All Questions
617 questions
0
votes
1
answer
47
views
Why does batch() return only one batch?
I'm beginner in image processing. I have two binary classes as subdirectory which total of 496 images and I have an issue with the last batch that has remainder of 13 images. So, instead of tf.dataset ...
- 9
0
votes
1
answer
352
views
TypeError: Binding inputs to tf.function failed, Can not cast input_tensor TensorSpec to TensorSpec
error message:
Traceback (most recent call last):
File "/home/prakrisht/-------------/detect_from_webcam.py", line 173, in <module>
run_inference(detection_model, category_index, ...
1
vote
0
answers
43
views
tf.callbacks.EarlyStopping doesn't work properly when feeding tf.data.dataset objects to the model
I set patience=5 for it to stop training if val_loss doesn't decrease for 5 epochs straight. However, training always stop at the 5th epoch, and the best weights are set to 1st epoch even though ...
- 11
0
votes
0
answers
34
views
Tensorflow custom layer accessing value of output tensor from previous layer
So I'd like to create a custom Tensorflow.Keras layer with purpose of returning label name as a text.
The previous layer is an argmax that returns integer representing the index of predicted class and ...
- 1
0
votes
0
answers
39
views
Accesing python lists inside TensorFlow graph-traceable functions
I'm trying to access a python list inside a function that can be run in eager mode or graph mode as shown below:
import tensorflow as tf
import numpy as np
class SlotGenerator:
def __init__(self):
...
- 469
1
vote
0
answers
35
views
dataset of tensors shuffled after applying map or model.predict
I am trying to predict a target image from an input image and then display both the input and prediction. For some reason, test_images seems to be reshuffled in the process so I can't get them to line ...
0
votes
0
answers
137
views
i keep getting this error : TypeError: Expected any non-tensor type, but got a tensor instead
i am trying to train mobilevit using this bee dataset from tensorflow and i keep getting this error
TypeError: Expected any non-tensor type, but got a tensor instead.
this is the code i wrote, ...
0
votes
1
answer
162
views
Tensor size does not match batch size
I have used this code below to train an unet model. My dataset at first consisted of 10000 images, shape=(256,256,3), what was working fine. However, ofter enlargening it to 14000 images i encountered ...
- 9
0
votes
0
answers
32
views
Multiple issues and errors with tensor flow array / matrix / tensor shape and data manipulation
import tensorflow as tf
import numpy as np
from tqdm import tqdm
from datasets import load_dataset
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from ...
1
vote
1
answer
47
views
Get n-th item from multi-dimensional array (python)
I have a tensor of shape (12, 19601, 1000) and I want to just take every n-th element of the second entry, I want a tensor of size (12, 19601 / n, 1000). Is there an efficient way to do this? ...
- 21
1
vote
0
answers
92
views
Interpretation of Tensorflow Probability tensor_coercible object
I have a tensorflow model (keras sequential) that ends with a Tensorflow Probability (TFP) mixture layer.
My goal is to fit this network with a custom loss function. The unexpected behaviour is the ...
- 146
0
votes
0
answers
208
views
ValueError: Attempt to convert a value (class) with an unsupported type (class) to a Tensor
these codes were running flawlessly on tensorflow==2.15, for the purpose of GPU acceleration, I switched to tensorflow-gpu == 2.10.1 with keras 2.10, respectively. and this ValueError raised up on my ...
- 331
-2
votes
1
answer
90
views
InvalidArgumentError: `predictions` contains negative values [closed]
I was trying to run the Tensorflow Audio classification code following the article of tensorflow. When I ran the following python code after finishing all above cells orderly:
Code:
confusion_mtx = ...
- 40.4k
0
votes
1
answer
75
views
Pyhton extract matrices from rank 3 tensor
I have data X_train with shape (19601, 1000, 12) but want to extract the 1000 x 12 matrices and combine/append them into one large matrix. Whenever I try to index through X_train and append the rows ...
- 21
-2
votes
1
answer
957
views
Tensorflow : could not a find a version that satisfies the requirement tensorflow
I am try to install tensorflow through pip but it showing error "could not a find a version that satisfies the requirement tensorflow"
Python 3.12.0
pip 23.3.1
i tried this cmd:
python3 -m ...
