42,347 questions
0
votes
0
answers
16
views
MobileNet dynamic range quantization breaks model accuracy
I've been working on building a binary fire detection model based on TF keras MobileNet v2 and transfer trained from ImageNet weights. After training the model and inferencing it works well with about ...
- 77
0
votes
0
answers
26
views
Trouble loading tensorflow when running cloned repo
So, I'm trying to get the code from this repo https://github.com/amin20/GBM_WSSM working but I'm running into a persistent error.
Using TensorFlow backend.
Traceback (most recent call last):
File &...
0
votes
0
answers
37
views
model.predict hangs in celery/uwsgi
import numpy as np
import tensorflow as tf
import tensorflow_hub as hub
from apps.common.utils.error_handling import suppress_callable_to_sentry
from django.conf import settings
from threading import ...
- 3,002
1
vote
0
answers
65
views
my clasification A.I. model cant surpass a certain validation precision threshold
I've recently getting started with A.I. and for a project i wanted to create a model that can classify what kind of disease you have based on a chest x-ray, After writing the model and using the ...
- 111
0
votes
0
answers
16
views
Keras 3 equivalent of getting inbound layers of a given layer
I would like to get the inputs of a given layer linked to a previous layer.
My code with Keras 2.x was the following
def get_inputs(layer):
"""Get the inputs of a layer.""&...
- 13k
0
votes
0
answers
30
views
When I use multiple ImageInput，errors happened [closed]
my code:
inputEle = [ak.ImageInput(name='n1'),ak.ImageInput(name='n2'),
ak.ImageInput(name='n3'),ak.ImageInput(name='n4')]
outputEle = [ak.ClassificationHead(name='n7')]
am =...
0
votes
0
answers
25
views
Why does TimeDistributed(Flatten()) raise an InvalidArgumentError when reshaping works?
I'm building a lip-reading model using tensorflow.keras and getting an error when applying TimeDistributed(Flatten()) after my Conv3D layers. Here's a simplified version of my model architecture:
CODE
...
-3
votes
0
answers
101
views
xor example tensorflow C api
Simple xor functions. How load model using https://www.tensorflow.org/install/lang_c .
#!/usr/bin/env python
import numpy as np
import tensorflow as tf
X = np.array([[0, 0], [0, 1], [1, 0], [1, 1]], ...
- 51
0
votes
0
answers
47
views
Changing model parameters to get accurate predictions from RNN model in R
I am trying to create a RNN model in R. I have ~300 samples with the array dimensions as follows c(300, 10500, 6) reflecting (sample, time_steps, num_of_features). The labels is a single numerical ...
- 557
0
votes
0
answers
25
views
Keras SKLearnClassifier wrapper can't fit MNIST data
I'm trying to use the SKLearnClassifier Keras wrapper to do some grid searching and cross validation using the sklearn library but I'm unable to get the model to work properly.
def build_model(X, y, ...
1
vote
1
answer
16
views
TimeDistributed layer in keras 3 showing very slow inference
Inference with TimeDistributed(Dense(1, activation="sigmoid")) in Keras 3 is a lot slower than in Keras 2 (tf.keras) Profiling shows TimeDistributed is the bottleneck.
Model: Conv1D → LSTM → ...
- 13
-4
votes
0
answers
58
views
Problem with 80% accuracy(I need to get 90%) and I have fight it for hours [closed]
Good night, people . I’ve been fighting with this model for 3 hoours and can’t get validation accuracy higher than ≈ 78 – 82 %. My goal is at least 90 %.
1 . Dataset
Rows: 3 000
Features: 25 Likert‑...
-2
votes
1
answer
39
views
Why is my TensorFlow CNN OCR model outputting incorrect characters for Persian license plates? [closed]
I’m building a FastAPI web API to detect Persian car license plates using YOLOv8 and extract their text with a custom TensorFlow CNN OCR model. YOLOv8 correctly detects the plate’s bounding box, but ...
2
votes
1
answer
51
views
Cannot see all `Dense` layer info from `search_space_summary()` when using `RandomSearch Tuner` in Keras-Tuner?
I am trying to use keras-tuner to tune hyperparameters, like
!pip install keras-tuner --upgrade
import keras_tuner as kt
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers ...
- 104k
0
votes
1
answer
57
views
Why do model.evaluate() vs. manual loss computation with model.predict() in tf.keras do not add up?
I use keras and tensorflow to train a 'simple' Multilayer Perceptron (MLP) for a regression task, where I use the mean-squared error (MSE) as loss-function. I denote my training data as x_train, ...
- 113