All Questions
Tagged with machine-learning keras
7,500 questions
0
votes
0
answers
6
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 ...
- 69
-1
votes
0
answers
51
views
Does the fact that i have just train, test split using keras image_from_dataset affect my metrics
I've been trying to figure out why my metrics were low after training. I had an F1 score of 75% which is not what i expected at all. I reviewed the code and I suspected the issue was the train, ...
- 1
2
votes
1
answer
82
views
How to compile and run a model in Keras subclassing API?
I am learning to use the TensorFlow Recommenders library and the subclassing API and have been working through the documentation. I would like to know how to run and review the output of the ...
- 23
2
votes
0
answers
33
views
Conversion of model weights from old Keras version to Pytorch
I want to transfer pretrained weights from an old project on github : https://github.com/ajgallego/staff-lines-removal
The original Keras model code is:
def get_keras_autoencoder(self, input_size=256, ...
- 373
0
votes
1
answer
52
views
Why won't tf.keras let me pass a dictionary of multiple sample weights?
I am trying to pass individual np.arrays of sample_weights for two outputs of my Keras model, one of which is a confidence measure of a binary value and one of which is a continuous output. However, I ...
1
vote
1
answer
90
views
Unable to get Keras CV Object Detector (Yolov8) to perform as well as Ultralytics [closed]
I followed the published Keras CV computer vision tutorial (https://keras.io/examples/vision/yolov8/) using the YOLO V8 detector with a custom dataset and have ran into a couple of issues I was hoping ...
- 11
0
votes
0
answers
56
views
Tensorflow Keras model with interleave is having issues fitting
I'm working on a CNN project where I make use of TensorFlow and Keras. In addition, I use interleave as the dataset is rather large (too large to load into the RAM with our resources). But there's an ...
- 85
-1
votes
1
answer
94
views
ResNet50 on TPU calculates NaN for accuracy and loss, works fine on CPU in Google Colab
I've trained a ResNet50 on v2-8 TPU accelerator using google colab, I've fed it with 5000 images of shape (224, 224, 3). I've normalized them, no nans, no inf, no class imbalance and everything is ...
1
vote
2
answers
68
views
Why does my Keras model show 4 parameters instead of 2?
I'm training a simple Keras model with one Dense layer, but when I call model.summary(), it shows 4 parameters instead of 2.
import tensorflow as tf
import numpy as np
# Generate dummy data
X_train = ...
- 50.1k
1
vote
1
answer
86
views
numpy eager execution problem after loading a CNN model
I want to save and load a CNN model to further training. I have developed a model and saved it as .h5 file. There is no problem when creating, training, and saving at first run.
The problem exists ...
0
votes
1
answer
25
views
Train LSTM for time series with varying lengths
I'm training a LSTM for time series prediction, where data comes from sensors at irregular intervals. I'm using the last 5 min data to predict the next value, but some sequences are larger than others....
- 11
1
vote
0
answers
59
views
Non deterministic behavior of a CNN network after adding self attention
When I added NLBloclos, a self-attention layer to my network (simple CNN) the result of the network was not reproducible anymore, when I trained it again, the result was different. But when I remove ...
- 11
9
votes
1
answer
264
views
Clearing tf.data.Dataset from GPU memory
I'm running into an issue when implementing a training loop that uses a tf.data.Dataset as input to a Keras model. My dataset has an element spec of the following format:
({'data': TensorSpec(shape=(...
- 1,222
1
vote
1
answer
68
views
How to have reproducibility with Keras, Tensorflow?
I am not getting the same accuracy and loss each time I run the following code. I followed the instructions from previous posts, but I couldn't resolve it. What could be the problem?
import os
os....
- 31
0
votes
0
answers
44
views
VotingClassifier only supports binary or multiclass classification. Multilabel and multi-output classification are not supported
I got an error about KerasClassifer and VotingClassifer.
At the first, I used MNIST dataset and split it then fit xtrain and ytrain by Voting classifer. If I put their estimator type into Classifier ...
- 23