82,247 questions
Advice
0
votes
0
replies
29
views
How should I balance DSA, ML fundamentals, PyTorch implementation, and Kaggle practice for ML Engineer interviews?
I’m a Computer Science graduate preparing for ML/AI Engineer roles.
I’m facing a dilemma about what to focus on, how much to allocate time to each area, and what exact roadmap to follow to prepare ...
1
vote
2
answers
99
views
getting a tensor of shape (32,) instead of a single value as a label
when i try to print/plt.tile the label of an image, its printing the tensor(32,) instead of a single label value. When i tried to print before the resizing, it was printing fine.
Code:
####
# ...
1
vote
0
answers
32
views
what is the purpose of training=True argument? Is it an argument of keras.sequential() or not? [duplicate]
What is the purpose of training=True argument in the last line. I called help(tf.keras.Sequential) but could not find anything related to it. Also is it the argument of tf.keras.Sequential() or not
...
-2
votes
1
answer
84
views
NameError: name 'y' is not defined Tensorflow Dataset .map() Function Error [closed]
I just loaded the tensorflow dataset "cats vs dogs". Train, Test and Validation split is done nicely but as soon as i apply the .map() function on the split dataset i get name error as:
-----...
2
votes
1
answer
46
views
Tensorflow images guide not working in Google Colab
I'm trying to run the first guide from Tensorflow in Google Colab.
I import the dataset with
import pathlib
dataset_url = "https://storage.googleapis.com/download.tensorflow.org/example_images/...
1
vote
0
answers
70
views
ImportError: cannot import name 'model_lib_v2' from 'object_detection'
I'm attempting to train a model on TensorFlow, and I've used Nick's video as reference:
https://youtu.be/yqkISICHH-U?si=IYW6Jsqhs0gCwMyc&t=8267
I've experienced following error:
Traceback (most ...
-5
votes
0
answers
71
views
How to use gpu on tensorflow [closed]
i have a fairly new GPU (5060 Ti) and i've tried to make tensorflow use it for a project. However, it doesnt see the gpu and i've ran out of ideas to try. Any help would be appreciated. Cuda is ...
0
votes
0
answers
19
views
Unable to install tensorflow in mac [duplicate]
ERROR: Could not find a version that satisfies the requirement tensorflow (from versions: none)
ERROR: No matching distribution found for tensorflow
1
vote
1
answer
39
views
TensorFlow Custom Training Loop with Mixed Precision Causing NaN Loss After Epoch 15
I am implementing a custom training loop in TensorFlow 2.18 with mixed precision (float16) for a large vision transformer model. The training runs fine for about 15 epochs, but then the loss suddenly ...
1
vote
1
answer
40
views
How to display the basic tensorflow Graph with trace_on() and trace_export() by tensorboard without the 'profiler' error?
I would like to learn the tensorflow. While, when I run the code in my google-colab, I had the error message:
'UnavailableError: Cannot export profiling results. No profiler is running.'.
The code is ...
0
votes
2
answers
137
views
TensorFlow not detecting NVIDIA GPU (RTX 3050, CUDA 12.7, TF 2.20.0) [duplicate]
I’ve been trying to get TensorFlow to use my GPU on Windows, and even though everything seems installed correctly, it shows 0 available GPUs.
System setup
Windows 11
RTX 3050 Laptop GPU
NVIDIA driver ...
1
vote
1
answer
62
views
Why GenPareto from Scipy and Tensorflow-Probability show difference?
I'm trying to understand why the Generalized Pareto distribution shows different results for the same parameters. The results from SciPy make sense, while the results from TensorFlow Probability do ...
0
votes
1
answer
33
views
Pretrained ESRGAN (.pb) gives reddish or purple image — is this a preprocessing issue or model issue?
I'm trying to use a pretrained ESRGAN model that I downloaded in .pb format.
The model runs without errors, but the output image has a noticeable reddish/purple tint instead of the correct colors.
...
3
votes
0
answers
53
views
@tensorflow-models/face-landmarks-detection no longer works with tfjs. 403 error in network request for model
I get an error while trying to run tfjs. It was working last week but it seems that the url for model is no longer available. Any suggestions for working model url/refactor?
import {
createDetector,
...
1
vote
1
answer
146
views
Play Console warning: “Library that does not support 16 KB: base/lib/x86_64/libtensorflowlite_jni.so” when uploading AAB with TensorFlow Lite
I’m uploading my Android App Bundle (AAB) to Google Play Console and getting this warning:
Library that does not support 16 KB:
base/lib/x86_64/libtensorflowlite_jni.so after upgrading the lib
...