Menu
I am new in tensorflow and Python. I have an image data set in Matlab in a tensor with size : 96*96*5000 (image size , number of images) and I need to import it to Tensorflow. I looked at the Tensorflow tutorial, which says I should use TFRecords or CSV formats but I think this means that I save each image separately in csv format. Is there any way to directly import my tensor to tensorflow?
555
The base tf$Tensor class requires tensors to be “rectangular”—that is, along each axis, every element is the same size. However, there are specialized types of tensors that can handle different shapes: Ragged tensors (see RaggedTensor below)
Tensors are multi-dimensional arrays with a uniform type (called a dtype ). You can see all supported dtypes at tf. dtypes. DType . If you're familiar with NumPy, tensors are (kind of) like np.
A tensor can be described as a n-dimensional numerical array. A tensor can be called a generalized matrix. It could be a 0-D matrix (a single number), 1-D matrix (a vector), 2-D matrix or any higher dimensional structure. A tensor is identified by three parameters viz., rank, shape and size.
As Olivier said in his comment, the easiest solution is to convert the data into a Numpy array, and use TensorFlow's feeding mechanism to pass the data into your TensorFlow model.
The scipy.io.loadmat() function in SciPy can be used to load a Matlab .mat file into Python, as a dictionary mapping Matlab matrix names (as strings) to Numpy arrays.
68
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With
