch.Tensor instance
numpy() -> numpy.ndarray
Returns :attr:`self` tensor as a NumPy :class:`ndarray`. This tensor and the
returned :class:`ndarray` share the same underlying storage. Changes to
:attr:`self` tensor will be reflected in the :class:`ndarray` and vice versa.
This numpy() function is the converter form torch.Tensor to numpy array.
If we look at this code below, we see a simple example where the .numpy() convert Tensors to numpy arrays automatically.
import numpy as np
ndarray = np.ones([3, 3])
print("TensorFlow operations convert numpy arrays to Tensors automatically")
tensor = tf.multiply(ndarray, 42)
print(tensor)
print("And NumPy operations convert Tensors to numpy arrays automatically")
print(np.add(tensor, 1))
print("The .numpy() method explicitly converts a Tensor to a numpy array")
print(tensor.numpy())
In the 2nd last line of code, we see that the tensorflow officials declared it as the converter of Tensor to a numpy array.
You may check it out here
I have a generator that yields tf.sparse.SparseTensors. I want to turn this into a Tensorflow Dataset, but am running into some issues. I am using TF2. First, unlike regular Tensors, you cannot simply pass them in (and providing the correct data types for output_types). For a sparse tensor of [1,0,0,0,5,0], the error looks like
tensorflow.python.framework.errors_impl.InvalidArgumentError: TypeError: `generator` yielded an element that could not be converted to the expected type. The expected type was int64, but the yielded element was SparseTensor(indices=tf.Tensor(
E [[0]
E [4]], shape=(2, 1), dtype=int64), values=tf.Tensor([1 5], shape=(2,), dtype=int64), dense_shape=tf.Tensor([6], shape=(1,), dtype=int64)).
After doing some looking around on the internet, I found this open issue and tried to do something similar https://github.com/tensorflow/tensorflow/issues/16689 - read the indices, values, and shape as separate tensors into a TF Dataset, and then mapping over the dataset to create the sparse tensor. This is not working as shown in some of the examples in the github issue - tf.sparse.SparseTensor(indices, values, shape) does not seem to accept indices and shape in the form of a tf.Tensor - it will happily take in a list or numpy array, but not a Tensor. Since map is not eager, I also cannot call .numpy() on the Tensor either. What is best way to get this to work? I see there is tf.py_function/tf.numpy_function which could help, but constructing the output type can be tricky (though not impossible) for my use case - the incoming data is not fixed and can have a mix of sparse and dense tensors.
I have a 28x28 pixel image as a numpy array and its shape is (28,28) using the np.array.shape function. I want the shape to be 784x1. In other words with a NxN matrix how do you convert it to a N^2x1. Using the flatten function i get almost what I'm looking for, the shape from flatten is (784,).
Another possible way is to use np.atleast_2d
np.atleast_2d(arr.flatten())
I'm creating a layer which uses its input tensors to create a SparseTensor, i.e., the input tensors are the respective indices and values of the SparseTensor.
Since:
indices: A 2-D int64 tensor of shape
And because tf.cast(x, tf.int64) is not differentiable, I'm not sure if this is achievable.
Another option is to find a turnaround based on tf.round(), but SparseTensor won't accept a different type of tensor as indices.
Is there a way to cast a tensor to integer and not having None for gradient ?
How can I create a SparseTensor using previous layers outputs, which are float tensors ?