Stack Overflow
Stack Overflow

Questions tagged [ragged-tensors]

44 questions
8
votes
2 answers

Broadcast and concatenate ragged tensors

I have a ragged tensor of dimensions [BATCH_SIZE, TIME_STEPS, EMBEDDING_DIM]. I want to augment the last axis with data from another tensor of shape [BATCH_SIZE, AUG_DIM]. Each time step of a given example gets augmented with the same value. If the…
JuliettVictor
  • 614
  • 5
  • 14
3
votes
1 answer

Ragged Tensors have no len() after conversion to Tensor

I am training a deep learning model on stacks of images with variable dimensions. (Shape = [Batch, None, 256, 256, 1]), where None can be variable. I use tf.RaggedTensor.merge_dimsions(0,1) to convert the ragged Tensor to a shape of [None, 256,…
Wayne
  • 31
  • 2
3
votes
0 answers

RaggedTensor on TPU

I am trying to train a neural network using TensorFlow that takes as input (tf.keras.layers.Input) a RaggedTensor. It works fine on CPU and GPU but I am really strugling to make it work on TPU. I wanted to know if some of you managed to make it work…
Vince.Bdn
  • 1,145
  • 1
  • 13
  • 28
2
votes
1 answer

Tensorflow dataset with variable number of elements

I need a dataset structured to handle a variable number of input images (a set of images) to regress against an integer target variable. The code I am using to source the images is like this: import tensorflow as tf from tensorflow import…
Alberto
  • 467
  • 3
  • 16
2
votes
0 answers

How to provide two inputs to a Tensorflow Model using ragged tensors?

I am trying to create a model with two inputs. The model is very simple containing only one lstm layer for each input. The problem is that I want to provide lists of different length as inputs. For that, I am using ragged tensors, but the training…
psitronic
  • 21
  • 2
2
votes
0 answers

'RaggedTensor' object has no attribute 'set_shape' when passing RaggedTensor to BatchNormalization layer in Tensorflow 2.8

I am trying to pass a 3D RaggedTensor of shape (batch_size=None, 1, 136) to a batch normalization layer, but am receiving the error in the title. I assume because RaggedTensors can very in dimensions, and thus have no set_shape() method as it would…
Jage
  • 453
  • 2
  • 9
2
votes
2 answers

RaggedTensor request to TensorFlow serving fails

I've created a TensorFlow model that uses RaggedTensors. Model works fine and when calling model.predict and I get the expected results. input = tf.ragged.constant([[[-0.9984272718429565, -0.9422321319580078, -0.27657580375671387,…
Shlomi Schwartz
  • 8,693
  • 29
  • 109
  • 186
1
vote
0 answers

How to feed Images of different size being into the CNN

The problem being solved is a binary classification using CNN. Here I have images of different size. I am scaled down the images to 20% and normalizing them to the range (0,1) and obviously they still have different sizes. I am using x_train =…
Chetan
  • 11
  • 3
1
vote
1 answer

Correct way to iterate over Keras ragged tensor

I have an input Tensorflow ragged tensor structured like this [batch num_images width height channels] and I need to iterate over the dimension num_images to extract some features relevant for downstream applications. Example code is the…
Alberto
  • 467
  • 3
  • 16
1
vote
0 answers

Setting shape of RaggedTensor with Known Shape

I'm working with RaggedTensors to manipulate a dense tensor. Something like this : out_left = tf.ragged.boolean_mask(input, index) index = tf.math.logical_not(index) out_right = tf.ragged.boolean_mask(input, index) …
Liam F-A
  • 135
  • 11
1
vote
1 answer

strip and filter strings in ragged tensor

I would like learn if there is a decent and tensorflownic way to do follow conversion. Basically each string(row) as several words, and each word has a suffix like "%1", and goal is to strip string and only leave words with suffix value <= certain…
user1269298
  • 717
  • 2
  • 8
  • 26
1
vote
0 answers

Dense layer only supports RaggedTensors when the innermost dimension is non-ragged. Received: inputs.shape=(None, None, None)

I have a tf.data.dataset with 2 and 3 dimensional ragged tensors: [ [1,2,3,4], [5,6,7,8], ... ] and [ [[1,2,3], [4,5,6] ], [[7,8,9], [10,11,12], ... ] ] I receive the error in the title when passing the…
Jage
  • 453
  • 2
  • 9
1
vote
1 answer

how to pad sequences in a tensor slice dataset in TensorFlow?

I have a tensor slice dataset made from two ragged tensors. tensor_a is like: tensor_b is like: (Same…
pieckannie
  • 33
  • 3
1
vote
1 answer

Sample from ragged tensor

I have a raggedTensor of row_lens going from 1 to up to 10k. I would like to select elements randomly from it with an upper limit on the number per row in a scalable way. Like in this example: vect = [[1,2,3],[4,5][6],[7,8,9,10,11,12,13]] limit =…
Nodiz
  • 333
  • 2
  • 8
1
vote
1 answer

IndexError: Dimension out of range (expected to be in range of [-2, 1], but got 3)

I created a random function with the line below x = torch.randn(4, 3) and used the transpose function as shown here torch.transpose(x, 0, 1) I got the error line below. Who can assist with a solution IndexError …
Lamosh
  • 41
  • 5
1
2 3